Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Efficient Multilingual Reasoning Transfer via Progressive Code-SwitchingAlibaba · arXiv (Cornell University)Jul 1M2Note: Continual Evolution of Vision Language Models via Mistake Notebook LearningAlibaba · arXiv (Cornell University)Jul 1AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual SynchronizationAlibaba · arXiv (Cornell University)Jul 1DanceDiT: towards efficient and consistent human image animation with diffusion transformerAlibaba · Visual IntelligenceJul 1MaTe3D: Mask-Guided Text-based 3D-Aware Portrait EditingAlibaba · International Journal of Computer VisionJul 1BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative DecodingAlibaba · arXiv (Cornell University)Jun 30Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal IndexAlibaba · arXiv (Cornell University)Jun 30CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement RecipesAlibaba · arXiv (Cornell University)Jun 30Investigating the Effect of Class Imbalance on the Performance of Self-Admitted Technical Debt Prediction ModelsAlibaba · International Journal of Software Engineering and Knowledge EngineeringJun 30Dynamo: Dynamic Skill-Tool Evolution for Vision-Language AgentsAlibaba · arXiv (Cornell University)Jun 29A Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure DiagnosisAlibaba · arXiv (Cornell University)Jun 28The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-trainingAlibaba · arXiv (Cornell University)Jun 28The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement LearningAlibaba · arXiv (Cornell University)Jun 28A Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure DiagnosisAlibaba · arXiv (Cornell University)Jun 28MedP-CLIP: Medical CLIP with region-aware prompt integrationAlibaba · Medical Image AnalysisJun 27HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-SpeechAlibaba · arXiv (Cornell University)Jun 26Diagnosing Task Insensitivity in Language AgentsAlibaba · arXiv (Cornell University)Jun 25Discovering Millions of Interpretable Features with Sparse AutoencodersAlibaba · arXiv (Cornell University)Jun 25SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing AlignmentAlibaba · arXiv (Cornell University)Jun 24PolicyAlign: Direct Policy-Based Safety Alignment for Large Language ModelsAlibaba · arXiv (Cornell University)Jun 24Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing AgentsAlibaba · arXiv (Cornell University)Jun 24SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing AlignmentAlibaba · arXiv (Cornell University)Jun 24Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed TomographyAlibaba · arXiv (Cornell University)Jun 24Large Models for Time Series and Spatio-Temporal Data: A Survey and OutlookAlibaba · ACM Computing Surveys57 citationsJun 23ActPlane: Programmable OS-Level Policy Enforcement for Agent HarnessesAlibaba · arXiv (Cornell University)Jun 23