26 papers
Quo Vadis, World Modeling?
Yu Yang, Xuemeng Yang, Licheng Wen +17
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to paralleliz…
UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomy
Yicheng Xu, Jiangning Zhang, Zhucun Xue +5
In-context learning (ICL) enables fast task adaptation from demonstrations without per-task parameter updates but remains highly sensitive to example selection and formatting. In u…
ChatImage: Navigating Long-Form LLM Answers through Interactive Images
Wencan Jiang, Jiangning Zhang, Yong Liu
Large Language Models (LLMs) can produce detailed answers to complex queries, but these answers are typically presented as dense linear text, which makes fine-grained inspection, n…
M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding
Juntao Jiang, Jiangning Zhang, Yali Bi +7
Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, and recent advances have extended this…
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
Bo Yin, Xiaobin Hu, Chengming Xu +6
Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evi…
What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
Hangyu Lin, Chao Wen, Chengming Xu +4
Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-based video editing. The prevai…