Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Incentivizing Strong Reasoning from Weak SupervisionAlibaba, Allen Institute for AI · Conference of the European Chapter of the Association for Computational LinguisticsJan 1ProGVC: Progressive-Based Generative Video Compression via Auto-Regressive Context ModelingAlibaba · Lecture notes in computer scienceJan 1Alleviating Contextual Misguidance: Response-Aware Prompt Compression for Long-Context Question AnsweringAlibaba · IEEE Transactions on Audio Speech and Language ProcessingJan 1Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene EditingAlibaba · Lecture notes in computer scienceJan 1Vascular Anatomy-aware Self-supervised Pre-training for X-ray Angiogram AnalysisAlibaba · IEEE Transactions on Biomedical EngineeringJan 1A Concern-Decoupled Architecture for Scenario-Optimized Congestion Control in Large-Scale Live Video CDNsAlibaba · IEEE Transactions on NetworkingJan 1RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning Under Urban Road ScenariosAlibaba · Lecture notes in computer scienceJan 1Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion ModelsAlibaba · Lecture notes in computer scienceJan 1Automated Profile Inference with Language Model AgentsAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language ModelsAlibaba · Lecture notes in computer scienceJan 1d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Distribution Matching Distillation Meets Reinforcement LearningAlibaba · Lecture notes in computer scienceJan 1RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy OptimizationAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Do LLMs Really Know What They Don’t Know? Internal States Mainly Reflect Knowledge Recall Rather Than TruthfulnessAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation EnergyAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement LearningAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Attention Beyond Neighborhoods: Reviving Transformer for Graph ClusteringAlibaba · IEEE Transactions on Circuits and Systems for Video TechnologyJan 1AnimateAnywhere: Rouse the Background in Human Image AnimationAlibaba · IEEE Transactions on MultimediaJan 1Memp: Exploring Agent Procedural MemoryAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM AgentsAlibaba · Lecture notes in computer scienceJan 1Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action MemoryAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMsAlibaba · Lecture notes in computer scienceJan 1From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive OptimizationAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic ReasoningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented GenerationAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1