10 papers
StreamScout: Learning When to Look Deeper for Streaming Video Understanding
Ce Zhang, Jing Bi, Jinxi He +9
Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily focus on what to retain in a…
LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos
Ce Zhang, Jinxi He, Katia Sycara +1
Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. While recent keyframe sampling…
Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
Muyi Bao, Yuxin Cai, Hang Xu +7
Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as…
SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling
Zhifei Xu, Jierui Lan, Zixuan Liang +2
Agentic Large Language Model (LLM) systems decompose complex tasks into workflow Directed Acyclic Graphs (DAGs) whose primitives must be scheduled on heterogeneous clusters. Existi…
Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory
Ce Zhang, Jinxi He, Junyi He +2
Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pres…
ROAP: A Reading-Order and Attention-Prior Pipeline for Optimizing Layout Transformers in Key Information Extraction
Tingwei Xie, Jinxin He, Yonghong Song
The efficacy of Multimodal Transformers in visually-rich document understanding (VrDU) is critically constrained by two inherent limitations: the lack of explicit modeling for logi…
: Generating Instructional Illustrations via Text-Conditioned Diffusion
Jing Bi, Pinxin Liu, Ali Vosoughi +3
The effective communication of procedural knowledge remains a significant challenge in natural language processing (NLP), as purely textual instructions often fail to convey comple…
Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
Yunlong Tang, Jing Bi, Chao Huang +16
We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects…
Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
Jing Bi, Susan Liang, Xiaofei Zhou +16
Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their re…
VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity
Jing Bi, Junjia Guo, Susan Liang +8
Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLL…