collaborators

7 papers

cs.LG2026

MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion

Haofeng Huang, Yifei Han, Long Zhang +3

Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions. We propose MVCL-DAF++, which extends MVCL-DAF wi…

cs.CL2026

HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST

Shuyu Zhang, Yifan Wei, Xinru Wang +5

Zero-shot Dialog State Tracking (zs-DST) is essential for enabling Task-Oriented Dialog Systems (TODs) to generalize to new domains without costly data annotation. A central challe…

cs.CV2026

DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models

Chenyang Li, Jieyuan Liu, Bin Li +5

Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to under…

cs.MM2025

CPCLDETECTOR: Knowledge Enhancement and Alignment Selection for Chinese Patronizing and Condescending Language Detection

Jiaxun Yang, Yifei Han, Long Zhang +5

Chinese Patronizing and Condescending Language (CPCL) is an implicitly discriminatory toxic speech targeting vulnerable groups on Chinese video platforms. The existing dataset lack…

cs.CL2025

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning

Haiyang Yu, Yuchuan Wu, Fan Shi +18

Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and unders…

cs.CV2025

See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question Answering

Junjie Wang, Yunhan Tang, Yijie Wang +4

Multimodal Large Language Models (MLLMs) have pushed the frontiers of Knowledge-Based Visual Question Answering (KBVQA), yet their reasoning is fundamentally bottlenecked by a reli…