Chmielewski

Eryk-Chmielewski's activity

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

upvoted a paper about 6 hours ago

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

Paper • 2510.18855 • Published Oct 21, 2025 • 74

liked a model about 12 hours ago

kaitchup/Qwen3.8-27B-SLQ-EAR98

Text Generation • 7B • Updated about 21 hours ago • 17 • 18

liked a model about 21 hours ago

RecursiveSI/flint

Text Generation • 40B • Updated 1 day ago • 420 • 473

liked a model about 22 hours ago

KRAFTON/Raon-1-mini-preview

Text Generation • 29B • Updated about 14 hours ago • 249 • 127

upvoted a collection 1 day ago

MoESQ

Collection

Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores. • 6 items • Updated about 7 hours ago • 5

liked a model 1 day ago

InternScience/Sage-A1.5

Text Generation • 36B • Updated about 4 hours ago • 396 • 209

upvoted 11 papers 1 day ago

RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents

Paper • 2609.23466 • Published about 1 month ago • 1

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published Aug 10 • 806

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

Paper • 2609.07821 • Published Sep 7 • 15

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

Paper • 2609.13443 • Published Sep 11 • 15

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 370

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 22 days ago • 48

What Matters for Latent Reasoning with Flow Matching

Paper • 2610.06666 • Published 18 days ago • 14

How to Loop MoE: Flatten the Experts, Untie the Attention

Paper • 2609.35751 • Published 25 days ago • 15

Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective

Paper • 2610.03185 • Published 21 days ago • 33

Recurrent Looped Transformer

Paper • 2610.07591 • Published 17 days ago • 36

EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory

Paper • 2610.10533 • Published 16 days ago • 9

upvoted 2 collections 1 day ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 489 items • Updated about 23 hours ago • 102

new architecture

Collection

41 items • Updated 2 days ago • 7

upvoted a paper 1 day ago

The Surprising Effectiveness of Shared Memory in Looped Transformers

Paper • 2610.02383 • Published 22 days ago • 1