Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward MisalignmentAlibaba · arXiv (Cornell University)Oct 12Recall Begets Recall: Recurrent Memory Ranking for Personalized LLMsAlibaba · arXiv (Cornell University)Oct 12OncoReg: Medical Image Registration for Oncological ChallengesAlibaba · The Journal of Machine Learning for Biomedical ImagingOct 11SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill CompositionAlibaba · arXiv (Cornell University)Oct 10Last Secure Code Benchmark: Is the Code You Vibe Secure?Alibaba · arXiv (Cornell University)Oct 10What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training StrategiesAlibaba · arXiv (Cornell University)Oct 10Towards Merging-conditional Backdoor Unalignment against Large Language ModelsAlibaba · arXiv (Cornell University)Oct 10Agentic Data Engineering for LLMs: System Design and a Controlled Empirical StudyAlibaba · arXiv (Cornell University)Oct 9Scaling Agentic Data for Long-Horizon Terminal IntelligenceAlibaba · arXiv (Cornell University)Oct 9Why DiT Models Underperform as Representation Learners without Long Skip ConnectionsAlibaba · arXiv (Cornell University)Oct 9Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy LimitsAlibaba · arXiv (Cornell University)Oct 9Test-Time Memory ConstructionAlibaba · arXiv (Cornell University)Oct 9Frontend-Assisted Large Audio-Language Models for SLT2026 SmartGlasses ChallengeAlibaba · arXiv (Cornell University)Oct 9CAST: Credit Alignment for Cross-Tokenizer On-Policy DistillationAlibaba · arXiv (Cornell University)Oct 9Temporal Evidence Forests for Long-Horizon Multi-Party Conversational MemoryAlibaba · arXiv (Cornell University)Oct 9State-OPD: State-Grounded On-Policy Distillation for Multi-Turn AgentsAlibaba · arXiv (Cornell University)Oct 9A lightweight dual-mode optimization for generative face video codingAlibaba · NeurocomputingOct 9SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent TracesAlibaba · arXiv (Cornell University)Oct 8REMORY: Learning Residual Memory for Context CompactionAlibaba · arXiv (Cornell University)Oct 8Beyond Sequences: Distilling Structured Decision Memory for LLM RecommendationAlibaba · arXiv (Cornell University)Oct 8UniData: Universal Multimodal Instruction Generation PipelineAlibaba · arXiv (Cornell University)Oct 8When KL Regularization Misfires in Group Policy OptimizationAlibaba · arXiv (Cornell University)Oct 8V-CoLA: Vision Token Compression with Linear AttentionAlibaba · arXiv (Cornell University)Oct 8Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational AgentsAlibaba · arXiv (Cornell University)Oct 8When Should Agents Think? Adaptive Reasoning via Cross-Turn EstimationAlibaba · arXiv (Cornell University)Oct 8