A training-free editing framework that reuses a single editor to support diverse video edits across multiple tasks without per-task training.

GraphVid lets users steer video generation via interactive graph controls that align structure, motion, and semantics.

We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, av... Read more

Discrete video VAEs underpin modern text-to-video generation and video understanding systems, yet existing tokenizers typically learn visual codebooks at a single scale with limited vocabularies and s... Read more

Segmentation Vision-Language Models (VLMs) have significantly advanced grounded visual understanding, yet they remain prone to pixel-grounding hallucinations, producing masks for incorrect objects or ... Read more

RewardFlow optimizes image generation pipelines by directly aligning outputs with user-defined reward signals, enabling more reliable control over synthesis objectives.

Recent advances in Large Vision-Language Models (LVLMs) have enabled general-purpose vision tasks through visual instruction tuning. While existing LVLMs can generate segmentation masks from text prom... Read more

Expressing confidence is challenging for embodied agents navigating dynamic multimodal environments, where uncertainty arises from both perception and decision-making processes. We present the first w... Read more

Despite significant advancements in Large Vision-Language Models (LVLMs) capabilities, existing pixel-grounding models operate in single-image settings, limiting their ability to perform detailed, fin... Read more

While numerous environmental factors contribute to the spread of antibiotic resistance genes (ARGs), quantifying their relative contributions remains a fundamental challenge. Similarly, it is importan... Read more