16 papers
PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle
Yicheng Xiao, Haoxuan Ma, Caorui Li +7
Recent studies develop pixel-level multimodal large language models (MLLMs) that support both Region Segmentation and Region Understanding, extending multimodal interaction from wh…
Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
Kexin Ma, Jing Xiao, Chaofeng Chen +4
Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding less informative visual to…
TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
Fan Yang, Shurong Zheng, Hongyin Zhao +5
Recent Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in image understanding and natural language generation. However, current approaches focus predominan…
UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
Hongyu Guo, Xiangzhao Hao, Jiarui Guo +3
Few-shot fine-grained visual classification (FGVC) aims to leverage limited data to enable models to discriminate subtly distinct categories. Recent works mostly finetuned the pre-…
GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models
Shurong Zheng, Yousong Zhu, Hongyin Zhao +4
Multimodal Large Language Models (MLLMs) have demonstrated impressive progress in single-image grounding and general multi-image understanding. Recently, some methods begin to addr…
From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation
Fan Yang, Zhiyang Chen, Yousong Zhu +2
Current video generation models produce physically inconsistent motion that violates real-world dynamics. We propose TrajVLM-Gen, a two-stage framework for physics-aware image-to-v…