OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination Paper • 2610.02999 • Published 3 days ago • 6
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines Paper • 2610.01108 • Published 7 days ago • 13
Region-Level Policy Optimization for Fine-grained MLLM Perception Paper • 2609.19745 • Published 21 days ago • 41
Adaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2 Paper • 2608.15380 • Published Sep 6 • 26
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise Paper • 2609.07139 • Published Sep 7 • 17
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published about 1 month ago • 55
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Paper • 2608.13546 • Published Aug 13 • 143