Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
From Scattered Gaussians to Structured Maps: Efficient Gaussian Splatting Coding via Dual-phase Morton SortingAlibaba · arXiv (Cornell University)Sep 24Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion ProblemsAlphabet · arXiv (Cornell University)Sep 24C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon TasksAlibaba · arXiv (Cornell University)Sep 24On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic VariationSakana AI · arXiv (Cornell University)Sep 24Learning Better Reasoning for Generative Recommendation with Semantic IDsMicrosoft · arXiv (Cornell University)Sep 24agentic-ger: terminology recovery in long-form speech using global contextAlibaba · arXiv (Cornell University)Sep 24The Next Memory Wall: Why Moving Data Will Define the Future of AI InferenceMicrosoft · ComputerSep 24Renegotiating the Social Contract of SearchMicrosoft · ComputerSep 24EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive AlignmentAlibaba · Lecture notes in computer scienceSep 24LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-MakingAlibaba · Lecture notes in computer scienceSep 24Benchmarking Pathology Foundation Models for Spatial Domain UnderstandingAlibaba · Lecture notes in computer scienceSep 24RADAR: A Multimodal Benchmark for 3D Image-Based Radiology Report ReviewMicrosoft · Lecture notes in computer scienceSep 24Xtrace: High-Fidelity GPU Intra-Kernel Tracing via Binary-Level Instruction SplicingMeta · arXiv (Cornell University)Sep 23CinematicVQA: Benchmarking Film-Grammar Reasoning in Large Vision-Language ModelsAlphabet · arXiv (Cornell University)Sep 23Speculative Evaluation of Stochastic LLMsAlibaba · arXiv (Cornell University)Sep 23CART: Closed-Loop Adaptive Red Teaming for Large Language ModelsMicrosoft · arXiv (Cornell University)Sep 23NV-Reason-CT: 3D Visual Language Model for CT AnalysisNVIDIA · arXiv (Cornell University)Sep 23ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)Sep 23MolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular DesignLG AI Research · arXiv (Cornell University)Sep 23When Parallel Drafter Meets Parallel Speculative DecodingAlibaba · arXiv (Cornell University)Sep 23Performance-portable GPU acceleration of the hybrid particle-in-cell code dHybridRCerebras Systems · arXiv (Cornell University)Sep 23Confidence Falls Short: Asymmetric Certainty Gains from Optimization Hinder Multimodal ClassificationAlibaba · arXiv (Cornell University)Sep 23Quantum Advantage in Topological Data Analysis via Mayer HomologyAlphabet · arXiv (Cornell University)Sep 23Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction FollowingAlibaba · arXiv (Cornell University)Sep 23LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language ModelsNVIDIA · arXiv (Cornell University)Sep 23