Jialong Sun

Pillow-1's activity

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

upvoted 3 papers 5 days ago

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

Paper • 2604.08224 • Published 6 days ago • 46

Neural Computers

Paper • 2604.06425 • Published 8 days ago • 27

RAGEN-2: Reasoning Collapse in Agentic RL

Paper • 2604.06268 • Published 8 days ago • 61

upvoted a paper 7 days ago

Can LLMs Learn to Reason Robustly under Noisy Supervision?

Paper • 2604.03993 • Published 10 days ago • 42

upvoted a paper 12 days ago

A Survey of On-Policy Distillation for Large Language Models

Paper • 2604.00626 • Published 13 days ago • 9

upvoted 2 papers 14 days ago

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published 25 days ago • 335

EpochX: Building the Infrastructure for an Emergent Agent Civilization

Paper • 2603.27304 • Published 17 days ago • 47

upvoted a paper 16 days ago

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Paper • 2603.25158 • Published 19 days ago • 50

upvoted a paper 26 days ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published 28 days ago • 138

upvoted 2 papers 28 days ago

EvoClaw: Evaluating AI Agents on Continuous Software Evolution

Paper • 2603.13428 • Published Mar 13 • 21

Attention Residuals

Paper • 2603.15031 • Published 29 days ago • 179

commented a paper 29 days ago

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published Mar 10 • 151 •

7

upvoted 3 papers about 1 month ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 53

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published Mar 10 • 151

SkillNet: Create, Evaluate, and Connect AI Skills

Paper • 2603.04448 • Published Feb 26 • 93

upvoted 3 papers 2 months ago

Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making

Paper • 2602.06570 • Published Feb 6 • 61

MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

Paper • 2602.06075 • Published Feb 3 • 14

CL-bench: A Benchmark for Context Learning

Paper • 2602.03587 • Published Feb 3 • 23

upvoted 2 papers 3 months ago

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published Jan 28 • 68

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Paper • 2601.14724 • Published Jan 21 • 75