collaborators

18 papers

cs.LG2026

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng +4

Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering propertie…

cs.LG2026

Grounding Computer Use Agents on Human Demonstrations

Aarash Feizi, Shravan Nayak, Xiangru Jian +14

Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web…

cs.CV2026

GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation

Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer +3

Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. In this work, we enhance the T2I dive…

cs.CV2026

PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs

Rim Assouel, Amir Bar, Michal Drozdzal +1

Despite remarkable progress in Multimodal Large Language Models (MLLMs), these models still struggle with fine-grained understanding tasks. In this work, we propose Procedurally Ge…

cs.CV2026

Inference-time Physics Alignment of Video Generative Models with Latent World Models

Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich +7

State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency t…

cs.CV2026

The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models

Zhang Xiaofeng, Aaron Courville, Michal Drozdzal +1

Text-to-image (T2I) models offer great potential for creating virtually limitless synthetic data, a valuable resource compared to fixed and finite real datasets. Previous works eva…