Shivaen Ramshetty's picture

5 55

Shivaen Ramshetty

shivr

·

AI & ML interests

NLP, CV, Multimodal

Organizations

shivr's activity

upvoted a paper 5 days ago

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Paper • 2404.12253 • Published 12 days ago • 45

upvoted 2 papers 6 days ago

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Paper • 2404.13208 • Published 10 days ago • 36

SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Paper • 2404.14396 • Published 8 days ago • 15

upvoted a paper 18 days ago

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

Paper • 2404.07413 • Published 19 days ago • 32

upvoted 2 papers 26 days ago

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published 28 days ago • 97

Stealing Part of a Production Language Model

Paper • 2403.06634 • Published Mar 11 • 85

upvoted 2 papers 27 days ago

Are large language models superhuman chemists?

Paper • 2404.01475 • Published 28 days ago • 12

Octopus v2: On-device language model for super agent

Paper • 2404.01744 • Published 28 days ago • 50

upvoted a paper 29 days ago

Gecko: Versatile Text Embeddings Distilled from Large Language Models

Paper • 2403.20327 • Published Mar 29 • 40

upvoted 6 papers about 1 month ago

ViTAR: Vision Transformer with Any Resolution

Paper • 2403.18361 • Published Mar 27 • 48

The Unreasonable Ineffectiveness of the Deeper Layers

Paper • 2403.17887 • Published Mar 26 • 73

LLM Agent Operating System

Paper • 2403.16971 • Published Mar 25 • 62

RAFT: Adapting Language Model to Domain Specific RAG

Paper • 2403.10131 • Published Mar 15 • 56

DiPaCo: Distributed Path Composition

Paper • 2403.10616 • Published Mar 15 • 11

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Paper • 2403.09919 • Published Mar 14 • 18

upvoted 5 papers about 2 months ago

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Paper • 2403.09611 • Published Mar 14 • 119

MoAI: Mixture of All Intelligence for Large Language and Vision Models

Paper • 2403.07508 • Published Mar 12 • 68

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Paper • 2403.03853 • Published Mar 6 • 61

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Paper • 2403.03950 • Published Mar 6 • 11

Learning to Decode Collaboratively with Multiple Language Models

Paper • 2403.03870 • Published Mar 6 • 17

upvoted 13 papers 2 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27 • 560

CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models

Paper • 2402.15021 • Published Feb 22 • 11

Genie: Generative Interactive Environments

Paper • 2402.15391 • Published Feb 23 • 67

Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping

Paper • 2402.14083 • Published Feb 21 • 43

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

Paper • 2402.14658 • Published Feb 22 • 76

User-LLM: Efficient LLM Contextualization with User Embeddings

Paper • 2402.13598 • Published Feb 21 • 17

In deep reinforcement learning, a pruned network is a good network

Paper • 2402.12479 • Published Feb 19 • 16

Neural Network Diffusion

Paper • 2402.13144 • Published Feb 20 • 92

AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling

Paper • 2402.12226 • Published Feb 19 • 37

Speculative Streaming: Fast LLM Inference without Auxiliary Models

Paper • 2402.11131 • Published Feb 16 • 41

FiT: Flexible Vision Transformer for Diffusion Model

Paper • 2402.12376 • Published Feb 19 • 46

How to Train Data-Efficient LLMs

Paper • 2402.09668 • Published Feb 15 • 33

Chain-of-Thought Reasoning Without Prompting

Paper • 2402.10200 • Published Feb 15 • 89

upvoted 19 papers 3 months ago

Lumos : Empowering Multimodal LLMs with Scene Text Recognition

Paper • 2402.08017 • Published Feb 12 • 22

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

Paper • 2402.08093 • Published Feb 12 • 52

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Paper • 2402.07033 • Published Feb 10 • 16

Premier-TACO: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Paper • 2402.06187 • Published Feb 9 • 8

ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling

Paper • 2402.06118 • Published Feb 9 • 12

Direct Language Model Alignment from Online AI Feedback

Paper • 2402.04792 • Published Feb 7 • 25

Grandmaster-Level Chess Without Search

Paper • 2402.04494 • Published Feb 7 • 62

MusicRL: Aligning Music Generation to Human Preferences

Paper • 2402.04229 • Published Feb 6 • 16

Learning Universal Predictors

Paper • 2401.14953 • Published Jan 26 • 18

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Paper • 2402.01831 • Published Feb 2 • 11

Rethinking Interpretability in the Era of Large Language Models

Paper • 2402.01761 • Published Jan 30 • 18

Specialized Language Models with Cheap Inference from Limited Domain Data

Paper • 2402.01093 • Published Feb 2 • 45

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Paper • 2312.00752 • Published Dec 1, 2023 • 130

MM-LLMs: Recent Advances in MultiModal Large Language Models

Paper • 2401.13601 • Published Jan 24 • 41

AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents

Paper • 2401.12963 • Published Jan 23 • 11

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

Paper • 2401.12168 • Published Jan 22 • 21

Self-Rewarding Language Models

Paper • 2401.10020 • Published Jan 18 • 134

Improving fine-grained understanding in image-text pre-training

Paper • 2401.09865 • Published Jan 18 • 12

Tuning Language Models by Proxy

Paper • 2401.08565 • Published Jan 16 • 19

upvoted a paper 4 months ago

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Paper • 2312.11514 • Published Dec 12, 2023 • 252

upvoted 2 papers 5 months ago

Honeybee: Locality-enhanced Projector for Multimodal LLM

Paper • 2312.06742 • Published Dec 11, 2023 • 7

Steering Llama 2 via Contrastive Activation Addition

Paper • 2312.06681 • Published Dec 9, 2023 • 9