Chmielewski

Eryk-Chmielewski's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 collections 2 days ago

DigiRL

Collection

Online RL for digital agents. • 4 items • Updated 28 days ago • 3

Digi-Q

Collection

What will happen if we train a Q function for digital agents? • 4 items • Updated 19 days ago • 3

upvoted a paper 12 days ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published 13 days ago • 67

upvoted a paper 26 days ago

Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning

Paper • 2502.06060 • Published 28 days ago • 34

upvoted 13 papers about 1 month ago

UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Paper • 2501.12326 • Published Jan 21 • 53

RL + Transformer = A General-Purpose Problem Solver

Paper • 2501.14176 • Published Jan 24 • 25

ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer

Paper • 2501.15570 • Published Jan 26 • 23

Towards General-Purpose Model-Free Reinforcement Learning

Paper • 2501.16142 • Published Jan 27 • 26

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published Jan 26 • 63

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

Paper • 2501.16975 • Published Jan 28 • 26

Optimizing Large Language Model Training Using FP4 Quantization

Paper • 2501.17116 • Published Jan 28 • 36

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 108

Large Language Models Think Too Fast To Explore Effectively

Paper • 2501.18009 • Published Jan 29 • 23

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch

Paper • 2501.18512 • Published Jan 30 • 27

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Paper • 2501.18585 • Published Jan 30 • 56

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Paper • 2501.19324 • Published Jan 31 • 38

s1: Simple test-time scaling

Paper • 2501.19393 • Published Jan 31 • 109

upvoted a collection about 1 month ago

HIGGS

Collection

Models prequantized with [HIGGS](https://arxiv.org/abs/2411.17525) zero-shot quantization. Requires the latest `transformers` to run. • 18 items • Updated 10 days ago • 6

upvoted an article about 1 month ago

view article

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 795

upvoted a paper about 1 month ago

Tensor Product Attention Is All You Need

Paper • 2501.06425 • Published Jan 11 • 84