From the 1 of 15 linked papers with an AI index.
15 papers
VisionPulse: A Virtual Reality System Enabling Accessible Discovery and Navigation for Blind and Low Vision Users
Samuel Martin, Pooyan Fazli, Hasti Seifi
Free exploration is an important aspect of many engaging virtual reality (VR) experiences, yet remains largely inaccessible to blind and low vision (BLV) users due to its reliance…
CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation
Chaoyu Li, Fei Tao, Pooyan Fazli
The paper proposes CASHEW, an inference-time method that stabilizes multi-step reasoning in vision-language models by aggregating multiple reasoning trajectories with visual verifi…
EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning
Yogesh Kulkarni, Pooyan Fazli
Egocentric video understanding requires procedural reasoning under partial observability and continuously shifting viewpoints. Current multimodal large language models (MLLMs) stru…
FrameOracle: Learning What to See and How Much to See in Videos
Chaoyu Li, Tianzhi Li, Fei Tao +6
Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of f…
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
Chaoyu Li, Yogesh Kulkarni, Pooyan Fazli
The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference v…
AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video
Yogesh Kulkarni, Pooyan Fazli
Multimodal reasoning over long-horizon video is challenging due to the need for precise spatiotemporal fusion and alignment across modalities. While recent methods such as Group Re…