Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
UniVocal: Unified Speech-Singing Code-Switching SynthesisAlibaba · arXiv (Cornell University)Jun 1Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh TokenizationAlibaba · arXiv (Cornell University)Jun 1Beyond uniform evaluation: Texture-conditioned complementary decomposition and interaction for super-resolution image quality assessmentAlibaba · Digital Signal ProcessingJun 1Explaining sentiment in self-admitted technical debt: a comparative study of model-agnostic explainability methodsAlibaba · International Journal of Intelligent Computing and CyberneticsJun 1BraveGuard: From Open-World Threats to Safer Computer-Use AgentsAlibaba · arXiv (Cornell University)May 31Memory Shot for Long-Term DialogueAlibaba · arXiv (Cornell University)May 30WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache FilteringAlibaba · arXiv (Cornell University)May 30LISA: Linear-Indexed Sparse Attention for Efficient Long-Context ReasoningAlibaba · arXiv (Cornell University)May 29BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMsAlibaba · arXiv (Cornell University)May 29SpecDB: LLM-Generated Customized Databases via Feature-Oriented DecompositionAlibaba · arXiv (Cornell University)May 29Learning Agent-Compatible Context Management for Long-Horizon TasksAlibaba · arXiv (Cornell University)May 29cPMEM: A Design of Byte-Addressable Persistent Memory with Compute Express Link for Data Center ApplicationsAlibaba · Proceedings of the ACM on Measurement and Analysis of Computing SystemsMay 29Physical plausibility reasoning via HCM-GRPO: Empowering compact model for superior performanceAlibaba · Pattern RecognitionMay 29Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation DatasetAlibaba · arXiv (Cornell University)May 28DMC-CF: Dynamic Multimodal CounterFactual QA benchmark for Causal ReasoningAlibaba · arXiv (Cornell University)May 28Robust and Generalizable Safety Steering for Text-to-Image Diffusion TransformersAlibaba · arXiv (Cornell University)May 28Make LLM Learn to Synthesize from Streaming Experiences through FeedbackAlibaba · arXiv (Cornell University)May 28On-Policy Replay for Continual Supervised Fine-TuningAlibaba · arXiv (Cornell University)May 28FinGuard: Detecting Financial Regulatory Non-Compliance in LLM InteractionsAlibaba · arXiv (Cornell University)May 28RTP-LLM: High-Performance Alibaba LLM Inference EngineAlibaba · arXiv (Cornell University)May 28EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended GenerationAlibaba · arXiv (Cornell University)May 28Evolving Skill-Structured Attack Memory Enhances LLM JailbreakingAlibaba · arXiv (Cornell University)May 28STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual EnvironmentsAlibaba · arXiv (Cornell University)May 28GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language ModelsAlibaba · arXiv (Cornell University)May 28CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline MaterialsAlibaba · arXiv (Cornell University)May 28