Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent EvolutionAlibaba · arXiv (Cornell University)May 17AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question AnsweringAlibaba · arXiv (Cornell University)May 17SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS EngineeringAlibaba · arXiv (Cornell University)May 17VGL-DPO: Vision-Guided Lexical Direct Preference Optimization for Mitigating Hallucination in Multimodal Large Language ModelsAlibaba · ACM Transactions on Multimedia Computing Communications and Applications1 citationMay 16Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training StepsAlibaba · arXiv (Cornell University)May 16LERA: LLM-Enhanced RAG for Ad Auction in Generative ChatbotsAlibaba · arXiv (Cornell University)May 15DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text DetectionAlibaba · arXiv (Cornell University)May 15Embedding-perturbed Exploration Preference Optimization for Flow ModelsAlibaba · arXiv (Cornell University)May 15DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text DetectionAlibaba · arXiv (Cornell University)May 15XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge CompositionAlibaba · arXiv (Cornell University)May 14Deep Pre-Alignment for VLMsAlibaba · arXiv (Cornell University)May 14Agentic Reverse Engineering: From I/O to Code with Discovery AgentAlibaba · arXiv (Cornell University)May 14Agentic AI and Human-in-the-Loop Interventions: Field Experimental Evidence from Alibaba's Customer Service OperationsAlibaba · arXiv (Cornell University)May 14Agentic AI and Human-in-the-Loop Interventions: Field Experimental Evidence from Alibaba's Customer Service OperationsAlibaba · arXiv (Cornell University)May 14Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA ArchitectureAlibaba · arXiv (Cornell University)May 14Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RLAlibaba · arXiv (Cornell University)May 14Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching WorkflowsAlibaba · arXiv (Cornell University)May 14Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video ReconstructionAlibaba · arXiv (Cornell University)May 14STRIDE: Learnable Stepwise Language Feedback for LLM ReasoningAlibaba · arXiv (Cornell University)May 13Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive PerspectiveAlibaba · arXiv (Cornell University)May 13PACMMOD, V4, N2 (PODS), May 2026 EditorialAlibaba · Proceedings of the ACM on Management of DataMay 12SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge EvaluationAlibaba · arXiv (Cornell University)May 12Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language ModelsAlibaba · arXiv (Cornell University)May 12SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill GraphsAlibaba · arXiv (Cornell University)May 12Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations MatterAlibaba · arXiv (Cornell University)May 12