70 citations · 184 across the 18 of their papers we have counts for
3 papers · 1 filter
Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision
Hanoona Rasheed, Mohammed Irfan Kurpath, Bin Ren +3
Frontier general-purpose systems are rapidly expanding beyond visual understanding into capabilities traditionally handled by dedicated computer-vision models. As these capabilitie…
Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding
Hanoona Rasheed, Haania Siddiqui, Ming-Hsuan Yang +2
Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval. Existing multimodal large l…
Training-Free Speech-Centric Omni Understanding with Frozen VLMs
Ankan Deria, Hanoona Rasheed, Xilin He +2
Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships. Existing omni models typically…