OmniEcho: Spatial Audio Understanding for Embodied Agents Paper • 2609.23407 • Published 10 days ago • 33
All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation Paper • 2609.27901 • Published 7 days ago • 18
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue Paper • 2609.26780 • Published 8 days ago • 100
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs Paper • 2609.26796 • Published 8 days ago • 36
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction Paper • 2609.24983 • Published 9 days ago • 55
When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation Paper • 2609.20942 • Published 13 days ago • 9
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 13 days ago • 137
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX Paper • 2609.18011 • Published 14 days ago • 30