Papers - Training Research - Clamping - a matlok Collection

matlok 's Collections

matlok - Python Copilot Image Datasets

matlok - Python Code Instruction Datasets

matlok - Python Copilot Audio Datasets

matlok - Python Src Code Datasets (base)

How to build a Python Coding Model with Alpaca Instructions

Dataset - Python Coding Alpaca Instructions

Text Instruction Papers

Multimodal Papers

Mixture of Experts Papers

Embedding Papers

Transformer Arch

LMM

LoRA

Non-English Embeddings and Models

More Alpaca Instruction Datasets

Model Benchmarking

Actor Critic Papers

Gaming Reinforcement Learning

Search papers from a url

Datasets - Geospatial

Models - Geospatial

Papers - Geospatial

Models - Biotech

Datasets - Financial

Models - Video Editing

Models - Testing

Papers - Attention

Papers - Context

Papers - Synthetic Data

Models - Fintech

Models - Multimodal

Models - MultiAgent

Models - n-gram and Kneser-Ney

Papers - NLP Research

Papers - Multi-turn Conversations

Datasets - Synthetic - Instruct

Models - Watermarking

Models - Captions

Papers - Fintech - Benchmarks

Models - Touch and Image

Datasets - Image - Text

Models - NeRFs - Image Radiance Fields

Models - Parameter Testing

Models - Predicting Models

Models - Robotics

Datasets - Coding

Models - ReAct - Reasoning and Action

Models - Custom-Training

Papers - Decoders

Papers - Testing a Coding Model

Datasets - Text

Datasets - Multimodal - Text and Images

Models - Large Scale

Papers - Coding

Papers - Transfer Learning

Datasets - Text - Multiple Choice

Datasets - Binarized

Papers - Pipeline - Multimodal

Papers - Reasoning

Models - Gaming

Papers - Learning and Compression

Papers - Conversations

Models - Quants

Models - Image - Geometric Algebra

Datasets - Math

Models - Base - 7B

Models - Base - 1B

Spaces - Vision

Datasets - Image and Bounding Box

Models - Science

Papers - Sampling

Models - Byte Transformer

Models - Cooking

Papers - Math - GSM8K

Papers - Model Scaling

Papers - Training Research

Models - UI - Front-End

Papers - Reasoning - Vision

Models - Text - Explanation

Papers - Multi-Agent

Papers - Ring Attention

Papers - Sequence Parallelism

Helpful - VRAM Calculator

Models - Audio - Translation

Models - Video Generation

Models - Image - Long Context

Papers - Masked Sequence Packing

Papers - Speculative Decoding

Papers - Fine-tuning - Multimodal

Datasets - Math - Word Problems

Spaces - Coding

Models - Audio - Music Generation

Datasets - Audio

Datasets - Audio - Fine-tuning

Models - Audio - Sheet Music Gen

Papers - Striped Attention

Datasets - Text - Instruction (non-Alpaca)

Models - Images - Instruct

Papers - Benchmarks - Image and Text

Papers - Image - Not-using CLIP

Models - Suggest - Audiobooks from Playlist

Models - MoE - IoT

Models - MoE - Mulitmodal

Papers - MoE - Research

Papers - Image - Knowledge Graphs

Papers - MoE - Training

Papers - Image - MoE

Models - Image - MoE

Papers - Lora - LCM

Models - Image - Drone Photography

Models - Image - Lora

Models - MoE - Principles

Models - MoE - Constitutional Experts

Models - MoE - Visual Relationship Detection

Models - MoE - Training using Lora

Papers - Training with Lora

Papers - MoE - Prompt Immunity

Papers - MoE - Router

Models - MoE - Audio - Underwater Acoustics

Models - MoE - Audio

Papers - MoE - Malicious Queries

Papers - MoE - Image

Models - MoE - Image

Papers - MoE - Training - Blocks

Papers - MoE - Scaling

Papers - MoE - Adversary Queries

Papers - MoE - Deny an Expert

Papers - MoE - Custom Layers

Papers - MoE - Frankenmerge

Papers - Multimodal

Papers - Image - Bounding Box

Papers - Multimodal - Documents

Papers - Exploit - Model Layer Retrieval

Papers - Image - Dataset Generator

Datasets - Text and Video

Papers - Video - Mamba

Papers - Performance Trends in AI

Papers - Fine-tuning - Home Lab

Papers - MoE - Audio

Papers - MoE - Attention

Papers - Quants

Papers - Image - MoE - IoT

Papers - MoE - Speech Recognition

Papers - MoE - Router - Task

Papers - MoE - Multilingual

Papers - MoE - Federated Learning

Papers - MoE - Training - Weight Sharing

Papers - MoE - Router - Research

Papers - Image - Handwriting Recognition

Papers - MoE - IoT

Papers - MoE - Handwriting Recognition

Papers - Image - OCR Handwriting

Papers - Image - Adversarial

Papers - Image - Segment - Handwriting

Papers - Image - Handwriting and Online Gestures

Papers - Image - Handwritten Characters

Papers - Image - Fine-tuning

Papers - Image - HTR - Math Gestures and Symbols

Papers - Image - Handwritten Generation

Models - Text - Multilingual

Models - Image - Diffusion Probabilistic Models

Papers - Benchmark - Handwriting Recognition

Papers - Image - Handwriting Recognition - Lexical Features

Datasets - Image - Handwritten Recognition

Papers - Image - Custom Layers

Papers - Image - Handwriting Recognition - Tetrolets

Papers - Image - Handwriting Recognition - Near-Realtime

Papers - Text - Encoders

Papers - Text - Decoders

Papers - Text - Bidirectional - Bio

Papers - Text - Bidirectional Encoders

Papers - Text - Pre-training

Papers - Text - Pre-training - Research

Papers - Text - Pre-training - Decoder Multi-Steps

Papers - Text - Benchmarks - Quality Diversity

Papers - Image - Multimodal - Handwriting Recognition

Papers - Text - Research

Papers - Text - Multilingual

Papers - Multimodal - Speech and Text

Papers - Multimodal - Speech and Text - Multilingual

Papers - Multimodal - Training and Tuning

Papers - Multimodal - Document Analysis

Papers - Video - Motion Control

Papers - Video - Entity Recognition

Papers - Video - Pre-training

Papers - Image - Pre-training

Papers - Image - Caption Generation

Papers - Image - Synthetic Data Generator

Papers - Transformer Research - Custom Layers

Papers - ResNet

Papers - SuperNets

Papers - Federated Learning

Papers - Mamba - Structured State Space Model

Papers - Image - Human Motion Generator

Papers - MoE - Multimodal

Papers - Autonomous Drones

Papers - Multimodal - Drone

Papers - Multimodal - Drone - Object Manipulation

Papers - Training Research - Time series

Papers - Pre-training - Time Series

Papers - Neural Architecture Search

Papers - Training - Hardware Detection

Papers - Image - Split Computing

Papers - Image - IoT - Split Computing

Papers - Image - Segmentation

Papers - Image - Segmentation - Cancer

Papers - Video - Synthetic Data Generator

Papers - Image - Segmentation - Drone

Papers - Image - Segmentation - Report

Papers - Image - Segmentation - Adversarial

Papers - Image - Segmentation - MRI

Papers - Image - Segmentation - Stroke Brain Lesions

Papers - Image - SkipNet

Papers - Image - IoT

Papers - Image - Hybrid

Papers - Image - Hybrid - ResNet - U-Net

Papers - Image - Hybrid - Swin - U-Net

Papers - Image - Segmentation - Bio Cell

Papers - Image - Segmentation - Quantum

Papers - Image - Hybrid - Graph Net - U-Net

Papers - Image - Hybrid - Patient Meta Data - U-Net

Papers - Image - CSWin - Cross-Shaped Windows

Papers - Image - Encoders

Papers - Image - Encoders - LePE - Local-Enhanced Pos Enc

Papers - Image - Attention - BOAT - Bilateral Local Attn

Papers - Image - Attention - Multi-Scale

Papers - Image - Swin

Papers - Text - Fine-tuning - Math

Papers - Robot - Tasks - Boss

Papers - Text - Model Guided Training

Papers - Robot - Research

Papers - Image - Hybrid - Hybrid Task Cascade (HTC) - Swin

Papers - Image - GasHis

Papers - Image - Dino

Papers - Text - Architecture - Scaling to 1000 Layers

Papers - DenseNet

Papers - Adversarial Testing

Papers - Image - EfficientNet

Papers - Image - Compound Scaling Method

Papers - Base Models - Text - Coding

Papers - Image - Visualization - Splatting

Papers - AI - Social Risks

Papers - AI - Safety

Papers - Testing - Single Layer Model

Papers - Custom Layers

Papers - Pre-training

Papers - Motion Control

Papers - Fine-tuning

Papers - Fine-tuning - LoRA

Papers - Reinforcement Learning

Papers - AI - Self-refinement - Training and Tuning

Papers - Training

Papers - Text - Math

Papers - Observability and Interpretability

Papers - Multimodal - Healthcare

Papers - Interpretability - DAS

Papers - Named Entity Extraction - Healthcare

Papers - Multilingual

Papers - Healthcare

Papers - Watermark

Papers - Image - Clip

Papers - Proof of Learning

Papers - Disaster Recovery

Papers - Named Entity Extraction and Disambiguation

Papers - Neural Architecture Search - Report

Papers - Neural Architecture Search - One-shot

Papers - Neural Architecture Search - Tabular Data

Papers - Hyperparameter Architecture Search

Papers - Image - Neural Architecture Search

Papers - Neural Architecture Search - RNN

Papers - Neural Architecture Search - Reinforcement Learning

Papers - Neural Architecture Search - Quantization - FLIQS

Papers - AutoML

Papers - Neural Architecture Search - AutoML

Papers - Testing - Speech and Text

Papers - AI - Are models similar to a human brain?

Papers - Automated Training - Self Discover

Papers - Math - Automated Discovery

Papers - Math - Research

Papers - Alpaca

Papers - Critical Thinking - Step Back

Papers - Critical Thinking

Papers - Text - Length Generalization

Papers - Text - Encoders - Fire

Papers - Image - Multi-Image Reasoning

Paper - Image - Chain of Thought

Papers - Image - Text and Symbolic Image Generator

Models - Fine-tuning - Mixture of Loras

Papers - Multimodal - Text to 2D to 3D Mesh

Datasets - HTML

Datasets - Multimodal - Text and Image

Papers - Image - Mamba

Papers - Image - Selective Scan

Papers - Healthcare - Mental Health

Papers - Encoders

Papers - Encoders - Fire

Papers - Video - Understanding with Many Models

Papers - Video - Understanding

Papers - Image - Understanding

Papers - Multimodal - Encoders

Papers - Image - GiT

Papers - Text - Star

Papers - QFormer

Papers - Image - Near Real Time

Papers - Image - Attention - Window

Papers - Image - Editing

Papers - Image - Training - Noise

Papers - Image - LCM

Papers - Image - Training - Quantized Mask

Papers - Image - Editing - Glide

Papers - Image - Training - Seed Vector

Papers - Image - Semantic Palette

Papers - Blockwise Parallel

Papers - Training - Distributed

Papers - Training - Masked Sequence Packing

Datasets - Chess

Papers - Semantic Segmentation

Papers - Training - FixMatch

Papers - Training - Self-Training - Student and Teacher

Papers - Task Assistant - ExploreLLM

Papers - Training - Guided Task Flow

Papers - Training - Problem Solving

Papers - Structured Thoughts

Papers - GUI - Task Assistants

Papers - Chinchilla

Papers - Model Scaling - Effective Parameter Count

Papers - Custom Layers - Hash Layers

Papers - Scaling

Papers - Hallucination - Reduction

Papers - Chain of Verification

Papers - Reading Comprehension

Datasets - Text - Multilingual

Papers - Training - Chain of Thought

Papers - Chain of Thought

Papers - Ethics

Papers - Fine-tuning - QA-LoRA

Papers - Fine-tuning - Understanding Tables

Papers - Text - Perform Tasks on Tabular Data

Datasets - Text - Tabular

Papers - Text - Dataset - TabLib - Tabular

Papers - Qwen - Report

Papers - Multimodal - Report

Papers - MoE - Quantization

Papers - Attention - Custom Encoder

Papers - Research - Replacing Attention

Papers - Research - Safety

Embeddings - C4 - Jina

Papers - Reduce Model Size - SliceGPT

Papers - Decoders - CoT Decoding

Papers - Rag - Multi-hop Queries

Papers - Encoders - Coding

Embeddings - Coding

Embeddings - Coding - CodeBert

Papers - Training - Synthetic Noise

Papers - Coding - Fill in the Middle - Infilling

Papers - Text - Pre-training - Synthetic Noise

Papers - Training - Knowledge Graphs

Papers - Image - Training - Knowledge Graphs

Papers - Image - Training - Adversarial

Papers - Multimodal - Fine-tuning - Report

Papers - Text - Tabular - Conditional Formatting

Papers - Text - Training - Code - Byte Pair Encoding

Papers - Coding - Out of Vocabulary

Papers - Coding - BPE vs Pointer Mixture Network

Papers - Automatic Speech Recognition

Papers - Automatic Speech Recognition - Beam Search

Papers - Beam Search

Papers - Explainability

Papers - Training - Synthetic Data - Sycophancy

Papers - Training - DoReMi

Papers - Training - Domain Reweighting

Papers - Training - AI training AI

Papers - Training - Proxy Model - Group DRO

Papers - Adafactor

Papers - Coding - Decoding with Static Analysis

Papers - MoE - Hashing instead of a Router

Datasets - Multimodal - Image and Text

Papers - Multimodal - Document and Text

Datasets - Multimodal - Document and Image

Papers - Encoder - Byte-Pair Encoding

Papers - Text - SQL

Papers - Science - Research Analysis

Papers - Training - Speculative Decoding - Single Model

Papers - Attention - Tree Attention

Papers - Fine-tuning - Rag

Models - Table - Extraction

Papers - Video - Agent

Papers - Audio - GAN - Upsamplimg

Papers - Audio - GAN

Papers - Image - Illumination

Papers - Decoders - 3D Nerf

Papers - Image - Edit

Papers - ControlNet

Papers - Fine-tuning - Parameter Efficiency

Papers - Image - Lightning

Papers - Text - 3D Mesh - Volumetric

Papers - Text - Label Generator

Papers - Image - Limited-Training

Papers - Image - Chart to Table

Papers - Image - Plot - Understanding and Reasoning

Papers - Image - 3D Asset Enhancement

Papers - Text - Taxonomy Generator

Papers - Training - Reward Model

Papers - Fine-tuning - Language Model Policy with LoRA

Papers - Fine-tuning - Mixture of LoRA (MoL)

Papers - Robotic - Observational Learning

Papers - Attention - Cross

Papers - Training - Skill Learning

Papers - FIne-tuning - Multi-Agent

Papers - mPlug-Owl

Papers - Image - Document - mPlugOwl

Papers - Document - mPlugOwl

Papers - Structured Learning - Document

Papers - Prompt - Prompt Compression - Report

Papers - Prompt

Papers - Image - Gaussian Splatting and NeRF

Models - Reverse Engineering - Decompiler

Models - Reverse Engineering

Papers - Text - 3D

Models - Table - Structure - Recognition

Paper - Image - Table - Extraction

Paper - Image - Table

Papers - Tabular

Papers - Image - Object Detection

Models - Image - Object Detection

Papers - Benchmarks - Reward Models

Papers - 3D - Text

Papers - Science - Molecule

Papers - Frankenmerging

Papers - Image - Frankenmerging

Papers - Image - Model Merging

Papers - Attention - Grouped-Query Attention (GQA)

Papers - Image - Math

Papers - Benchmarks - Math

Papers - Image - Reward Model

Papers - Multimodal - Mamba

Papers - Video - Editing

Papers - Image - Personalization

Papers - Image - Personalization - Captions

Papers - Image - Blip

Papers - 3D - Reconstruction

Papers - Image - Video Generator

Papers - Video - Upsampler

Papers - Video - Time Reversal Fusion

Papers - Image - Adversarial (GAN)

Papers - Image - Video - Adversarial (GAN)

Papers - Toxicity

Papers - Fine-tuning - Toxicity

Papers - Video - Content Motion Latent Diffusion

Papers - Decoders - Chain of Thought

Papers - Image - Depth Estimation

Papers - Image - Flow Matching

Papers - Image - Training

Papers - Text - Classification - Social Media

Papers - Text - Classification

Papers - Text - Training - Classification

Papers - Audio - Training

Papers - Multimodal - Audio

Papers - Audio - Whisper vs Clap - Whisper wins with ASR

Papers - Encoders - Audio

Papers - ICL - In-Context Learning

Papers - Math - Derive New Math - Function Class

Papers - Agent - Architecture

Papers - Agent - Memory

Papers - Fine-tuning - DPO

Papers - Critic Models

Papers - Training - Critic Model

Papers - Security

Papers - Security - Fuzzing

Papers - Reasoning - Critic Pattern

Papers - Benchmarks - Reasoning

Papers - Sports

Papers - Pop Culture

Papers - Coding - Chain of Thought

Papers - Coding - Training

Papers - Coding - Fine-tuning

Papers - Coding - Reasoning

Papers - Fine-tuning - Reasoning

Papers - Video - Streaming

Papers - Mamba - FFT - EinFFT

Papers - Encoders - Video

Papers - Multimodal - Video - Text - Audio

Papers - Multimodal - Captions - Audio

Papers - Multimodal - Captions - Speech

Papers - Multimodal - Captions - Video

Papers - Synthetic Data - Multimodal

Papers - 3D - Synthetic Data

Papers - Document - Understanding

Papers - Documents - Fine-tuning

Papers - Compiler

Papers - Coding - Compiler

Papers - Training - Teacher Model

Papers - Tree of Thoughts

Papers - Searchformer

Papers - Coding - Stack Traces

Papers - Training Research - Stack Traces

Papers - Fine-tuning - Search Based

Papers - Fine-tuning - Procedure Cloning

Papers - Encoders - T5

Papers - Decoders - T5

Papers - DenseFormer

Papers - Training - Weighted Average

Papers - Encoders - Image - Clip

Papers - Training - Fitness Score

Papers - Training Research - Exemplary Prompts

Papers - Fine-tuning - Prompts

Models - Documents

Papers - Encoders - VAE

Papers - Agent - Operating Systems

Papers - Image - Synthetic Data - Human Faces

Papers - Multilingual - Japanese

Papers - Fine-tuning - Multilingual

Papers - Document - Understanding - Historical Images Text

Papers - SAM - Segment Anything Model

Papers - Image - Historical

Papers - Image - Explainability

Papers - Image - VGG

Papers - Image - Pattern Recognition

Papers - Image - Historical - Symbolic and Artistic

Papers - Training - Distribution-based

Papers - Research - Emergent Properties

Papers - Image - In-Context Learning

Papers - Deepmind - ICL vs RNN vs LTSM

Papers - Deepmind - ICL Rule-based Classification

Papers - DeepMind - ICL Small Models are More Exemplar-Based

Spaces - Decoders - Beam Search Visualizer

Spaces - Decoders - Beam

Spaces - Decoders

Papers - Video - NeRF

Papers - Fine-tuning - Model Layer Pruning

Papers - Healthcare - Text - Antibodies

Papers - Intel - MLP

Papers - Performance - Intel

Papers - Image - Prompt

Papers - Fine-Tuning - SFT

Papers - Fine-tuning - Report

Papers - Text - Video Generator

Papers - Video - Enhance

Spaces - LangChain

Papers - Image - Gaussian Splatting - 2D

Papers - Audio - Image

Papers - Image - Avatar Generator

Papers - Training Research - Audio

Papers - Healthcare - Synthetic Data Generator - 3D

Models - Image - Streaming

Datasets - Fine-tuning

Datasets - Meta

Papers - University - MIT

Papers - Google

Papers - Image - MultiDiffusion

Papers - Imagen

Papers - Convert - T2I to T2V

Papers - University - University of California Berkeley

Papers - OpenAI

Papers - Text - Fact Checking

Papers - Text - Factuality

Papers - Healthcare - Text

Papers - Healthcare - Training Research

Papers - University - Stanford University

Papers - DataBricks

Models - Healthcare

Papers - Image - Generator - Large Resolution

Papers - Encoders - Synthetic Noise

Papers - Video - Clothing

Papers - Encoders - Video - MetaCLIP

Papers - IoT - Assistant

Papers - Training Research - Mixture FOFE

Papers - Training Research - AD FOFE

Papers - Image - Editing - Object Removal

Papers - Image - Editing - Object Insertion

Papers - Image - Editing - Counterfactual Supervision

Papers - 3DGS - Feature Rendering

Papers - 3DGS - Open-world Segmentation

Papers - 3DGS - Security Camera Object Detection

Papers - Microsoft

Papers - University - Carnegie Mellon University

Papers - Healthcare - Image Analysis

Papers - Healthcare - Image - SynthRAD2023

Papers - Healthcare - Image - CT

Models - MoE - GQA

Papers - Image - Segmentation - Bounding Box Infilling

Models - MoE - Coding

Papers - Image - Translation

Papers - Text - Translation

Papers - Multilingual - German

Papers - Image - Synthetic Noise

Papers - Multilingual - Translation

Papers - Johns Hopkins

Papers - Multilingual - Synthetic Noise

Papers - Fine-tuning - Text - U-Net

Papers - Image - Encoders - Text

Papers - Image - Encoders - Clip

Papers - Video - Reasoning - Time of Events

Papers - Video - Encoders

Papers - Video - Training - Understanding Time

Papers - Nvidia

Papers - U-Net - 3D

Papers - 3DGS - 3D Mesh Generator

Models - Fine-tuning

Papers - Model - SFT - Alpaca and DPO - Solar

Papers - Fine-tuning - Preference-based RL (PbRL)

Papers - University - Cornell

Papers - Robotics - Fine-tuning - PbRL

Papers - Fine-tuning - DPO - Reward Model Training

Papers - Reward Model

Papers - Reward Model - Bradley-Terry

Papers - Reward Model - Training

Papers - University of Chicago

Papers - Reward Models - KL Regularization - RL

Papers - KL Regularization - ADP - Con/Divergence Error Rate

Models - Fine-tuning - PPO

Papers - Fine-tuning - Factuality

Papers - Fine-tuning - Emulator

Datasets - RLHF

Datasets - Fine-tuning - RLHF

Papers - top-p - Nucleus Sampling

Papers - top-k - Flat (good) vs Peaked (bad) Dist Sampling

Papers - Distribution - Zipf Analysis

Papers - Institute - Allen Institute

Papers - University - University of Washington

Models - Bitnet - Text

Papers - Coding - Unit Tests

Papers - Tacotron 2

Papers - Audio - WaveNet

Papers - Audio - Time Domain Waveforms

Papers - Audio - TTS

Papers - Audio - Mel Spectogram

Papers - Decoders - Audio

Papers - Image - GAN

Papers - GAN - Compression - Bitstream

Papers - GAN - Compression

Papers - Audio - STT - ASR

Papers - Audio - Speech Transcription

Papers - Audio - WhisperX

Papers - Audio - Voice Activity Detection

Papers - Audio - VoiceCraft

Models - Audio - TTS

Papers - Audio - Compression

Models - Audio - Codec

Models - Audio - Encoders

Models - Audio - Decoders

Models - Meta - FAIR

Models - Audio - Music Generator

Models - Getting Started - Pre-training

Models - TinyLlama

Models - Reward Model

Models - Starling

Datasets - Chat - RLHF

Datasets - Starling

Papers - Audio - Masked Language Model

Papers - Audio - Residual Vector Quantization

Papers - Audio - Encoders

Models - Image - Object Detection - DETR

Models - ResNet

Papers - Audio - Inference - Rescore Models

Papers - Inference - Rescore Models

Inference - Autoregressive and Non-Autoregressive Models

Papers - Kyutai

Models - Text - Music Generator

Models - Audio - Hybrid - AR with NAR Models

Papers - MoE - Mamba

Papers - Flan-T5

Papers - IoT - Screen Usage Understanding and Context

Papers - Mobile - User Entity Context Understanding

Papers - Mamba - Limitations - In-Context Learning (ICL)

Models - MoE - Mamba

Papers - AI21 Labs

Papers - University of Tokyo

Papers - University of Wisconsin

Papers - Image - Report

Papers - Hallucinations

Papers - Trustworthiness

Papers - University of Bristol

Papers - Healthcare - Surgical Gestures

Papers - Vanderbilt

Papers - Fine-tuning - Dataset - Few-Shot Retrieval (FRet)

Papers - University - New York University

Papers - Embeddings

Papers - Embeddings - Text

Papers - Text - Memorization

Papers - Training a 2.8B Model in 38 days

Papers - Huawei

Papers - Inference - vLLM

Papers - Attention - PagedAttention

Papers - Fine-tuning - Model Merge

Papers - Frankenmerge - Model Stock - Use Fine-tuned Models

Models - Model Stock

Models - Frankenmerge

Models - Frankenmerge - Model Stock

Papers - Benchmarks

Papers - Benchmarks - Financials

Papers - Video - Fine-tuning

Papers - Video - Reward Model

Models - Spright

Papers - Hugging Face

Papers - University of Maryland

Papers - University - Tsinghua University

Papers - Chinese Academy of Sciences

Papers - Xidian University

Papers - 3D - FlexiCubes

Papers - ShengShu

Papers - Fine-tuning - Llava - DPO

Papers - Non-Autoregressive Transformers

Papers - Salesforce

Papers - Safety

Papers - Speech - Chain of Thought

Papers - Audio - Chain of Thought

Papers - Chinese University of Hong Kong

Papers - Audio - Fine-tuning

Papers - Audio - Fine-tuning - Lora

Papers - Image - Continual Training Framework

Papers - Documents - LayoutLM

Papers - Documents - FormNet

Papers - Document - OCR

Papers - Ohio State

Papers - Video - Captions

Papers - Video - Streaming - Captions

Papers - Decoders - Training Decoding Point Supervision

Papers - Healthcare - Cardiac MRI - CMRxRecon Challenge 2023

Papers - Image - Healthcare - Cardiac MRI

Papers - Image - Healthcare

Papers - Training Research - Optimizers

Papers - Coding - C/C++ - Memory

Papers - Coding - C/C++

Papers - Coding - Annotations, Decorators and Captions

Papers - Coding - Operating Systems - Memory

Papers - Image - Contrastive Graph Learning

Papers - Extended Transformer Construction

Papers - Documents - Tabular

Papers - Graph Convolutional Network

Papers - Documents - Graph Convolutional Network

Papers - Training Research - Contrastive Predictive Coding

Papers - Decoders - Bert

Papers - Optimizers - Adafactor

Papers - T5 - MoE

Papers - University of Georgia Tech

Papers - Image - Extract Style

Papers - Image - Contrastive Style Descriptors

Papers - Image - Use a Model to find a similar image

Papers - Ellis Institute

Papers - Shanghai AI Laboratory

Papers - Image - Security Cameras

Papers - Government - USA

Papers - University of Waterloo

Papers - Vector Institute

Papers - Benchmarks - Text

Papers - Benchmarks - In-Context Learning

Papers - Benchmarks - Text - Long Context

Models - Documents - OCR

Models - Text - Classifier - Zero-Shot

Models - Text - Classifier - Deberta

Papers - Network - Adaptive BitRate Algorithms

Papers - Network Traffic - 4G and 5G - OTA - Packet Shaping

Papers - Network Traffic - 4G and 5G - OTA

Papers - Network Traffic - 4G and 5G

Papers - Network Traffic - OTA

Papers - Network Traffic - Packet Shaping

Papers - Network Traffic - Transport Optimization

Papers - Network Traffic

Papers - University of Texas

Papers - University of Peking

Papers - Coding - Preference Trees

Papers - Coding - Understanding Tree Structures

Papers - Math - Reasoning

Papers - University of Illinois

Papers - University - Northeastern University

Papers - Multilingual - Finnish

Papers - Multilingual - Encoders - BPE

Papers - Multimodal - Training

Papers - Encoders - DinoV2

Papers - Image - Encoders - DinoV2

Papers - Training Research - Scaling Properties - T2I

Papers - Training Research - Smaller vs Larger Models

Papers - Pre-training - In-filling - PSM and SPM ordering

Papers - Pre-training - Dynamic Context Length

Papers - Text - Supervised Fine-tuning

Papers - Text - Supervised Fine-tuning - Batch Grouping

Papers - Fine-tuning - PPO

Papers - Multilingual - Benchmarks

Papers - Amazon

Papers - Image - SDXL

Papers - ByteDance

Papers - Video - Autoregressive Model

Papers - Infererence - Performance

Papers - Coding - Algorithmic Reasoning

Papers - Coding - Think and Execute vs CoT and PoTs

Papers - Coding - Program of Thoughts (PoT)

Papers - Coding - Think and Exectue - 7B vs 13B vs GPT

Papers - Prompts - Detailed Examples

Papers - Infra - Cost - Automatic Compute Planning

Papers - Mixture of Depths - MLP, residuals, router, tokens

Papers - MoD - Router

Papers - Yonsei University

Papers - Image - NeRF

Papers - Alibaba

Papers - University of Fudan

Papers - Image - Frequency Decomposition

Papers - Image - Demosaic

Papers - University - Hong Kong University of Science and Te

Papers - Image - Interior Design

Papers - 3D - Interior Design

Papers - ETH Zurich

Papers - 3D - Indoor Scene Synthesis

Datasets - Reasoning

Papers - Reasoning - Self-Reference Metalinguistic

Papers - University - University of California San Diego

Papers - PlayTest AI

Papers - Contextual AI

Papers - Reasoning - MRGSM8k - Meta Math Multi Step

Papers - Reasoning - GSM8k

Papers - Tencent

Papers - Benchmarks - GSM8k

Datasets - Reasoning - Meta Math Multi-Step - GSM8k

Datasets - Math - Meta Context Reasoning

Papers - University of Cambridge

Papers - Southern University of Science and Technology

Papers - Alan Turing Institute

Papers - Max Planck Institute

Datasets - Text - QA

Datasets - Text - System Chat

Models - Image - Handwriting Comprehension

Models - Table - Handwriting Comprehension

Papers - Arctic University of Norway

Papers - Document - Tabular - Manual Review

Papers - Documents - Tabular - Census

Papers - Image - Custom Annotation and Labeling Tools

Papers - Documents - Custom Annotation and Labeling Tools

Papers - Image - Tabular

Papers - CascadeTabNet

Papers - Image - OCR

Papers - Pune Institute

Papers - Image - Table Structure Recognition

Papers - Documents - Table Recognition - Fine-tuning

Papers - Image - Fine-tuning - Tables

Papers - Image - OCR - Tesseract for Text Location

Papers - Document AI

Papers - Harbin Institute

Papers - Coding - Benchmarks - Report

Papers - Coding - OpenCodeInterpreter

Papers - Benchmarks - Coding

Papers - Coding - Training - Equal-Info Windows

Papers - Coding - Multi-Model Inference

Papers - Coding - Distributed - Adaptive Computation Time

Papers - Anthropic

Papers - Training Research - Compression and Multi-Model Inf

Papers - Coding - Encoders

Papers - Encoders - Compression

Papers - Coding - Compression

Papers - Tokenizer - Neural Compression

Papers - Inference - Multi-Model

Papers - Fine-tuning - ReFT

Papers - Fine-tuning - Report - Llama 7B and 13B

Datasets - Reasoning - Commonsense

Papers - Tokenizers - Roberta

Papers - Reasoning - Commonsense

Papers - Reasoning - Social IQ

Papers - University of Houston

Papers - Image - Classifier - Label Quality Assessment

Datasets - Reasoning - Math

Papers - Benchmarks - Image - Labels

Papers - Benchmarks - Image

Papers - Reasoning - Math

Papers - Reasoning - Math - AQuA

Papers - University of Oxford

Papers - University of IAIR Xi’an Jiaotong

Papers - Training - Instruction-Following

Datasets - Text - Instruction-following

Papers - Benchmarks - Text - General Language Understanding

Papers - Benchmarks - Text - Glue

Datasets - Benchmarks - Glue

Datasets - Benchmarks - Text

Papers - Encoders - Roberta

Papers - Reasoning - Program of Thoughts

Papers - University of California Santa Barabra

Papers - StructLM - Understanding Structured Data

Models - StructLM

Datasets - Text - StructLM

Papers - Prompts - System Chat

Papers - Prompts - Chain of Thought

Papers - Tokenizers - LLaMA Byte Pair Encoding (BPE)

Datasets - OCR - Image with Text from Textract

Datasets - Documents - OCR - Image with Text from Textract

Papers - Benchmarks - Web Browsing Tasks

Papers - University of Harvard

Papers - Image - Point Cloud

Papers - Video - MultiView Compressive Coding (MCC)

Papers - Image - Encoders - RBG-D

Papers - Image - Training - Low Res Predicts High Res

Papers - University of Beihang

Papers - Tokenizers - Documents - TrOCR

Papers - Tokenizers - Image - TrOCR

Papers - Tokenizers - Image - Handwriting

Spaces - Image - Handwriting Recognition

Papers - University of Zhejiang

Papers - Audio - Text to Speech

Papers - Audio - TTS - VALL-E

Papers - Audio - TTS - RALL-E

Papers - Security - Jailbreak

Papers - Benchmark - Security

Papers - LMU Munich

Papers - Siemens

Papers - University of Wuhan

Papers - Munich Center for Machine Learning (MCML)

Papers - Benchmarks - Website Navigation

Papers - Web Navigation - Chrome Extension

Papers - Web - Recognition

Papers - Web - Training - Curriculum Learning

Papers - Fine-tuning - Rejection Sampling (RFT)

Papers - Zhipu AI

Models - General Purpose

Datasets - Benchmarks - CodeEditorBench - OCI

Models - Text - Image

Models - Multimodal - Chat

Models - Audio - Understanding

Models - Synthetic Data - Audio

Models - Audio - Edit with Text

Models - Audio - Classification and Segmentation

Models - Image - Chat

Models - Image - Synthetic Data

Spaces - Image - Chat

Papers - Audio - Understanding

Papers - Audio - Captions

Spaces - Qwen - Image

Models - Audio - STT - ASR

Papers - Redwood Research

Papers - Automated Interpretability

Models - Encoders - Bidirectional

Models - Encoders - Bert

Papers - Text - Encoders - Image - Clip

Papers - Training Research - Rank-One Model Editing

Papers - Training Research - Mamba

Papers - Training Research - Ablation - Mamba

Papers - Training Research - Ablation - Factuality

Papers - Training Research - Weights - Activation Patching

Papers - Training Research - Interpretability

Papers - Interpretability - Rome - Factuality Editing

Papers - Interpretability

Papers - University of Tel-Aviv

Papers - Interpretability - Attention

Papers - University of Brown

Papers - Training Research - Layer Understanding

Papers - Interpretability - Prompts

Papers - Image - Imagen

Papers - Training Research - Control Attention Reweighting

Papers - Attention - Weights - Re-Weighting

Papers - Training Research - Text - Token Visualization

Datasets - Image - ImageNet

Datasets - Image

Papers - Recommendation - Cloze Task

Papers - Recommendation - Encoders - Bert

Papers - Recommendation

Papers - Recommendation - Multi-Task Learning

Papers - Recommendation - Bert4rec - SASRec

Papers - Recommendation - RTG Balancing

Papers - University of Zurich

Papers - Healthcare - Radiology

Papers - University of Shanghai Jiaotong

Papers - Training Research - Pre-training - ALBEF

Papers - Training Research - Vision Language Pre-training

Papers - Pre-training - ALBEF - Multimodal Encoder

Papers - Multimodal - Encoders - ALBEF

Papers - Dataset - MultiModal - MultiLingual - Wiki

Papers - Fine-tuning - RLHF - Direct Nash Optimization (DNO)

Papers - RLHF - Iterative Contrastive Self-Improvement

Datasets - Text - Alpaca

Papers - RL - Consistency Model (RLCM)

Papers - Fine-tuning - Image - Prompt Image Alignment

Papers - Harvey Mudd

Papers - Fine-tuning - Stream of Search

Papers - Training Research - Search Based (BFS / DFS)

Models - Text - Science

Papers - University of Tubingen

Papers - Kuaishou

Papers - Text - Dialog Inpainting

Papers - 3DGS - Motion Blur

Papers - 3DGS - Color Transformation

Papers - Image - Encoders - RGB-T (Thermal)

Papers - University of Dalian

Models - Image - Stock Market - Pattern Detection

Papers - Audio - Encoders - HuBert with EnCodec

Papers - Audio - Bark

Papers - Mobile - Multimodal - Screen Image with Captions

Papers - Training Research - DeiT

Papers - Healthcare- DeiT

Papers - Image - Object Detection - YoloV8

Papers - Healthcare - Image - Cancer - Brain

Papers - Image - Hybrid - DeiT and YoloV8

Papers - Image - Healthcare - DICOM

Papers - Image - Healthcare - PTP Metrics

Papers - Image - DeiT

Papers - Custom Layers - MLP

Papers - University of Melbourne

Papers - Multilingual - Image - Greek

Papers - Indian Institute of Technology

Papers - Indian Institute of Science

Papers - University of Sorbonne

Papers - Regularization - LayerScale

Papers - Regularization - Binary Cross Entropy

Models - Image - DeiT

Models - Image - Classification

Papers - Image - Report - VQA

Papers - Image - Training - Mistral

Papers - AIRI Institute

Papers - Sber AI

Papers - Skoltech

Papers - Image - LLaVA

Papers - Image - Coco Testing

Papers - Image - Clip - Coco Testing

Papers - Image - Frechet Inception Distance (FID)

Papers - Training - Long Context

Papers - Benchmark - Context

Papers - Benchmarks - Context - Ruler

Papers - Image - Decoders

Papers - Image - Decoders - ViT

Papers - Training - Image - Causal Self Attention

Papers - Image - Training - AS2D RoPE and SwiGLU

Papers - Training - Detailed Appendices

Papers - Image - Encoders - ViT

Papers - 3D - Panoramic View Generator

Papers - Image - Training - Self Refinement

Papers - Training - Noisy or Unseen Data Drops Accuracy 6%

Papers - Image - Object Detection - DETR

Spaces - Healthcare - Multimodal

Papers - Text - Social Skills

Papers - Fine-tuning - Orpo

Papers - KAIST AI

Papers - Image - Fourier Neural Operators (FNO) vs CNNs

Papers - Image - FNO - Low and High Frequency Data

Papers - Image - Training - Training with an Ensemble

Papers - Image - FNO - SpecBoost Ensemble

Papers - Image - Differential Equations - FNO - ReLu

Papers - Image - Spectral Analysis

Papers - Rag - Prompts

Papers - Rag - Multiple Documents in Parallel

Papers - Tokens - Path Equilibrium Positioning

Papers - Tokens - Real-Valued Positioning

Papers - Model - Griffin

Papers - Models - Griffin - RecurrentGemma

Models - Mistral - Orpo

Papers - Fine-tuning - ControlNet

Papers - University of Central Florida

Papers - Reward Model - Consistency Loss - ControlNet

Papers - Audio - Datasets - Dialog

Papers - Qwen - Audio

Papers - Advanced Micro Devices

Papers - Image - Auto - Lane Detection

Papers - Image - Auto - Lane - Training Segmentation

Papers - Operating Systems

Papers - Agents - Operating Systems

Papers - Benchmarks - Agent - Multimodal - Tasks

Papers - University of Aalto

Papers - Image - Classifier Free Guidance

Papers - University - Princeton University

Papers - Megatron

Papers - Attention - Mixture of Attention Heads (MoA)

Papers - DiffusionDet

Papers - Image - Generator - Gaussian Noise - Bounding Boxes

Papers - Image - Ordinary Differential Equations (ODE)

Papers - Image - Object Detection - Bounding Boxes

Papers - Image - Bounding Boxes - Loss - Timeseries

Datasets - Image - Coco - Obj Det, Segmentation, Captions

Models - Image - Image Segmentation - Coco

Models - Image - DPT - Dino

Papers - Image - ConsistencyDet

Papers - Image - TrOCR

Models - Mistral

Models - Image - Clip

Models - Image - Dino

Models - Agent - On-Device

Spaces - Comics

Papers - Chain of Thoughts - Visualization

Papers - Visualization of Thought (VoT) - Mind’s Eye

Papers - Benchmarks - Documentation

Papers - Benchmark - Multimodal - Image Documentation

Papers - AutoDesk

Papers - Investing - Stock Forecasting

Papers - University of Shenzhen

Papers - Investing - AceFormer - ACEEMD

Papers - Image - Knowledge Graph

Papers - Knowledge Graph - Tasks

Papers - Panasonic

Papers - University of Xiamen

Papers - Selective Language Modeling vs Causal

Papers - Fine-tuning - Math

Datasets - Chat

Papers - Image - VQA

Papers - Image - VQA - Captions High Res Alignment

Papers - University of Santa Barbara

Papers - University - Columbia University

Papers - Image - VQA - Ferret

Papers - Image - Encoders - Dual Vision MLP projectors

Papers - Image - Referring Object Classification (ROC)

Papers - Image - Dataset - LVIS

Papers - Image - Grounding

Papers - Image - Training - OCR - High-Res Dense Alignment

Papers - Image - Captioning

Papers - Documents - UDOP

Papers - Documents - Fine-tuning - LayoutLM and UDOP

Papers - Image - Scientific Charts

Papers - Documents - Scientific Charts

Papers - University of Ulm

Papers - Image - Fine-tuning - ICPR22 dataset

Papers - Image - Fine-tuning - CHIME-R and EconBiz datasets

Papers - Image - Fine-tuning - DeGruyter dataset

Papers - Embeddings - Text - RoBERTA and BPE

Papers - Embeddings - Image

Papers - Embeddings - Image - DiT and dVAE

Papers - LayoutLM - Fine-tuning - Word Patch Alignment

Papers - Tokenizers - Text - T5

Papers - Fine-tuning - Hyperparameter - FUNSD

Papers - Classification - F1 Macro and F1 Micro

Papers - Timeseries

Papers - University of Panjab

Papers - Image - Report - Training - CNN RNN LTSM MLP

Papers - Image - Connectionist Temporal Classification (CTC)

Papers - Image - Climate - SHAP

Papers - Courant Institute

Papers - Image - Climate - ERA5

Papers - Image - Coco - Annotation Pipeline

Papers - Image - Mask - box-kMaX over kMaX-DeepLab

Papers - Image - Coco - Annotation RLHF

Papers - Image - Coco - Panoptic

Papers - Video - NeRF - Real Estate Walkthroughs

Papers - NeRF - Training - Photometric Consistency Patches

Papers - Image - Datasets - ETH3D

Papers - Image - Datasets - TanksAndTemples

Papers - Image - NeRF - Mesh - TSDF fusion RGBD sequences

Papers - Image - Evaluation Metrics - PSNR SSIM LPIPS

Datasets - Research Papers - ARXIV QA

Papers - University of Alberta

Papers - University of Auburn

Papers - Explainability - Image - VQA

Papers - Explainability - Image - VQA - CHM-Corr++

Spaces - Chat - QA - Research Papers on Arxiv read by Claude

Audio Reading - 2404.08639 - COCONut

Audio Reading - 2403.07691 - ORPO Fine-tuning

Audio Reading - 2212.05525 - Extending TrOCR

Audio Reading - 2404.06209 - Elephants Never Forget

Audio Reading - 2404.07773 - ConsistencyDet

Models - Reasoning

Datasets - Audio - Large

Datasets - Audio - Multilingual

Datasets - Audio - Multilingual - Large

Spaces - Audio - TTS

Models - WizardLM

Datasets - Benchmark - Tasks

Models - Image - QA

Datasets - Chat - Persuasion

Papers - Training Research - Dataset Ordering

Papers - Training - Curriculum Learning

Papers - Training - Education Stage then Cognitive Hierarchy

Papers - Training - Curriculum Instruction Tuning

Papers - Llama 2

Papers - Training - AI2 Reasoning

Papers - Training - Out of Vocabulary

Papers - Training - Multilingual - Out of Vocabulary

Papers - University of Charles

Papers - Training - Report - LTSM vs LLM vs Ensemble

Papers - Training - Filter Low Quality with Contriever

Papers - University of Seoul National

Papers - University of Ewha Womans

Papers - University - National University of Singapore

Papers - University of Michigan

Papers - Audio - Fine-tuning - DPO

Papers - Audio - Fine-tuning - Alpaca

Papers - Audio - Clap

Papers - Audio - Encoder - Variational Auto-Encoder (VAE)

Papers - Audio - Frechet Audio Distance (FAD) like FID

Papers - University of North Carolina Chapel Hill

Papers - University of Southern California

Papers - Megalodon - Unlimited Context

Papers - Multimodal - Long Context - Megalodon

Papers - 3DGS - Compression

Papers - Multimodal - Speculative Decoding

Papers - Inference - Multimodal

Papers - Qualcomm

Papers - Inference - Speculative Decoding - Draft Model

Papers - Dataset Grooming - Report

Papers - Dataset Generation - Guide

Papers - Image - Hyperspectral Images (HSI)

Papers - Mamba - Bidirectional

Papers - Healthcare - Image - Cancer

Papers - Healthcare - Image - Cancer - Prostate

Papers - Agent - Research

Papers - Research - Automated Research

Papers - Fine-tuning - DPO - KL Divergence vs Learning Rates

Papers - Tinkoff AI

Papers - Embeddings - Scalable Positional Encodings

Papers - University of Pennsylvania

Papers - Image - Layer Pruning

Papers - Inference - Image

Papers - Inference - Image - Layer Pruning

Audio Reading - 2402.16827 - Survey on Data Selection ~3.5h

Audio Reading - 2404.08011 - Review Handwriting Recognition

Papers - Pre-training - Warm-Start - Encoder and Decoders

Papers - Pre-training - Pegasus

Papers - Imperial College of London

Papers - Pre-training - Text - Masked Language Models (MLM)

Papers - Pre-training - Self-Supervised for Downstream Tasks

Papers - Pre-training - Warm-Start - Encoders - BPE

Papers - Pre-training - Warm-Start - Encoders - Unigram

Papers - Pre-training - Summarization

Papers - Pre-training - Encoders - Bert

Papers - Pre-training - Encoders - Roberta

Papers - Pre-training - Warm-Start

Papers - Pre-training - Unsupervised

Papers - Pre-training - Checkpoints

Models - Fintech - Financial Summarization

Audio Reading - 2310.09518 - Instruct with Human Curriculum

Datasets - Image - Multilingual - VQA

Datasets - Image - VQA

Papers - Inference

Papers - Inference - KV Cache

Models - Encoders - Multimodal - Clip - SigLIP

Models - Image - Encoders

Spaces - Multimodal - Image and Chat

Papers - Stability AI

Papers - Audio - Activation - Snake

Papers - Audio - Decoders - DAC - No tanh activation

Papers - Audio - RoPE

Papers - Audio - Embedding - Time - Sinusoidal Cross Attensi

Papers - Audio - Embedding - Text - Clap - Cross Attention

Papers - Audio - Embedding - Clap - Timestep - Prepended

Papers - Audio - Encoders - Clap - HTSAT audio RoBERTa text

Papers - Attention - Block-wise

Papers - Audio - Encoders - Clap - Training - Metadata

Papers - Audio - Musical Structure Analysis

Papers - Audio - Encoders - Laion-Clap

Papers - Agent - Sima

Papers - World Sim - Agent - Tasks

Papers - Training - Video Games

Papers - Video Games

Papers - Video Games - Survival

Papers - Video Games - Crafting

Papers - Video Games - Survival - Valheim

Papers - Video Games - Navigation

Papers - Video Games - Object Tools

Papers - Video Games - Farming

Papers - Video Games - Environment Resource Planning

Papers - World Sim - Encoder - Image - Sparc

Papers - World Sim - Encoder - Video - Phenaki

Papers - World Sim - OCR

Papers - World Sim - Training - Classifier-Free Guidance

Papers - World Sim - Cognitive Architectures

Papers - Video - Phenaki

Papers - Video - Encoders - C-ViViT

Papers - Video - Encoders - C-ViViT - MaskGiT

Papers - Embeddings - Text - T5X

Papers - World Sim - Embedings - Text - T5X

Papers - Training - GNN

Papers - GNN - Dataset - LargeMix

Papers - GNN - Fine-tuning

Papers - GNN - Benchmark - TDC

Papers - GNN - Benchmark - Polaris

Papers - GNN - Benchmark - MoleculeNet

Papers - Hybrid Arch - Skip Connections

Papers - GNN - MPNN

Papers - GNN - Encoders

Papers - GNN - Encoders - Positional and Structural Encoding

Papers - GNN - Fine-tuning - Custom Layer - MLP

Papers - GNN - MoIE

Papers - Healthcare - Molecules - GNN

Papers - Healthcare - Molecules

Papers - Healthcare - GNN

Papers - GNN - Ensemble

Papers - Healthcare - Drug Discovery

Papers - Healthcare - Drug Discovery - GNN

Papers - Valence Labs

Papers - University of Montreal

Papers - University - University of Toronto

Papers - University of McGill

Papers - Healthcare - Image - X-ray

Papers - Healthcare - Image - Chest - X-ray

Papers - Healthcare - Image - Lung Disease

Papers - XAI - Gradient Weighted Class Activation Mapping

Papers - XAI - Loc Interpretable Model Agnostic Explanation

Papers - XAI - Fine-tuning

Papers - University of Ahsanullah

Papers - Healthcare - Image - Covid-19

Papers - Image - Visual Feature Extractor

Papers - Inference - Batch - Hierarchical Sharing Pattern

Papers - Optimizer - Lamb

Papers - Attention - Sliding Window

Papers - Training - 3D Parallelism - Back - Reduce-Scatter

Papers - Training - 3D Parallelism - Forward - All-Gather

Papers - Custom Layers - Feedforward Neural Network (FFN)

Papers - Training Research - Model FLOPs Utilization (MFU)

Papers - Training Research - Fault Tolerance

Papers - Custom Layers - Decoders - No FFN

Papers - Training - Parameter Reduction - FFN

Papers - Equall AI

Papers - Multilingual - Spanish

Datasets - Fine-tuning - Orpo

Papers - Emergent Properties

Papers - Emergent Properties - Multiple Choice Grade

Papers - Emergent Properties - Exact String Match

Papers - Emergent Properties - Image

Papers - Training - Epoch - 4 Epochs by Default

Papers - Attention - Mixture-of-Attention (MoA)

Papers - Surge Global

Papers - Benchmarks - Safety

Papers - Benchmarks - Toxicity

Papers - Reward Model - Fine-tuning

Papers - Fine-tuning - Reward Model

Papers - Reward Model - Cross-Lingual

Papers - Datasets - Multilingual - Documents - Seahorse

Papers - Datasets - Multilingual - OpenAssistant

Papers - Inference - Speculative Decoding - KV Cache

Papers - Speculative Decoding - KV Cache

Papers - KV Cache

Papers - Inference - Speculative Decoding - Draft - KV Cache

Papers - Speculative Decoding - Draft - Base Model - JF68M

Papers - Speculative Decoding - Long Context

Papers - Speculative Decoding - Draft - Model - SpecInfer

Models - Speculative Decoding - Draft - Base Model

Models - Speculative Decoding - Draft - SpecInfer

Papers - Speculative Decoding - Token Tree Verification

Papers - Speculative Decoding - Token Verification

Papers - TensorRT-LLM - FasterTransformer - deprecated

Papers - Multimodal - Reka - Image Video Text Audio

Papers - Tokenizers - tiktoken

Papers - Animation - Text

Papers - Animation - Text - Kinetic Typography

Papers - Video - Text Animation

Papers - Image - LPIPS

Papers - Video - Score Distillation Sampling

Models - Fine-tuning - Orpo

Papers. - Samsung

Papers - 3D - Mesh Generator

Papers - Training - 3D - NeRF

Papers - Games - AlphaGo

Papers - Training - Self-Improvement

Papers - University of Turku

Datasets - Benchmarks - Image - QA - Real World Objects

Papers - Benchmarks - Image - QA - Abstract

Papers - Benchmarks - Image - Visual Commonsense

Datasets - Benchmarks - Image

Datasets - Benchmarks - Image - QA

Datasets - Benchmarks - Image - Blink

Papers - Context - NoPE

Papers - International Human Phenome Institute

Papers - University - East China Normal University

Papers - Datasets - Training - Context - LongBencb

Papers - Context - Length Generalization

Papers - Attention - NoPE - Long Context with SoftMax Temp

Papers - Attention - Training - Context - Head-based Scaling

Papers - TinyLlama

Papers - Datasets - Training - Context - SlimPajama

Papers - Training - Eval - Sliding Window Perplexity

Papers - Datasets - Training - Context - Starcoderdata

Papers - Training - Eval - Sliding Window - PG19

Papers - Training - Eval - Sliding Window - Proof-pile

Papers - Context - NoPE vs RoPE - Passkey Retrieval Viz

Papers - Transformers Without Positional Encoding - NoPE

Papers - ServiceNow

Papers - Attention - Multi-Head Attention (MHA)

Papers - Training - Residual Connections

Papers - Text - Encoders - Bert

Papers - Positional Encodings

Papers - Embeddings - Absolute Position Embedding (APE)

Papers - Embeddings - ALiBi

Papers - Embeddings - Rotary - RoPE

Papers - Embeddings - No Positional Encodings - NoPE

Papers - Embeddings - T5 Relative Bias

Papers - Chain of Thought - Scratchpad

Papers - Text - Classification - FastFit

Datasets - Text - Argument Topics

Datasets - Text - FinTech

Papers - University - Hebrew University of Jerusalem

Papers - Text - Datasets - Classification and Labels

Papers - Benchmarks - Text - Classification - FewMany

Papers - Weather

Papers - Datasets - Weather

Papers - Datasets - Weather - ERA5

Papers - Historical - Weather

Papers - University of Aarhus

Papers - University - Berlin Technical University

Datasets - Coding - Code Reviews

Datasets - Benchmarks - Coding

Datasets - Text - Web

Datasets - Text - CommonCrawl

Datasets - Text - QA - Web

Datasets - Text - Research Papers - QA - QASPER

Papers - Image - Graph - Understanding

Papers - Knowledge Graphs

Papers - Image - Glip

Papers - University - UCLA

Papers - International Digital Economy Academy (IDEA)

Papers - Image - Phrase Grounding

Papers - Image - Bounding Box - Coco - Teacher and Student

Papers - Image - Grounded Captions

Models - Image - GLIGEN

Papers - Text - Instruct - Grounding and Captions

Papers - Image - UMAP

Papers - Text - Legal - Remove Redaction

Papers - University - University of Padua

Papers - Benchmarks - Text - Text Anonymization Benchmark

Papers - Text - Named Entity Recognition (NER)

Papers - Text - Encoders - Sentence Transformers (SBERT)

Papers - Text - Eval - SMOTE

Papers - ML - XGBoost

Papers - Text - Remove Redaction - Countermeasures

Papers - University - Delft University

Papers - FDM Business Services

Papers - Attention - Gated Self-Attentio - Spatial Grounding

Papers - Inference - Scheduled Sampling

Papers - Image - Object Detection - YOLO

Papers - Image - Inpainting

Papers - Image - Keypoint

Papers - 3DGS - Structure from Motion

Papers - SQL - Database Migrations

Papers - SQL - Knowledge Graphs

Papers - SQL - Query Tree

Papers - SQL - Curriculum Learning

Papers - Web - Agent

Papers - University - Simon Fraser University

Papers - University - University of British Columbia

Papers - Coding - Git Commits

Papers - Coding - Defects

Papers - 3DGS - Material Point Method (MPM)

Papers - 3DGS - Motion

Papers - Video - Simulated Material Dynamics - MLS-MPM

Papers - 3DGS - K-Means Clustering

Papers - University - Huazhong University

Papers - Phi-3 - Technical Report

Papers - Text - Mobile

Papers - Audio - Classifier-Free Guidance (CFG)

Papers - Kunlun

Papers - Image - Fine-tuning - LoRA

Papers - Multimodal - XAI

Papers - XAI - Eval - Synthetic Vision Neuron

Papers - XAI - Research in Appendix

Papers - XAI - MAIA

Papers - Llama 3

Papers - Llama 3 - Fine-tuning - Quantization

Papers - Llama 3 - Fine-tuning

Papers - Llama 3 - GPTQ AWQ PB-LLM BiLLM - 1.1-8 bits LoRA

Papers - Image - NeRF - Structure from Motion (SfM)

Papers - Niantic

Papers - Benchmarks - Fintech

Papers - Coding - Automated Workflows

Papers - Fintech - Datasets - SEC - Edgar Filings DB - N-CEN

Papers - Investing - Document QA - SEC Filings

Papers - JP Morgan Chase

Papers - Image - Consistency Trajectory Model (CTM)

Papers - KL Regularization - Diffusion Matching Distillation

Papers - Security - Prompt Injection

Papers - Prompts - Security - Instruction Prioritization

Papers - Image - Multi-Concept Customization (MCC)

Papers - Image - Adaptive Concept Normalization (ACN)

Papers - Image - Encoder - Single-Concept Learning - QFormer

Papers - Image - Synthetic Generator - Canny

Papers - Image - Synthetic Generator - Depth

Datasets - Image - Classification

Papers - Image - Datasets - CIFAR

Papers - Image - Datasets - MNIST

Papers - Activation Functions

Papers - Pre-training - Layer Initialization

Papers - Pre-training - Layer Initialization - LSUV

Papers - Image - Datasets - ImageNet

Papers - University - Czech Technical University

Papers - Pre-training - Weight Initialization

Models - Instruct - Context - 128k

Models - Text - Long Context

Papers - Audio - Attention - FlashSpeech

Papers - Command-R

Papers - Cohere

Papers - Pre-training - Text - Cross-lingual

Papers - Training - KL-divergence Upper bound (KLUB)

Papers - Twelve Labs

Papers - Audio - Latent Consistency Model (LCM)

Papers - Audio - Discriminator - Adversarial Loss

Papers - Audio - Prosody Generator

Papers - Audio - Voice Conversion

Papers - University - Inner Mongolia University

Papers - University - Beijing University

Papers - Attention - Flash Attention

Papers - MobiLlama

Papers - Fine-tuning - Dataset - Instruct - UltraFeedback

Papers - Fine-tuning - PEFT

Papers - Fine-tuning - DoRA

Papers - OpenELM

Papers - Fine-tuning - Text - Bottleneck - RMSNorm

Models - OpenELM

Papers - Training Research - Flash Memory - DRAM

Papers - Attention - Sparse Attention

Papers - Attention - Hard Attention

Papers - Image - Mask2Former

Papers - Training - Early Exit - Gating Network

Papers - Image - Detectron2

Paper - Image - Segmentation - Cost vs Quality - Gating Net

Papers - University - University of California Riverside

Papers - NEC Laboratories

Papers - Image - Cost Reduction - Early Exit

Papers - Custom Layers - No Dropout - Batch Normalization

Papers - Model - Inception

Papers - Pre-training - Batch Normalization

Papers - Image - Training - Per-class Regressor (PCR)

Papers - Healthcare - DNA

Papers - Healthcare - Mamba

Papers - University - University of Massachusetts

Papers - Fine-tuning - Multilingual - Multi-task

Papers - Fine-tuning - Transfer Learning - Cross-Lingual

Papers - Fine-tuning - Named Entity Recognition (NER)

Papers - Fine-tuning - Part of Speech (POS)

Papers - University - University of Groningen

Papers - Cross-lingual

Models - Multilingual - Rag - Catalan, Spanish, English

Datasets - Text - Multilingual - Catalan, Spanish, English

Models - Audio - TTS - Catalan

Datasets - Text - Web, Medical Journals

Spaces - Image - Clothing

Papers - Coding - Knowledge Graphs

Papers - Knowledge Graphs - Construction and Validation

Papers - Rag - Knowledge Graphs

Papers - Documents - Knowledge Graphs

Papers - Data Extraction - OpenIE

Papers - Prompt - Knowledge Graphs

Papers - Knowledge Graphs - Prompts

Papers - Knowledge Graphs - Validation - Pydantic

Papers - Quantexa

Papers - Knowledge Graphs - Llama 2

Papers - Apple - CoreNet

Papers - Training - Contrastive Loss - CatLIP

Papers - Image - Classification- WordNet synsets

Papers - Image - Pre-training - Transfer Learning

Papers - Mixture of Data Experts (MoDE)

Papers - Pre-training - Continual - Expert Onboarding

Papers - Image - MoDE - Clip

Papers - Training - Image - MoE - Clip

Papers - Image - Pre-training - Distribution Clustering

Papers - Embeddings - Clustering

Papers - Image - Encoders - MetaClip

Papers - Embeddings - Text - SimCSE

Papers - Embeddings - Text - TF-IDF

Papers - Pre-training - MoE - Flexible Expert Ensembles

Papers - MoE - Training - Expert Prioritization

Papers - Pre-training - MoE - Continual Learning

Papers - Pre-Training - MoE - Train One Expert

Papers - Inference - MoE - Routing with Task Metadata

Papers - MoE - Inference - Routing with Task Metadata

Papers - Image - Datasets - Flickr

Papers - Image - Encoders - OpenClip

Papers - MoE - Image - MoDE

Papers - Image - Benchmarks - Clip

Papers - Image - Datasets - LAION

Papers - MoE - Routing - Softmax Normalization

Papers - Attention - BASS

Papers - 3DGS - Segmentation

Papers - 3D - NeRF

Papers - 3D - Interactive - Semantic Editing based on Loss

Papers - 3D - Interactive

Papers - 3D - Gaussian Splatting and NeRF

Papers - University - The Chinese University of Hong Kong

Papers - SenseTime Research

Papers - Benchmarks - Multimodal

Papers - Benchmarks - Multimodal - SEED-Bench

Papers - Multimodal - Benchmarks - Report

Papers - ARC Lab

Papers - Inference - Early Exit

Papers - Inference - Draft Model - Early Exit - Dropout

Papers - Prompts - Adversarial

Papers - Agent - Image

Papers - Agent - Robotics

Papers - Agent - Tasks

Papers - Healthcare - Fine-tuning

Papers - Healthcare - Chain of Reasoning (CoR)

Papers - Chain of Reasoning (CoR)

Papers - Training - Self-Guided with Search

Papers - Inference - Uncertainty-Guided Search

Papers - Healthcare - VQA - Understanding

Papers - Healthcare - Multimodal

Papers - Healthcare - Biomedical Research

Papers - Gemini

Papers - Healthcare - Prompts

Papers - Healthcare - Surgery - VQA

Papers - Healthcare - Radiology Objects in Context (ROCO)

Papers - Healthcare - Benchmarks - Text - NEJM

Papers - Healthcare - Benchmarks - Text - MMMU-HM

Papers - Healthcare - Benchmarks - Long Context - MIMIC-III

Papers - Healthcare - Benchmarks - VQA - MedVidQA

Papers - Healthcare - Benchmarks - Video - Cholec80

Papers - Healthcare - Benchmarks - Video - Cholec80-CVS

Papers - Healthcare - Report

Papers - Speculative Decoding - Early Exit

Papers - 3D - Garment

Papers - Training - Multi-Model Evaluation

Papers - Training - Multi-Model Evaluation - PoLL

Papers - Training - Evaluation - Multi-Hop QA

Papers - Prompts - Training - Evaluation - Multi-Hop QA

Papers - Agent - Training

Papers - Agent - Fine-tuning

Papers - Agent - Evaluation

Papers - Blender

Papers - 3D - Blender

Papers - 3D - Mesh Editing

Papers - 3D - Texture Editing

Papers - 3D - Lighting

Papers - Video - Robot Simulator - VQA

Papers - World Sim - VQA

Papers - World Sim - Scene Generation

Papers - University - Central South University

Papers - Image - Fine-tuning - Dataset - StylusDocs

Papers - Image - Multi-Model Evaluation

Papers - Image - Datasets - DOCCI

Papers - Image - Annotation Pipeline

Papers - Image - Annotation UI

Papers - 3DGS - Test - Dataset - RealEstate10k

Papers - 3DGS - Test - Dataset - Objaverse

Papers - Image - Detailed Multi-Object Generation

Papers - SK Telecom

Papers - 3DGS - Point Cloud - COLMAP

Papers - 3DGS - Tabular Structure Detection

Papers - 3DGS - Test - PSNR

Papers - 3DGS - Structure Preservation

Papers - University - Imperial College London

Papers - Custom Layers - KAN

Papers - Octopus

Papers - Nexa AI

Papers - Alternative Layers - KAN instead of MLP

Papers - California Institute of Technology

Papers - National Science Foundation (NSF)

Papers - University - University College London

Papers - ICL - Induction Head

Papers - ICL - Induction Circuit

Papers - ICL - Training - Activations - Clamping

Papers - Ensemble

Papers - Audio - Codec - Bitrate - Low

Papers - Model Editing

Papers - Image - Comics

Papers - Image - Multi-Caption Generation

Papers - University - Nankai University

Papers - Institute - Nankai Int Advanced Research Institute

Papers - Fine-tuning - LoRA - LoRAX

Spaces - Comics and Cartoons

Papers - Training - Datasets - Few-Shot Learning - OmniGlot

Papers - Emergent Properties - ICL - Induction Heads

Papers - Custom Layers - No Dropout - Dropout Regularization

Papers - Custom Layers - Residual Connection - Ablation

Papers - Ablation - Attention - Head Pruning

Papers - XAI - Attention - Induction Heads

Papers - Attention - Induction Heads

Papers - Attention - Ablation

Papers - Training - Ablation

Papers - Attention - Previous Token Head

Papers - Training Research - Loss Dynamics - Clamping

Papers - Training Research - Clamping

Papers - XAI - Induction Head - Phase Change - Components

Papers - ICL - Induction Head - Num Labels vs Classes - Loss

Papers - ICL - Induction Circuit - Data Dependent Learning

Papers - Training - ICL - Induction Circuit Evolution

Papers - ICL - Induction Head - Copy vs QK Match

Papers - ICL - Phase Change - Delay - Classes and Labels

Papers - XAI - Framework - pyvene

Papers - Pr(Ai)2R Group

Papers - Training - Interventions - Understanding

Papers - ICL - Locating Early and Late Fact Associations

Papers - ICL - Training - Distributed Alignment Search

Papers - ICL - Phase Change Delay - Large Vocabulary Size

Papers - XAI - Attention - LayerNorm

Models - MoE - Reward Model

Papers - Reward Model - Preference Collection Construction

Papers - Reward Model - Model Merging vs Joint Training

Papers - Model Merging - DARE better than TIES

Datasets - Reward Model - Preference Collection

Papers - ICL - Residual Head Hypothesis

Papers - Dataset Storage - Orc vs Parquet

Papers - Dataset Storage - Parquet

Papers - Dataset Storage - Orc

Papers - Voltron Data

Papers - Dataset Storage - cuDF - Parquet and Orc

Papers - Dataset Storage - Zarr

Papers - Dataset Storage - Technical Report

Papers - Dataset Storage - Lessons Learned

Papers - BitNet

Papers - Pre-training - Rerankers

Papers - Fine-tuning - Rerankers

Models - Coding - Code Interpreter - Agent - Multi-shot

Papers - Training - Math

Papers - FNet - Fourier Transformers

Papers - Mamba - Mamba 2

Papers - Training - Cost Estimates

Papers - Epoch AI

Papers - Training - Historical GPU Cost Trends

Papers - Training - Report - Historical Cost Estimates

Papers - Reasoning - Complex - Alice in Wonderland - AIW

Papers - Reasoning - Complex - TACT

Papers - Text - Table Generation - Pandas DataFrames

Papers - Reasoning - Prompt - Table and Calculations

Papers - Coding - Table and Calculations using Pandas

Papers - Reasoning - Datasets - TACT

Models - Video - Captions

Datasets - Video - Captions

Papers - Chain of Thoughts - Multi-Shot - Buffer of Thoughts

Papers - Training Research - Clamping

updated May 5

Modifying activations during training with proper gradient flow

What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

Paper • 2404.07129 • Published Apr 10 • 3
Note See Appendix D.2