8 papers
Understanding NVIDIA Grace-Blackwell Unified Memory Through Placement-Controlled Microbenchmarks
Nathan Graddon, Aaron Jarmusch, Sunita Chandrasekaran
NVIDIA Grace--Blackwell systems make CPU--GPU memory increasingly unified at the programming level, but unified addressability does not make the memory system uniform. A CUDA manag…
MeSD: Multi-Evidence Self-Distillation for VideoLLM
Weijie Zhu, Han Fang, Hanyu Fu +13
While reinforcement learning with verifiable rewards provides reliable outcome supervision for VideoLLMs, sequence-level rewards offer limited token-level guidance. On-policy self-…
GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding
Hao Li, Han Fang, Zixin Pan +8
Although multimodal large language models (MLLMs) have achieved remarkable progress, understanding 3D spatial relationships from 2D images remains a critical challenge. Existing me…
Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding
Tianyi Gao, Han Fang, Tianyi Ding +9
Multimodal Large Language Models have made great progress in grounding tasks, yet existing methods still struggle to unify precise localization and complex reasoning. For one thing…
Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing
Zijin Yin, Bing Li, Kongming Liang +4
Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is criti…
WAT: Online Video Understanding Needs Watching Before Thinking
Zifan Han, Hongbo Sun, Jinglin Xu +6
Multimodal Large Language Models (MLLMs) have shown strong capabilities in image understanding, motivating recent efforts to extend them to video reasoning. However, existing Video…
Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design
Haoxiang Sun, Tao Wang, Chenwei Tang +2
Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLM…
TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding
Canhui Tang, Zifan Han, Hongbo Sun +7
Multimodal Large Language Models (MLLMs) have demonstrated significant progress in vision-language tasks, yet they still face challenges when processing long-duration video inputs.…