Coding Agents for Generalized Task and Motion Planning Problems Paper • 2609.30233 • Published 6 days ago • 24
PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing Paper • 2609.23784 • Published 10 days ago • 14
Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament Paper • 2609.26346 • Published 8 days ago • 11
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 13 days ago • 190
LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay Paper • 2609.25053 • Published 23 days ago • 17
All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts Paper • 2609.24058 • Published 9 days ago • 55
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published 8 days ago • 160
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents Paper • 2609.22000 • Published 12 days ago • 79
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence Paper • 2609.05571 • Published 26 days ago • 119
Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches Paper • 2609.17652 • Published 15 days ago • 8
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published 15 days ago • 811
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus Paper • 2609.15504 • Published 16 days ago • 37
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX Paper • 2609.18011 • Published 14 days ago • 30
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction Paper • 2609.13285 • Published 22 days ago • 81
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement Paper • 2609.13406 • Published 19 days ago • 84
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published 23 days ago • 375
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking Paper • 2609.13141 • Published 19 days ago • 65