Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM AgentsAlibaba · arXiv (Cornell University)Sep 16GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language AgentsAlibaba · arXiv (Cornell University)Sep 15Turn-level Multiscale Density Ratio Estimation for LLM AgentsAlibaba · arXiv (Cornell University)Sep 15AgentPProf: Semantic Profiler for Long Horizon AI AgentsAlibaba · arXiv (Cornell University)Sep 14Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-TrainingAlibaba · arXiv (Cornell University)Sep 14PACE: Progressive Angular-to-Norm Contrastive EmbeddingAlibaba · arXiv (Cornell University)Sep 14LazFormer: Scaling Transformers for Industrial Recommendation via Transferable Generative Pre-trainingAlibaba · arXiv (Cornell University)Sep 14The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data SynthesisAlibaba · arXiv (Cornell University)Sep 13VARG: Value-Aware and Ranking-Aligned Generative Retrieval for Dynamic E-commerce SearchAlibaba · arXiv (Cornell University)Sep 13MoUNets: Static-Weighted Ensemble of UNet-Based Experts for Levator Hiatus Segmentation in Pelvic Floor UltrasoundAlibaba · Ultrasound in Medicine & BiologySep 13HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)Sep 12Certifying Model Upgrades with Slice-Wise Non-Regression and Incumbent FallbackAlibaba · arXiv (Cornell University)Sep 12SCOPE-OPSD: Fisher-Conditioned Privileged Subspaces for On-Policy Self-DistillationAlibaba · arXiv (Cornell University)Sep 11MIMA: Multi-Interest Recommendation via Multi-Positive Exclusive AssignmentAlibaba · arXiv (Cornell University)Sep 11LiveProBench: Can Streaming Video Models Really Interact Like Humans?Alibaba · arXiv (Cornell University)Sep 11DiffSynth-Music: Audio-Conditioned KV-Cache Adapters for Controllable Music GenerationAlibaba · arXiv (Cornell University)Sep 11The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language modelsAlibaba · arXiv (Cornell University)Sep 10Fusion-Enhanced Bidirectional Multimodal Entity Linking ModelAlibaba · Engineering Applications of Artificial IntelligenceSep 10RecGPT: A User Intent-Centric Next-Generation LLM-Powered Recommender System in Industrial PracticeAlibaba · ACM Transactions on Information SystemsSep 10Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)Sep 7EAGER: Enrich-and-Align Generative Query Recommendation from Clicked Items in E-commerce SearchAlibaba · arXiv (Cornell University)Sep 7RoLA: Rotary-Positioned Low-Rank Linear Attention for Efficient Diffusion TransformersAlibaba · arXiv (Cornell University)Sep 6Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal ConfirmationAlibaba · arXiv (Cornell University)Sep 5Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language ModelsAlibaba · arXiv (Cornell University)Sep 5UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation ParadigmsAlibaba · arXiv (Cornell University)Sep 5