Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) ApplicationsAlibaba · ACM Symposium on Applied Computing2 citationsMar 23SkillRouter: Skill Routing for LLM Agents at ScaleAlibaba · arXiv (Cornell University)Mar 23Generalizable Self-Evolving Memory for Automatic Prompt OptimizationAlibaba · arXiv (Cornell University)Mar 23SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image GenerationAlibaba · arXiv (Cornell University)Mar 23Rethinking Token Reduction for Large Vision-Language ModelsAlibaba · arXiv (Cornell University)Mar 23A novel multi-objective SKG-skyline algorithm integrating spatial keyword data transformationAlibaba · Complex & Intelligent SystemsMar 23SMDG: Enhancing In-Memory Dynamic Graph Processing With Storage-Class MemoryAlibaba · IEEE Transactions on Knowledge and Data EngineeringMar 23AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward LearningAlibaba · arXiv (Cornell University)1 citationMar 22AnyPro: Preference-Preserving Anycast Optimization based on Strategic AS-Path PrependingAlibaba · arXiv (Cornell University)Mar 22JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution OptimizationAlibaba · arXiv (Cornell University)Mar 22AgentHER: Hindsight Experience Replay for LLM Agent Trajectory RelabelingAlibaba · arXiv (Cornell University)Mar 22AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query RecommendationAlibaba · arXiv (Cornell University)Mar 20AgenticRS-EnsNAS: Ensemble-Decoupled Self-Evolving Architecture SearchAlibaba · arXiv (Cornell University)Mar 20AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query RecommendationAlibaba · arXiv (Cornell University)Mar 20PoC: Performance-oriented Context Compression for Large Language Models via Performance PredictionAlibaba · arXiv (Cornell University)Mar 20Enhancing 3D medical multi-modal large language models with integrated human body priors for computed tomographyAlibaba · Pattern Recognition1 citationMar 19Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging ApproachAlibaba · arXiv (Cornell University)Mar 18Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduction, and Hybrid Reward ModelingAlibaba · arXiv (Cornell University)Mar 18Beyond Forced Modality Balance: Intrinsic Information Budgets for Multimodal LearningAlibaba · arXiv (Cornell University)Mar 18Revisiting Cross-Attention Mechanisms: Leveraging Beneficial Noise for Domain-Adaptive LearningAlibaba · arXiv (Cornell University)Mar 18Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and MethodAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence5 citationsMar 17Semantic One-Dimensional Tokenizer for Image Reconstruction and GenerationAlibaba · arXiv (Cornell University)Mar 17Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward ModelsAlibaba · arXiv (Cornell University)Mar 17HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language ReasoningAlibaba · arXiv (Cornell University)Mar 17Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward ModelsAlibaba · arXiv (Cornell University)Mar 17