Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Labeling Copilot: A Deep Research Agent for Automated Data Curation in Computer VisionMicrosoft · IEEE International Conference on Big Data (BigData)5 citationsDec 8, 2025ReSTIR PG: Path Guiding with Spatiotemporally Resampled PathsNVIDIA · SIGGRAPH Asia Conference Papers5 citationsDec 8, 2025CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware DiffusionAlibaba · SIGGRAPH Asia Conference Papers5 citationsDec 8, 2025Rethinking Generative Human Video Coding with Implicit Motion TransformationAlibaba · Picture Coding Symposium4 citationsDec 8, 2025Single-step Diffusion-based Video Coding with Semantic-Temporal GuidanceMicrosoft · arXiv (Cornell University)4 citationsDec 8, 2025SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language ModelsAlibaba · arXiv (Cornell University)4 citationsDec 8, 2025LVT: Large-Scale Scene Reconstruction via Local View TransformersAlphabet · SIGGRAPH Asia Conference Papers4 citationsDec 8, 2025Audio Driven Real-Time Facial Animation for Social TelepresenceMeta · SIGGRAPH Asia Conference Papers4 citationsDec 8, 2025A Multi-Grid Implicit Neural Representation for Multi-View VideosNVIDIA · Picture Coding Symposium3 citationsDec 8, 2025SDT-GNN: Streaming-Based Distributed Training Framework for Graph Neural NetworksNVIDIA · IEEE International Conference on Big Data (BigData)3 citationsDec 8, 20254DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous CaptureNVIDIA · SIGGRAPH Asia Conference Papers3 citationsDec 8, 2025High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion ModulationAlibaba · SIGGRAPH Asia Conference Papers3 citationsDec 8, 2025GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving ScenesAlibaba · SIGGRAPH Asia Conference Papers3 citationsDec 8, 2025PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR SystemsMeta · SIGGRAPH Asia Conference Papers3 citationsDec 8, 2025TSGM: Regular and Irregular Time-Series Generation Using Score-Based Generative ModelsLG AI Research · IEEE International Conference on Big Data (BigData)2 citationsDec 8, 2025Keeping Humans in the Loop: The Role of Human Skills in Large Language Model–Based Natural Language ApplicationsAllen Institute for AI · Annual Review of Linguistics2 citationsDec 8, 2025EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the FlySenseTime · SIGGRAPH Asia Conference Papers2 citationsDec 8, 2025Short-Context Dominance: How Much Local Context Natural Language Actually Needs?Google DeepMind · arXiv (Cornell University)1 citationDec 8, 2025How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New BaselineCloudWalk Technology · arXiv (Cornell University)1 citationDec 8, 2025Sample Space Partitioning and Spatiotemporal Resampling for Specular Manifold SamplingNVIDIA · SIGGRAPH Asia Conference Papers1 citationDec 8, 2025HTMMM: Novel Hybrid Truncated Montgomery Modular Multiplication Algorithm and Hardware ArchitectureSenseTime · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems1 citationDec 8, 2025Diffusion-Guided Relighting for Single-Image SVBRDF EstimationNVIDIA · SIGGRAPH Asia Conference Papers1 citationDec 8, 2025HRM^2Avatar: High-Fidelity Real-Time Mobile Avatars from Monocular Phone ScansAlibaba · SIGGRAPH Asia Conference Papers1 citationDec 8, 2025SNSVS: Scalable Network Slicing with Virtualized Systems using Post-Quantum CryptographyNVIDIA · GlobecomDec 8, 2025Loop Filters and Edge Enhancement for Variable Resolution Video CodingAlphabet · Picture Coding SymposiumDec 8, 2025