Research

A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.

Field
Lab
Clear filters

2,751 papers from Alibaba in Computer Science, newest first. Some proceedings carry OpenAlex's date of January 1.

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement LearningAlibaba · arXiv (Cornell University)Jul 21Open-Vocabulary Gaze Object Prediction: Benchmark and MethodAlibaba · arXiv (Cornell University)Jul 21Integrating AI Clusters into Virtual Private CloudAlibaba · Asia-Pacific Workshop on Networking (APNet)Jul 21Scaling LLM Agent Tool Access at Cloud ScaleAlibaba · Asia-Pacific Workshop on Networking (APNet)Jul 21When More Is Not Better: Multimodal Information Efficiency in Conversational InterfacesAlibaba · ACM Conference on Conversational User Interfaces (CUI)Jul 21Single-Core Hotspots on Your VNF? Break Them Up!Alibaba · Asia-Pacific Workshop on Networking (APNet)Jul 21cPMEM: A Design of Byte-Addressable Persistent Memory with Compute Express Link for Data Center ApplicationsAlibaba · ACM SIGMETRICS Performance Evaluation ReviewJul 20SpecLA: Efficient Speculative Decoding for Linear-Attention ModelsAlibaba · arXiv (Cornell University)Jul 18Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided RefinementAlibaba · arXiv (Cornell University)Jul 18Scalable LLM Agent Tool Access in the CloudAlibaba · arXiv (Cornell University)Jul 17QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual SidesAlibaba · arXiv (Cornell University)Jul 17Before the Action: Benchmarking LLMs on Prospective Hypothesis DiscoveryAlibaba · arXiv (Cornell University)Jul 17MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video GenerationAlibaba · ACM SIGGRAPH Conference (SIGGRAPH)3 citationsJul 16Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization AgentAlibaba · arXiv (Cornell University)Jul 16CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator DisaggregationAlibaba · arXiv (Cornell University)Jul 16UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World ModelsAlibaba · ACM SIGGRAPH Conference (SIGGRAPH)Jul 16SCOPE: Scale-Consistent One-Pass Estimation of 3D GeometryAlibaba, Horizon Robotics · ACM SIGGRAPH Conference (SIGGRAPH)Jul 16GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow NetworksAlibaba · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)1 citationJul 15PReM: Learning What to Preserve and When to Refresh for Context CompressionAlibaba · arXiv (Cornell University)Jul 15Equity vs. Equality: Optimizing Ranking Fairness for Tailored Provider NeedsAlibaba · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)Jul 15TRACE: Term-level Reasoning And Chain-of-thought Enhanced distillation for E-commerce Multi-modal Relevance LearningAlibaba · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)Jul 15EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content DetectionAlibaba · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)Jul 15Beyond Dense Connectivity: Explicit Sparsity for Scalable RecommendationAlibaba · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)Jul 15KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at TaobaoAlibaba · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)Jul 15UniNDM: A Unified Noise-Driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image GenerationAlibaba · IEEE Transactions on Pattern Analysis and Machine IntelligenceJul 15