13 papers
SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models
Hongxiang Li, Hongxu Chen, Chenyang Zhu +5
Multimodal Large Language Models (MLLMs) have achieved remarkable success in visual understanding but remain constrained in visual generation due to the fundamental feature discrep…
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
Yiming Zhao, Yu Zeng, Wenxuan Huang +11
Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localiza…
LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs
Hongyu Lu, Feng Zhang, Wenwei Jin +5
Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolutio…
GIR-Bench: Versatile Benchmark for Generating Images with Reasoning
Hongxiang Li, Yaowei Li, Bin Lin +7
Unified multimodal models integrate the reasoning capacity of large language models with both image understanding and generation, showing great promise for advanced multimodal inte…
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
Jack Hong, Shilin Yan, Jiayin Cai +3
We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. In contrast to existing…
Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning
Yudi Shi, Shangzhe Di, Qirui Chen +5
Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the…