Rykov Elisei

lmeribal

lmeribal

AI & ML interests

NLP, Multimodality

Recent Activity

upvoted an article 9 days ago

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

upvoted a paper 11 days ago

Chain of Draft: Thinking Faster by Writing Less

upvoted a paper 21 days ago

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

View all activity

Organizations

lmeribal's activity

upvoted an article 9 days ago

Article

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

•

Feb 7

• 70

upvoted a paper 11 days ago

Chain of Draft: Thinking Faster by Writing Less

Paper • 2502.18600 • Published 17 days ago • 44

upvoted a paper 21 days ago

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published 22 days ago • 85

upvoted a paper 28 days ago

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators

Paper • 2502.06394 • Published Feb 10 • 86

upvoted 2 papers about 1 month ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 58

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 112

upvoted a collection about 2 months ago

Zeroshot Classifiers

Collection

These are my current best zeroshot classifiers. Some of my older models are downloaded more often, but the models in this collection are newer/better. • 12 items • Updated Jan 6 • 127

upvoted a paper about 2 months ago

HALoGEN: Fantastic LLM Hallucinations and Where to Find Them

Paper • 2501.08292 • Published Jan 14 • 17

upvoted a paper 2 months ago

Fine-grained Hallucination Detection and Editing for Language Models

Paper • 2401.06855 • Published Jan 12, 2024 • 4

upvoted a paper 4 months ago

Inference Optimal VLMs Need Only One Visual Token but Larger Models

Paper • 2411.03312 • Published Nov 5, 2024 • 7

upvoted 3 papers 5 months ago

upvoted 3 papers 6 months ago

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Paper • 2409.12191 • Published Sep 18, 2024 • 76

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning

Paper • 2409.12568 • Published Sep 19, 2024 • 48

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

Paper • 2409.02813 • Published Sep 4, 2024 • 29

upvoted a paper 7 months ago

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published Aug 22, 2024 • 126

upvoted a collection 7 months ago

Vision-Language Modeling

Collection

Our datasets and models for Visual-Language Modeling • 5 items • Updated Nov 25, 2024 • 6

upvoted 2 papers 8 months ago

Vision language models are blind

Paper • 2407.06581 • Published Jul 9, 2024 • 83

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

Paper • 2407.07053 • Published Jul 9, 2024 • 45