activity
20242026
collaborators

12 papers

cs.CL2026

Dynamic Linear Attention

Xin Wang, Hui Shen, Boyuan Zheng +7

The scalability of Large Language Models (LLMs) to long contexts is fundamentally constrained by the quadratic complexity of standard attention, motivating the adoption of linear a…

cs.LG2026

QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models

Jingxuan Zhang, Yunta Hsieh, Zhongwei Wan +5

Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing co…

cs.CV2026

MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

Peizhou Huang, Zixuan Zhong, Zhongwei Wan +12

Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA…

cs.CL2025

Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS

Alex ZH Dou, Zhongwei Wan, Dongfei Cui +6

Test-time scaling has emerged as a promising paradigm in language modeling, leveraging additional computational resources at inference time to enhance model performance. In this wo…

cs.CL2025

MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation

Zhongwei Wan, Che Liu, Xin Wang +6

Electrocardiogram (ECG) is the primary non-invasive diagnostic tool for monitoring cardiac conditions and is crucial in assisting clinicians. Recent studies have concentrated on cl…

cs.CV2025

Autoregressive Models in Vision: A Survey

Jing Xiong, Gongye Liu, Lun Huang +17

Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in co…