CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 7 days ago • 252
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production Paper • 2605.11733 • Published 8 days ago • 3
MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks Paper • 2604.27818 • Published 20 days ago • 5
From Context to Skills: Can Language Models Learn from Context Skillfully? Paper • 2604.27660 • Published 17 days ago • 157
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model Paper • 2604.20796 • Published 28 days ago • 240
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents Paper • 2604.07429 • Published Apr 8 • 121
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published Apr 9 • 290
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 324
Emergent Compositional Communication for Latent World Properties Paper • 2604.03266 • Published Mar 18 • 7
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 364
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 503
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 342