Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Large-scale esophageal cancer screening through noncontrast computed tomography and artificial intelligenceAlibaba · Nature MedicineSep 22MemCalib: Benchmarking and Optimizing Memory Use in LLM AgentsAlibaba · arXiv (Cornell University)Sep 21Beyond Endpoint Performance: Process-Level Evaluation of Self-Evolving AgentsAlibaba · arXiv (Cornell University)Sep 21CLOOPD: Closing the Learner Loop in On-Policy DistillationAlibaba · arXiv (Cornell University)Sep 21VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding TasksAlibaba · arXiv (Cornell University)Sep 20MuLA-Bench: A Multilingual Long-Form Audio Understanding Benchmark via Multi-Tier AuditingAlibaba · arXiv (Cornell University)Sep 20Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor ConversationsAlibaba · arXiv (Cornell University)Sep 20RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM AgentsAlibaba · arXiv (Cornell University)Sep 20The Right Future for Action: Learning Action-Relevant Predictive States in World Action ModelsAlibaba · arXiv (Cornell University)Sep 20BabelArena: A Large-Scale Multilingual Benchmark for LLM AgentsAlibaba · arXiv (Cornell University)Sep 20Omni2Web: Benchmarking Audiovisual Website DevelopmentAlibaba · arXiv (Cornell University)Sep 20Block-Sparse Attention with Semantic-Geometric Decoupled RoutingAlibaba · arXiv (Cornell University)Sep 19Auto-Bidding with Disentangled Advertiser Profiles and Train-Free AdaptationAlibaba · arXiv (Cornell University)Sep 18Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal InteractionAlibaba · arXiv (Cornell University)Sep 18Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication OverlapAlibaba · arXiv (Cornell University)Sep 18ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RLAlibaba · arXiv (Cornell University)Sep 18CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video GenerationAlibaba · arXiv (Cornell University)Sep 18Multi-Dimensional Prosody Judgment For Live Streaming Speech SynthesisAlibaba · arXiv (Cornell University)Sep 17RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)Sep 17Generative Query Suggestion via Intent Coverage and Query-Level Credit AssignmentAlibaba · arXiv (Cornell University)Sep 16Behavior2Value: Benchmarking and Empowering LLMs for Consumer Value Measurement from E-commerce BehaviorsAlibaba · arXiv (Cornell University)Sep 16A Zeroth-Order Paradigm for LLM Preference AlignmentAlibaba · arXiv (Cornell University)Sep 16ScienceIDE: Turning World's Scientific Codebase into Agent Learnable EnvironmentsAlibaba · arXiv (Cornell University)Sep 16Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read ItAlibaba · arXiv (Cornell University)Sep 16HBFlex: A Flexible Memory System for Bridging Fine-Grained LLM States and Coarse-Grained HBF Parallel ExecutionAlibaba · arXiv (Cornell University)Sep 16