LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches Paper • 2610.06647 • Published 5 days ago • 42
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks Paper • 2610.05750 • Published 5 days ago • 18
Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering Paper • 2610.05894 • Published 5 days ago • 16
When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model Paper • 2609.34227 • Published 12 days ago • 24
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution Paper • 2610.03675 • Published 8 days ago • 29
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation Paper • 2609.38839 • Published 10 days ago • 80
LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models Paper • 2609.39071 • Published 10 days ago • 64
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop Paper • 2610.00559 • Published 10 days ago • 37
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published 9 days ago • 88
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent Paper • 2610.01215 • Published 9 days ago • 63
SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation Paper • 2609.33399 • Published 13 days ago • 19
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding? Paper • 2609.38079 • Published 11 days ago • 56
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 13 days ago • 672
Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure Paper • 2609.23551 • Published 20 days ago • 7
Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy Paper • 2609.28660 • Published 17 days ago • 16
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published 18 days ago • 93
CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation Paper • 2601.06352 • Published 20 days ago • 7
The Past Frames the Future: Memory for Autoregressive Video Generation Paper • 2609.28466 • Published 17 days ago • 65