4 papers · 1 filter
SAM3-I: Segment Anything with Instructions
Jingjing Li, Yue Feng, Yuchen Guo +10
Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentation, enabling users to segment all instances associated with a given conce…
DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model
Qian Chen, Xianyin Zhang, Lifan Guo +2
Recent advances in vision-language models (VLMs) have enabled end-to-end document parsing and understanding, achieving strong performance on diverse optical character recognition (…
Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
Xu Cai, Yang Wu, Qianli Chen +3
We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel veloci…
Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?
Shuqing Li, Qiang Chen, Xiaoxue Ren +1
Physics Engines (PEs) are fundamental software frameworks that simulate physical interactions in applications ranging from entertainment to safety-critical systems. Despite their i…