Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-TrainingAlibaba · arXiv (Cornell University)Apr 16Modeling LLM Unlearning as an Asymmetric Two-Task Learning ProblemAlibaba · arXiv (Cornell University)Apr 16Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue ModelsAlibaba · arXiv (Cornell University)Apr 16Modeling LLM Unlearning as an Asymmetric Two-Task Learning ProblemAlibaba · arXiv (Cornell University)Apr 16WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-TrainingAlibaba · arXiv (Cornell University)Apr 16Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue ModelsAlibaba · arXiv (Cornell University)Apr 16Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient InferenceAlibaba · arXiv (Cornell University)Apr 15RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache EvictionAlibaba · arXiv (Cornell University)Apr 14RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache EvictionAlibaba · arXiv (Cornell University)Apr 14QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical IntelligenceAlibaba · arXiv (Cornell University)Apr 14PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement LearningAlibaba · arXiv (Cornell University)Apr 14AI UXpert: Comparing the Performance and Perception of AI and Human Experts in B2B Ease of Use EvaluationAlibaba · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)1 citationApr 13DashChat: Interactive Authoring of Performance Dashboard Design Prototypes through Conversation with LLM-Powered AgentsAlibaba · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)1 citationApr 13Hesitation and Tolerance in Recommender SystemsAlibaba · CHI Conference on Human Factors in Computing Systems1 citationApr 13E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-TuningAlibaba · arXiv (Cornell University)Apr 13Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal LanguageAlibaba · arXiv (Cornell University)Apr 13RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test TimeAlibaba · arXiv (Cornell University)Apr 13E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-TuningAlibaba · arXiv (Cornell University)Apr 13OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment SimulationAlibaba · arXiv (Cornell University)Apr 13Judge Like Human Examiners: A Weighted Importance Multi-Point Evaluation Framework for Generative Tasks with Long-form AnswersAlibaba · arXiv (Cornell University)Apr 13Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal LanguageAlibaba · arXiv (Cornell University)Apr 13RTMC: Step-Level Credit Assignment via Rollout TreesAlibaba · arXiv (Cornell University)Apr 13CodeTracer: Towards Traceable Agent StatesAlibaba · arXiv (Cornell University)Apr 13Enabling Low-Latency, GPU-Efficient Serverless Inference with Model SwappingAlibaba · ACM Transactions on Architecture and Code OptimizationApr 13IntentWeave: A Progressive Entry Ladder for Multi-Surface Browser Agents in Cloud PortalsAlibaba · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13