17 papers
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging
Jie Cao, Zhenxuan Fan, Zhuonan Wang +8
Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT metho…
Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
Tianwei Lin, Zhongwei Qiu, Jie Cao +7
Medical vision-language models (VLMs) have rapidly advanced as general-purpose multimodal assistants, yet their deployment in 3D Computed Tomography (CT) analysis remains constrain…
EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs
Yang Dai, Dian Jiao, Tianwei Lin +1
The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the ability for MLLMs to recognize fin…
CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
Wei Wang, Yuqian Yuan, Tianwei Lin +4
Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and intera…
IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation
Haoyu Zheng, Tianwei Lin, Wei Wang +4
Real-world industrial inspection requires not only localizing defects, but also explaining them in natural language and generating controlled defect edits. However, existing approa…
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
Juekai Lin, Yun Zhu, Honglin Lin +6
Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While Ti…