Chmielewski

Eryk-Chmielewski's activity

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

upvoted 5 papers 11 days ago

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

Paper • 2601.09688 • Published 16 days ago • 125

MAXS: Meta-Adaptive Exploration with LLM Agents

Paper • 2601.09259 • Published 16 days ago • 95

MemoBrain: Executive Memory as an Agentic Brain for Reasoning

Paper • 2601.08079 • Published 17 days ago • 37

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Paper • 2601.10355 • Published 15 days ago • 39

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published 17 days ago • 146

upvoted a paper 15 days ago

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

Paper • 2601.06487 • Published 20 days ago • 52

upvoted 7 papers 17 days ago

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

Paper • 2601.04720 • Published 22 days ago • 51

MiMo-V2-Flash Technical Report

Paper • 2601.02780 • Published 24 days ago • 33

Nested Learning: The Illusion of Deep Learning Architectures

Paper • 2512.24695 • Published about 1 month ago • 42

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

Paper • 2601.06002 • Published 21 days ago • 51

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

Paper • 2512.24615 • Published about 1 month ago • 119

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published 22 days ago • 211

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 30 days ago • 289

liked a model 17 days ago

AngelSlim/Qwen3-VL-30B-A3B-Instruct_eagle3

0.1B • Updated 17 days ago • 60 • 1

upvoted a collection 17 days ago

EAGLE3

Collection

The collection of eagle3 series models for Qwen3 and Hunyuan. • 15 items • Updated 17 days ago • 3

liked 4 models 17 days ago

AngelSlim/Qwen3-32B_eagle3

Updated 17 days ago • 69 • 3

meituan/EvoCUA-8B-20260105

Image-Text-to-Text • 9B • Updated about 21 hours ago • 686 • 14

openbmb/AgentCPM-Explore

Text Generation • 4B • Updated 12 days ago • 3.46k • 401

Spirit-AI-robotics/Spirit-v1.5

Updated 19 days ago • 143 • 28

reacted to AdinaY's post with 🚀 17 days ago

view post

Post

2847

AgentCPM-Explore🔥 on device agent foundation model released by OpenBMB
openbmb/AgentCPM-Explore
✨ 4B - Apache2.0
✨ Supports 100+ multi-turn environment interactions with search + verification
✨ Full training/inference stack is openly shared as well

See translation

• 

🚀

8

8

❤️

2

2

+

Reply