Chmielewski

Eryk-Chmielewski's activity

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

upvoted a collection 2 days ago

Weekly Releases (Oct 26–Nov 01, 2026)

Collection

Repositories created 2026-10-26 through 2026-11-01 (Europe/Istanbul); models/Spaces 15+ likes, datasets 10+ likes. • 83 items • Updated 3 days ago • 3

upvoted a collection 3 days ago

Meituan Robotics

Collection

0 items • Updated 1 day ago • 2

upvoted 5 papers 4 days ago

MemoryWalker: Stop Training Agents on Contexts They Never Saw

Paper • 2609.00865 • Published Sep 1 • 1

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Paper • 2610.11794 • Published 29 days ago • 37

Cortex: Consolidating Context into Parametric Memory

Paper • 2610.20399 • Published 23 days ago • 69

Agentic Memory Management Is the Next Frontier of Information Retrieval

Paper • 2610.32464 • Published 14 days ago • 1

Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought

Paper • 2610.30755 • Published 15 days ago • 22

upvoted a collection 5 days ago

LFM2.5-24B Harness adapters

Collection

A collection of models trained with RL on specific adapters for more efficient agentic development • 6 items • Updated 4 days ago • 24

upvoted 2 papers 6 days ago

WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

Paper • 2610.37161 • Published 10 days ago • 41

Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training

Paper • 2610.40362 • Published 8 days ago • 11

upvoted a collection 9 days ago

Ling Med

Collection

2 items • Updated 9 days ago • 3

upvoted 4 papers 10 days ago

On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models

Paper • 2610.32770 • Published 14 days ago • 31

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Paper • 2610.33956 • Published 12 days ago • 35

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 11 days ago • 115

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

Paper • 2610.33568 • Published 13 days ago • 39

upvoted 2 collections 11 days ago

Spark-X2.6

Collection

SOTA On-Device LLMs. Advancing the Frontier of On-Device Agents for Real-World Tasks. • 14 items • Updated 5 days ago • 43

Sage-A1.5

Collection

7 items • Updated 15 days ago • 16

upvoted a paper 11 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published Sep 17 • 203

upvoted a paper 15 days ago

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

Paper • 2510.18855 • Published Oct 21, 2025 • 74

upvoted a collection 16 days ago

MoESQ

Collection

Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores. • 6 items • Updated 15 days ago • 6