Value-Aware Stochastic KV Cache Eviction for Reasoning Models Paper • 2606.03928 • Published 3 days ago • 8
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 9 days ago • 419
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction Paper • 2605.26115 • Published 11 days ago • 51
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published 29 days ago • 233
SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning Paper • 2605.09266 • Published 26 days ago • 14
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents Paper • 2605.05185 • Published about 1 month ago • 102
Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG Paper • 2604.14572 • Published Apr 16 • 7
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 327
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 506
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 366
FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol Paper • 2603.24943 • Published Mar 26 • 12