4 papers
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
Yuchen Xian, Yunqiu Xu, Yang He +1
Multimodal image fusion aims to integrate complementary information from different modalities into a fused image that preserves rich local details while maintaining globally consis…
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
Yuchen Xian, Yang He, Yunqiu Xu +1
Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-…
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
Shuhang Chen, Hangjie Yuan, Yunqiu Xu +5
Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and inte…
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
Shuhang Chen, Yunqiu Xu, Junjie Xie +7
Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is…