4 papers
Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples
Weidong Tang, Xinyan Wan, Siyu Li +1
While inference-time scaling has significantly enhanced generative quality in large language and diffusion models, its application to vector-quantized (VQ) visual autoregressive mo…
ZoomV: Temporal Zoom-in for Efficient Long Video Understanding
Junwen Pan, Rui Zhang, Xin Wan +5
Long video understanding poses a fundamental challenge for large video-language models (LVLMs) due to the overwhelming number of frames and the risk of losing essential context thr…
MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
Tao Shen, Xin Wan, Taicai Chen +10
Unified multimodal models aim to integrate understanding and generation within a single framework, yet bridging the gap between discrete semantic reasoning and high-fidelity visual…
TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
Junwen Pan, Qizhe Zhang, Rui Zhang +5
Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding.…