OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published 6 days ago • 579
Apertus 1.5: From Open Text Models to Open Multimodal Reasoners Paper • 2610.15542 • Published 8 days ago • 40
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published 12 days ago • 91
Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents Paper • 2609.32536 • Published 23 days ago • 13
IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications Paper • 2609.10539 • Published Sep 9 • 26
RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting Paper • 2609.07414 • Published Sep 7 • 9