evdcush (Evan)

upvoted a collection 6 days ago

H2O Danube3

Collection

6 items • Updated 6 days ago • 47

upvoted a paper 6 days ago

Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing

Paper • 2407.08770 • Published 11 days ago • 16

upvoted a collection 9 days ago

Seamless Communication

Collection

A significant step towards removing language barriers through expressive, fast and high-quality AI translation. • 16 items • Updated Jan 16 • 135

upvoted a paper 9 days ago

Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model

Paper • 2407.07053 • Published 13 days ago • 37

upvoted an article 10 days ago

Article

Orchestration of Experts: The First-Principle Multi-Model System

By

•

May 30

• 15

upvoted 10 papers 10 days ago

Unveiling Encoder-Free Vision-Language Models

Paper • 2406.11832 • Published Jun 17 • 45

Towards Building Specialized Generalist AI with System 1 and System 2 Fusion

Paper • 2407.08642 • Published 11 days ago • 9

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

Paper • 2407.03963 • Published 18 days ago • 13

Understanding Visual Feature Reliance through the Lens of Complexity

Paper • 2407.06076 • Published 14 days ago • 4

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

Paper • 2407.07061 • Published 13 days ago • 23

upvoted 4 articles 10 days ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 238

Article

Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCs

Jun 5

• 14

Article

Announcing New Dataset Search Features

15 days ago

• 17

Article

Create Mixtures of Experts with MergeKit

By

•

Mar 28

• 10

upvoted 2 papers 27 days ago

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Paper • 2406.16860 • Published 28 days ago • 52

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Paper • 2406.15877 • Published 30 days ago • 43

upvoted 4 papers about 1 month ago

Long Code Arena: a Set of Benchmarks for Long-Context Code Models

Paper • 2406.11612 • Published Jun 17 • 20

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

Paper • 2406.11931 • Published Jun 17 • 54

Discovering Preference Optimization Algorithms with and for Large Language Models

Paper • 2406.08414 • Published Jun 12 • 12

What If We Recaption Billions of Web Images with LLaMA-3?

Paper • 2406.08478 • Published Jun 12 • 38

upvoted an article about 1 month ago

Article

Don't repeat yourself - 🤗 Transformers Design Philosophy

Apr 5, 2022

• 7

upvoted 9 papers about 2 months ago

μLO: Compute-Efficient Meta-Generalization of Learned Optimizers

Paper • 2406.00153 • Published May 31 • 9

Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning

Paper • 2406.00392 • Published Jun 1 • 12

Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration

Paper • 2406.01014 • Published Jun 3 • 29

Block Transformer: Global-to-Local Language Modeling for Fast Inference

Paper • 2406.02657 • Published Jun 4 • 36

Self-Improving Robust Preference Optimization

Paper • 2406.01660 • Published Jun 3 • 18

LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes

Paper • 2406.02897 • Published Jun 5 • 13

Audio Mamba: Bidirectional State Space Model for Audio Representation Learning

Paper • 2406.03344 • Published Jun 5 • 16

Xmodel-LM Technical Report

Paper • 2406.02856 • Published Jun 5 • 7

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Paper • 2405.20204 • Published May 30 • 28

upvoted a collection 2 months ago

Phi-3

Collection

Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 23 items • Updated 11 days ago • 372

upvoted 7 papers 2 months ago

How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

Paper • 2106.10270 • Published Jun 18, 2021 • 2

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

Paper • 2404.12253 • Published Apr 18 • 52

Many-Shot In-Context Learning in Multimodal Foundation Models

Paper • 2405.09798 • Published May 16 • 26

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 81

Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection

Paper • 2405.10300 • Published May 16 • 25

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published May 16 • 117

What matters when building vision-language models?

Paper • 2405.02246 • Published May 3 • 93

upvoted 2 collections 2 months ago

SigLIP

Collection

Contrastive (sigmoid) image-text models from https://arxiv.org/abs/2303.15343 • 8 items • Updated 25 days ago • 31

PaliGemma Release

Collection

Pretrained and mix checkpoints for PaliGemma • 16 items • Updated 25 days ago • 124

upvoted 9 papers 2 months ago

Stylus: Automatic Adapter Selection for Diffusion Models

Paper • 2404.18928 • Published Apr 29 • 14

LEGENT: Open Platform for Embodied Agents

Paper • 2404.18243 • Published Apr 28 • 20

Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models

Paper • 2404.18796 • Published Apr 29 • 67

KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published Apr 30 • 102

Octopus v4: Graph of language models

Paper • 2404.19296 • Published Apr 30 • 116

STT: Stateful Tracking with Transformers for Autonomous Driving

Paper • 2405.00236 • Published Apr 30 • 7

Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3

Paper • 2405.00664 • Published May 1 • 18

Self-Play Preference Optimization for Language Model Alignment

Paper • 2405.00675 • Published May 1 • 21

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report

Paper • 2405.00732 • Published Apr 29 • 116

upvoted a collection 2 months ago

Canary

Collection

A collection of multilingual and multitask speech to text models from NVIDIA NeMo 🐤 • 1 item • Updated 5 days ago • 16

upvoted 4 papers 2 months ago

GAIA: a benchmark for General AI Assistants

Paper • 2311.12983 • Published Nov 21, 2023 • 176

Vision Transformers Need Registers

Paper • 2309.16588 • Published Sep 28, 2023 • 73

Large Language Models as Optimizers

Paper • 2309.03409 • Published Sep 7, 2023 • 73

Language Modeling Is Compression

Paper • 2309.10668 • Published Sep 19, 2023 • 82

upvoted a collection 2 months ago

Awesome Document AI

Collection

A collection of open-source document AI 📄 📝 📈 • 27 items • Updated Mar 11 • 43

Evan

AI & ML interests

Organizations

evdcush's activity

Orchestration of Experts: The First-Principle Multi-Model System

Uncensor any LLM with abliteration

Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCs

Announcing New Dataset Search Features

Create Mixtures of Experts with MergeKit

Don't repeat yourself - 🤗 Transformers Design Philosophy