5 papers
RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
Zhaolu Kang, Tailong Luo, Chenxin Li +13
Long chain-of-thought reasoning improves vision-language models (VLMs), but it also exposes a temporal grounding failure: as generation unfolds, models may drift from image evidenc…
DRILL: Training World Models to Improve Policies, Not Predict Pixels
Zhaolu Kang, Tailong Luo, Lei Wei +9
World models are increasingly used to reduce environment interaction when post-training vision-language-action (VLA) policies with reinforcement learning. Yet they are typically tr…
PMMD: A pose-guided multi-view multi-modal diffusion for person generation
Ziyu Shang, Haoran Liu, Rongchao Zhang +2
Generating consistent human images with controllable pose and appearance is essential for applications in virtual try on, image editing, and digital human creation. Current methods…
dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
Yi Xin, Siqi Luo, Tianxiang Xu +13
Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and ef…
Low-Cost Test-Time Adaptation for Robust Video Editing
Jianhui Wang, Yinda Chen, Yangfan He +6
Video editing is a critical component of content creation that transforms raw footage into coherent works aligned with specific visual and narrative objectives. Existing approaches…