collaborators

5 papers

cs.CV2026

Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs

Hao-Yu Hsu, Tianhang Cheng, Jing Wen +2

Understanding human activities and their surrounding environments typically relies on visual perception, yet cameras pose persistent challenges in privacy, safety, energy efficienc…

cs.CV2026

T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability

Savya Khosla, Sethuraman T, Aryan Chadha +2

Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-voc…

cs.CV2026

SimpliHuMoN: Simplifying Human Motion Prediction

Aadya Agrawal, Alexander Schwing

Human motion prediction combines the tasks of trajectory forecasting and human pose prediction. For each of the two tasks, specialized models have been developed. Combining these m…

cs.LG2025

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

Ho Kei Cheng, Alexander Schwing

Minibatch optimal transport coupling straightens paths in unconditional flow matching. This leads to computationally less demanding inference as fewer integration steps and less co…

cs.CV2025

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Ho Kei Cheng, Masato Ishii, Akio Hayakawa +3

We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to si…