A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
Paper • 2604.19572 • Published • 16
Anwar
abdoali5672
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
None yet
upvoted 2
papers 1 day ago
upvoted a paper 3 days ago
upvoted 4
papers 7 days ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 319
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Paper • 2603.26164 • Published • 359
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Paper • 2604.10098 • Published • 75
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
Paper • 2604.12627 • Published • 98
upvoted 5
papers 17 days ago
Self-Distilled RLVR
Paper • 2604.03128 • Published • 165
LightThinker++: From Reasoning Compression to Memory Management
Paper • 2604.03679 • Published • 37
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 200
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 110
SpikingBrain Technical Report: Spiking Brain-inspired Large Models
Paper • 2509.05276 • Published • 5
upvoted a paper 18 days ago
upvoted 2
papers 21 days ago
upvoted 5
papers 22 days ago
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Paper • 2603.24414 • Published • 183
Dynin-Omni: Omnimodal Unified Large Diffusion Language Model
Paper • 2604.00007 • Published • 19
Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
Paper • 2602.07824 • Published • 18
daVinci-LLM:Towards the Science of Pretraining
Paper • 2603.27164 • Published • 32
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper • 2603.27538 • Published • 144