Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
JOSer: Just-In-Time Object Serialization for Heavy Java Serialization WorkloadsAlibaba · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)Mar 10Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional FlowsAlibaba · arXiv (Cornell University)Mar 9Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional FlowsAlibaba · arXiv (Cornell University)Mar 9VisualDeltas: Learning Preferences from Visual Quality PerturbationsAlibaba · arXiv (Cornell University)Mar 7Efficient K-generalizable Learned SearchAlibaba · arXiv (Cornell University)Mar 6TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor AnalysisAlibaba · arXiv (Cornell University)Mar 6Reference-guided Policy Optimization for Molecular Optimization via LLM ReasoningAlibaba · arXiv (Cornell University)Mar 6Efficient K-generalizable Learned SearchAlibaba · arXiv (Cornell University)Mar 6Making Training-Free Diffusion Segmentors Scale with the Generative PowerAlibaba · arXiv (Cornell University)Mar 6FedAFD: Multimodal Federated Learning via Adversarial Fusion and DistillationAlibaba · arXiv (Cornell University)Mar 5MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language ModelsAlibaba · arXiv (Cornell University)Mar 5SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous IntegrationAlibaba · arXiv (Cornell University)2 citationsMar 4From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal ReasoningAlibaba · arXiv (Cornell University)Mar 4Talk With Your Fingers: A Depth-Aware Benchmark for Air-Writing RecognitionAlibaba · IEEE Transactions on Circuits and Systems for Video TechnologyMar 4How Controllable Are Large Language Models? A Unified Evaluation across Behavioral GranularitiesAlibaba · arXiv (Cornell University)Mar 3S2CDR: Smoothing-Sharpening Process Model for Cross-Domain RecommendationAlibaba · arXiv (Cornell University)Mar 3Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMsAlibaba · arXiv (Cornell University)Mar 3How Controllable Are Large Language Models? A Unified Evaluation across Behavioral GranularitiesAlibaba · arXiv (Cornell University)Mar 3LaSER: Internalizing Explicit Reasoning into Latent Space for Dense RetrievalAlibaba · arXiv (Cornell University)Mar 2AQD: Online Adaptive Query Dispatcher for HTAP DatabasesAlibaba · Proceedings of the VLDB EndowmentMar 1MemPO: Self-Memory Policy Optimization for Long-Horizon AgentsAlibaba · arXiv (Cornell University)Feb 28SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge GraphsAlibaba · arXiv (Cornell University)Feb 28ReMoT: Reinforcement Learning with Motion Contrast TripletsAlibaba · arXiv (Cornell University)Feb 28Geometry OR Tracker: Universal Geometric Operating Room TrackingAlibaba · arXiv (Cornell University)Feb 28MemPO: Self-Memory Policy Optimization for Long-Horizon AgentsAlibaba · arXiv (Cornell University)Feb 28