8 papers
Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
Wanxing Wu, He Zhu, Yixia Li +7
Large language models (LLMs) have achieved success, but cost and privacy constraints necessitate deploying smaller models locally while offloading complex queries to cloud-based mo…
A Very Big Video Reasoning Suite
Maijunxian Wang, Ruisi Wang, Juyi Lin +53
Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally c…
Gluon Generalized TMD signatures at the EIC from exclusive heavy (axial-)vector meson production
Shohini Bhattacharya, David DeAngelo, Lei Yang +2
Potential experimental signatures of gluon generalized transverse momentum-dependent distributions (GTMDs) are proposed via exclusive heavy (axial-)vector meson production in lepto…
Radiance-Field Guided Pretraining: Scaling Localization Models with Unlabeled Wireless Signals
Guosheng Wang, Shen Wang, Lei Yang
Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing. While deep learnin…
ConsistCompose: Unified Multimodal Layout Control for Image Composition
Xuanke Shi, Boxuan Li, Xiaoyang Han +4
Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with imag…
TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception
Zhiying Song, Lei Yang, Fuxi Wen +1
Cooperative perception presents significant potential for enhancing the sensing capabilities of individual vehicles, however, inter-agent latency remains a critical challenge. Late…
StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation
Shangjin Zhai, Zhichao Ye, Jialin Liu +10
Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each…
Discrete Distribution Networks
Lei Yang
We introduce a novel generative model, the Discrete Distribution Networks (DDN), that approximates data distribution using hierarchical discrete distributions. We posit that since…