Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Block Disentanglement in CRL: Bridging Identifiability and Visual State EstimationGoogle DeepMind · arXiv (Cornell University)Oct 5HERA: Harness-Environment Co-Evolution for Reliable Agentic AbstentionAllen Institute for AI · arXiv (Cornell University)Oct 5IdeaLens: Detecting AI Ideas in Long-form WritingAlphabet · arXiv (Cornell University)Oct 5Crossing Realities Has a Cost: Evaluating AR Second Screens for AI-Assisted Desktop AuthoringAlphabet · ACM Symposium on Spatial User Interaction (SUI)Oct 5JIVEAdapter: A Multi-Task Additive Low-Rank Adapter via Joint and Individual Variation Explained (JIVE)Microsoft · arXiv (Cornell University)Oct 4MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-TrainingAlibaba · arXiv (Cornell University)Oct 4Look Where You Say You're Looking: Self-Grounded Attention for Visual ReasoningNVIDIA · arXiv (Cornell University)Oct 4Towards Unbiased On-Policy Distillation for Block Diffusion Language ModelsAlibaba · arXiv (Cornell University)Oct 4ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon AgentsMicrosoft · arXiv (Cornell University)Oct 4OpticalRec: Unified Optical Vision-Language Representation for Multimodal RecommendationAlibaba · arXiv (Cornell University)Oct 4EchoChat: Structured Cognitive Reasoning in Empathetic Spoken DialogueMicrosoft · arXiv (Cornell University)Oct 4Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon TasksAlibaba · arXiv (Cornell University)Oct 4Causal Improvement Graph for Agentic Harness OptimizationAlibaba · arXiv (Cornell University)Oct 4TeleTune: Evolving Agent Skills From Offline TelemetryMicrosoft · arXiv (Cornell University)Oct 4Optimal and Verifiable Quantum Advantages in Communication ComplexityAlphabet · arXiv (Cornell University)Oct 4Geometry-Aware Preference Optimization for Text-to-Image Diffusion ModelsAlibaba · arXiv (Cornell University)Oct 4Cut Binary Cross Entropy: Efficient Large-Vocabulary Loss and Gradient Kernels for Sequential RecommendationAlphabet · arXiv (Cornell University)Oct 4AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVDMicrosoft · arXiv (Cornell University)Oct 3Principles that Guide, Actions that Inform: Agent Evolution via Knowledge AbstractionAlibaba · arXiv (Cornell University)Oct 3Indistinguishability Lifting for Keyed Oracles, Compressed Ideal Cipher, and More ApplicationsTechnology Innovation Institute · arXiv (Cornell University)Oct 3Playing social deduction games with reinforcement fine-tuned large language modelsAlibaba · arXiv (Cornell University)Oct 3A Bird's-Eye View of Iterative Reward DesignAnthropic · arXiv (Cornell University)Oct 3Prompt-Consistency Inference for Zero-Shot Flow-Matching Text-to-Speech ModelsMicrosoft · arXiv (Cornell University)Oct 3TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation ModelsAlphabet · arXiv (Cornell University)Oct 3XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary DecisionsSenseTime · arXiv (Cornell University)Oct 3