Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SecureVibe: Making Vibe Coding More SecureMicrosoft · arXiv (Cornell University)Sep 29Retrieval-Augmented Skill Optimization via Cross-Harness AdaptationMeta · arXiv (Cornell University)Sep 29Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before AnsweringAlphabet · arXiv (Cornell University)Sep 29AdaM-Rec: Adaptive Modality Routing for Multimodal RecommendationAlibaba · arXiv (Cornell University)Sep 29AIM: Agentic Idea Management for Automated ResearchAlphabet · arXiv (Cornell University)Sep 29Conditional Generation of Creative Chess Puzzles with Diffusion ModelsGoogle DeepMind · arXiv (Cornell University)Sep 29TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation ModelsAlphabet, Google DeepMind · arXiv (Cornell University)Sep 29Efficient Linkage-Based Compartmentalization on CHERIAlphabet · arXiv (Cornell University)Sep 29Optimal Ground-State Preparation with a Guiding StateAlphabet · arXiv (Cornell University)Sep 29When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM CollaborationAlibaba · arXiv (Cornell University)Sep 29TabFM: A Zero-Shot Foundation Model for Tabular DataAlphabet · arXiv (Cornell University)Sep 29The Safety Operator: Modulating the Expression of Safety Instructions via Spectral OptimizationAlphabet · arXiv (Cornell University)Sep 29How Can Recommendation Feedback Evolve Agent Memory?Alibaba · arXiv (Cornell University)Sep 29BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASRSakana AI · arXiv (Cornell University)Sep 29Local Search for Fair Max-Min DiversificationMicrosoft · arXiv (Cornell University)Sep 29Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMsNVIDIA · arXiv (Cornell University)Sep 29Hierarchical Compression of Vision-Language Model BenchmarksUpstage · arXiv (Cornell University)Sep 29Optimal single-copy estimation of quantum state moments: why $\operatorname{Tr}(ρ^3)$ and $\operatorname{Tr}(ρ^4)$ are equally hardTechnology Innovation Institute · arXiv (Cornell University)Sep 29CounterSteer: Suppressing Indirect Prompt Injection with Activation SteeringMicrosoft · arXiv (Cornell University)Sep 29Beyond Conditional Independence: Root Cause Analysis with Deep Causal ModelsMicrosoft · arXiv (Cornell University)Sep 29Purlin: Separating Orchestration from the Datapath of CollectivesNVIDIA · arXiv (Cornell University)Sep 29Follow the Entities: A Corpus Map for Agentic SearchMicrosoft · arXiv (Cornell University)Sep 29Beyond Interaction Capacity: Estimator Scaling with Recursive Models for CTR PredictionAlphabet · arXiv (Cornell University)Sep 29Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-PolicynessAlibaba · arXiv (Cornell University)Sep 29Towards verifiable quantum advantage with random circuits: Observables that survive concentrationAlphabet · arXiv (Cornell University)Sep 29