7 papers
UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
Jun Wang, Shuo Tan, Zelong Sun +5
Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge. However, existing visual RAG systems typically rely on generic ret…
SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs
Siting Wang, Minnan Pei, Luoyang Sun +6
Humans can imagine and manipulate visual images mentally, a capability known as spatial visualization. While many multi-modal benchmarks assess reasoning on visible visual informat…
-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
Siting Wang, Xiaofeng Wang, Zheng Zhu +7
Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning…
LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues
Haoyang Li, Zhanchao Xu, Yiming Li +9
Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, exist…
GTA: Grouped-head latenT Attention
Luoyang Sun, Cheng Deng, Jiwen Jiang +5
Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and pe…
AI and Deep Learning for Automated Segmentation and Quantitative Measurement of Spinal Structures in MRI
Praveen Shastry, Bhawana Sonawane, Kavya Mohan +9
Background: Accurate spinal structure measurement is crucial for assessing spine health and diagnosing conditions like spondylosis, disc herniation, and stenosis. Manual methods fo…