OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination Paper • 2610.02999 • Published 3 days ago • 6
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction Paper • 2610.01762 • Published 7 days ago • 233
WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing Paper • 2609.20423 • Published 21 days ago • 48
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 22 days ago • 37