7 papers
Generalize LMMs to Versatile Visual Modalities via Fabricated Modality Synthesis
Shihao Yuan, Yuanze Li, Ruyi Zhang +2
Despite the advancements of Large Multimodal Models (LMMs) in RGB vision, their ability to generalize to unseen visual modalities remains a largely unexplored challenge. We argue t…
Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
Liu Hanqing, Jianjun Cao, Yuanze Li +1
Deep neural networks exhibit periodic loss spikes during unregularized long-term training, a phenomenon known as the "Slingshot Mechanism." Existing work usually attributes this to…
FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step Computation
Zichen Tang, Haihong E, Rongjin Li +18
We introduce FinMMDocR, a novel bilingual multimodal benchmark for evaluating multimodal large language models (MLLMs) on real-world financial numerical reasoning. Compared to exis…
Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Process
Yuanze Li, Shihao Yuan, Haolin Wang +5
Although recent methods have tried to introduce large multimodal models (LMMs) into industrial anomaly detection (IAD), their generalization in the IAD field is far inferior to tha…
Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection
Yuanze Li, Haolin Wang, Shihao Yuan +6
Due to the training configuration, traditional industrial anomaly detection (IAD) methods have to train a specific model for each deployment scenario, which is insufficient to meet…
Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
Yuanze Li, Chun-Mei Feng, Qilong Wang +2
Human beings can leverage knowledge from relative tasks to improve learning on a primary task. Similarly, multi-task learning methods suggest using auxiliary tasks to enhance a neu…