Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Cross-Tokenizer Likelihood Scoring Algorithms for Language Model DistillationMeta · arXiv (Cornell University)3 citationsDec 16, 2025Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language ModelsMicrosoft · arXiv (Cornell University)Dec 16, 2025TorchTraceAP: A New Benchmark Dataset for Detecting Performance Anti-Patterns in Computer Vision ModelsMeta · arXiv (Cornell University)Dec 16, 2025Olmo 3Allen Institute for AI · arXiv (Cornell University)571 citationsDec 15, 2025Motus: A Unified Latent Action World ModelHorizon Robotics · arXiv (Cornell University)248 citationsDec 15, 2025Wait, Wait, Wait... Why Do Reasoning Models Loop?Microsoft · arXiv (Cornell University)34 citationsDec 15, 2025QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory ManagementAlibaba · arXiv (Cornell University)30 citationsDec 15, 2025LongVie 2: Multimodal Controllable Ultra-Long Video World ModelNVIDIA · arXiv (Cornell University)15 citationsDec 15, 2025Let's (not) just put things in Context: Test-Time Training for Long-Context LLMsOpenAI · arXiv (Cornell University)12 citationsDec 15, 2025VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language InferenceAlibaba · arXiv (Cornell University)10 citationsDec 15, 2025Few-Step Distillation for Text-to-Image Generation: A Practical GuideAlibaba · arXiv (Cornell University)8 citationsDec 15, 2025Low-carbon and QoS-aware operation of data centers by AI task splitting and allocationAlibaba · Applied Energy5 citationsDec 15, 2025GPU-accelerated Effective Hamiltonian CalculatorNVIDIA · Quantum4 citationsDec 15, 2025Silent Data Corruption: Optimal Mitigation Strategies for Data Center ComputingNVIDIA · IEEE Micro2 citationsDec 15, 2025I-Scene: 3D Instance Models are Implicit Generalizable Spatial LearnersNVIDIA · arXiv (Cornell University)2 citationsDec 15, 2025Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided ReflectionAlibaba · arXiv (Cornell University)2 citationsDec 15, 2025MIDUS: Memory-Infused Depth Up-ScalingUpstage · arXiv (Cornell University)1 citationDec 15, 2025BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential RecommendationiFlytek · arXiv (Cornell University)1 citationDec 15, 2025AngioDiff: Structure-Preserving and 3D-Consistent Diffusion for CT Angiography SynthesisAlibaba · IEEE International Conference on Bioinformatics and Biomedicine (BIBM)Dec 15, 2025Quantum oracles give an advantage for identifying classical counterfactualsGoogle DeepMind · arXiv (Cornell University)Dec 15, 2025The price of precision: the cost of preprocessing for automated code revision in code reviewGoogle DeepMind · Empirical Software EngineeringDec 15, 2025Incompressibility and Spectral Gaps of Random CircuitsMicrosoft · Annual Symposium on Foundations of Computer Science57 citationsDec 14, 2025Theoretical limitations of multi-layer TransformerAlphabet · Annual Symposium on Foundations of Computer Science50 citationsDec 14, 2025An Improved Greedy Approximation for (Metric) k-MeansAlphabet · Annual Symposium on Foundations of Computer Science8 citationsDec 14, 2025Round Elimination via Self-Reduction: Closing Gaps for Distributed Maximal MatchingAlphabet · Annual Symposium on Foundations of Computer Science8 citationsDec 14, 2025