10 papers
Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding
Qitong Wang, Fan Du, Pranav Maneriker +2
The rapid rise of Vision-Language Models (VLMs) in egocentric visual understanding has made low-latency inference in human-robot collaborative (HRC) tasks increasingly critical. We…
APT: Atomic Physical Transitions for Causal Video-Language Understanding
Shang Wu, Haoran Lu, Songling Liu +6
Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as "bounce" can be correct while hiding the proc…
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
Fan Du, Feng Yan, Jianxiong Wu +8
Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency: multi-step inference is required to re…
PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
Shang Wu, Chenwei Xu, Zhuofan Xia +6
State-of-the-art text-to-video (T2V) generators frequently violate physical laws despite high visual quality. We show this stems from insufficient physical constraints in prompts r…
Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion
Haoran Lu, Shang Wu, Songling Liu +9
Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consiste…
Glow with the Flow: AI-Assisted Creation of Ambient Lightscapes for Music Videos
Frederic Anthony Robinson, Vishnu Raj, David Cooper +2
Designed light is an established modality for live performance and music playback. Despite the growing availability of consumer smart lighting, the creation of designed light for m…
Towards Sparse Video Understanding and Reasoning
Chenwei Xu, Zhen Ye, Shang Wu +8
We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA). Instead of uniformly sampling frames…
DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation
Divyansh Srivastava, Akshay Mehra, Pranav Maneriker +5
Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing t…
MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
Xiyang Wu, Zongxia Li, Jihui Jin +7
Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial interactions. We present a nove…
PictOBI-20k: Unveiling Large Multimodal Models in Visual Decipherment for Pictographic Oracle Bone Characters
Zijian Chen, Wenjie Hua, Jinhao Li +4
Deciphering oracle bone characters (OBCs), the oldest attested form of written Chinese, has remained the ultimate, unwavering goal of scholars, offering an irreplaceable key to und…