Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle AgentsiFlytek · arXiv (Cornell University)Mar 25UniScale: Synergistic Entire Space Data and Model Scaling for Search RankingAlibaba · arXiv (Cornell University)Mar 25Enhancing federated unlearning using catastrophic forgetting in heterogeneous Industrial Internet of ThingsAlibaba · Computer CommunicationsMar 25PACMNET V4, CoNEXT1, March 2026 EditorialMeta · Proceedings of the ACM on NetworkingMar 25OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language ModelsAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence4 citationsMar 24Real‐Time Neural Materials on Mobile VRMeta · Computer Graphics Forum1 citationMar 24A Dual Merge Mode for Video CodingAlibaba · DCCMar 24Transform Domain Block and Reference Frame Prediction with Adaptive Predictor CoefficientsAlphabet · DCCMar 24BXRL: Behavior-Explainable Reinforcement LearningAlphabet · arXiv (Cornell University)Mar 24End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic TransitionsAlphabet · arXiv (Cornell University)Mar 24SortedRL: Accelerating RL Training for LLMs through Online Length-Aware SchedulingMicrosoft · arXiv (Cornell University)Mar 24GateSID: Adaptive Gating for Balancing Semantic and Collaborative Signals in RecommendationAlibaba · arXiv (Cornell University)Mar 24KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at TaobaoAlibaba · arXiv (Cornell University)Mar 24EVA: Efficient Reinforcement Learning for End-to-End Video AgentSenseTime · arXiv (Cornell University)Mar 24Leveraging LLMs and Social Media to Understand User Perception of Smartphone-Based Earthquake Early WarningsAlphabet · arXiv (Cornell University)Mar 24Towards Efficient 3D Gaussian Human Avatar Compression: A Prior-Guided FrameworkAlibaba · DCCMar 24Sparse2Dense: A Keypoint-Driven Generative Framework for Human Video Compression and Vertex PredictionAlibaba · DCCMar 24CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge FusionMicrosoft · ACM Transactions on Computer Systems3 citationsMar 23SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) ApplicationsAlibaba · ACM Symposium on Applied Computing2 citationsMar 23Quantum linear system algorithm with optimal queries to initial state preparationAlphabet, Microsoft · Quantum1 citationMar 23Language-Conditioned World Modeling for Visual NavigationMicrosoft · arXiv (Cornell University)Mar 23Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained FusionLG AI Research · arXiv (Cornell University)Mar 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 23