Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-SpeechAlibaba · arXiv (Cornell University)Jun 22AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio GenerationAlibaba · arXiv (Cornell University)Jun 22STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and GenerationAlibaba · arXiv (Cornell University)Jun 22StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMsAlibaba · arXiv (Cornell University)Jun 22Agent-as-a-Router: Agentic Model Routing for Coding TasksAlibaba · arXiv (Cornell University)Jun 22Adaptive Recurrent Message Passing for Test Time Computing on GraphsAlibaba · arXiv (Cornell University)Jun 21Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer DecodingAlibaba · arXiv (Cornell University)Jun 20DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuningAlibaba · NeurocomputingJun 19SAC: Disaggregated KV Cache System for Sparse Attention LLMs with CXLAlibaba · arXiv (Cornell University)Jun 18Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement LearningAlibaba · arXiv (Cornell University)Jun 18Marginal Advantage Accumulation for Memory-Driven Agent Self-EvolutionAlibaba · arXiv (Cornell University)Jun 18A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State MachineAlibaba · arXiv (Cornell University)Jun 17Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-DistillationAlibaba · arXiv (Cornell University)Jun 17Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-TrainingAlibaba · arXiv (Cornell University)Jun 17A Survey of Direct Preference Optimization: Datasets, Theories, Variants, and ApplicationsAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence1 citationJun 16Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to UnificationAlibaba · arXiv (Cornell University)Jun 16MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision FactorsAlibaba · arXiv (Cornell University)Jun 16ICBCBench: An Industry Consortium Benchmark for Financial Deep ResearchAlibaba · arXiv (Cornell University)Jun 16Beyond Domains: Reusing Web Skills via Transferable Interaction PatternsAlibaba · arXiv (Cornell University)Jun 16Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and ComposeAlibaba · arXiv (Cornell University)Jun 16Conditional disentangled information bottleneck for multi-view molecular graph representation learningAlibaba · Expert Systems with ApplicationsJun 16MixCache: Mixture-of-Cache for Video Diffusion Transformer AccelerationAlibaba · International Conference on Multimedia Retrieval1 citationJun 15EvoRec: Self Evolving Agentic Recommender SystemsAlibaba · arXiv (Cornell University)Jun 15AI-Enabled Teaching Reform of Database Principles and TechnologyAlibaba · Education Research and DevelopmentJun 15Understanding the Behaviors of Environment-aware Information RetrievalAlibaba · arXiv (Cornell University)Jun 15