Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Trust The TypicalAlphabet · arXiv (Cornell University)Feb 4Reinforced Attention LearningAlphabet, Google DeepMind · arXiv (Cornell University)Feb 4Scaling Agentic Verifier for Competitive CodingAlibaba · arXiv (Cornell University)Feb 4Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward ModelsAlibaba · arXiv (Cornell University)Feb 4Subliminal Effects in Your Data: A General Mechanism via Log-LinearityMicrosoft · arXiv (Cornell University)Feb 4Audio ControlNet for Fine-Grained Audio Generation and EditingMiniMax · arXiv (Cornell University)Feb 4Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical ReasoningMicrosoft · arXiv (Cornell University)Feb 4Efficient witnessing and testing of magic in mixed quantum statesTechnology Innovation Institute · npj Quantum Information14 citationsFeb 3SCALAR: Spatial-concept alignment for robust vision in harsh open worldSenseTime · Pattern Recognition2 citationsFeb 3Uniformity Preserving Transfer for Visual Prompt Tuning under Long-tailed DistributionMicrosoft · International Journal of Computer Vision1 citationFeb 3SLasH-DSA: Breaking SLH-DSA Using an Extensible End-To-End Rowhammer FrameworkAlphabet, Microsoft · Proceedings of the Microarchitecture Security Conference1 citationFeb 3Unveiling the Global Landscape of Android Security UpdatesAlphabet · IEEE Transactions on Dependable and Secure Computing1 citationFeb 3UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual DocumentsAlibaba · arXiv (Cornell University)Feb 3Phantom Transfer: Data Poisoning can Survive Data-Level DefencesGoogle DeepMind · arXiv (Cornell University)Feb 3One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social IntelligenceMicrosoft · arXiv (Cornell University)Feb 3SCASRec: A Self-Correcting and Auto-Stopping Model for Generative Route List RecommendationAlibaba · arXiv (Cornell University)Feb 3SEW: Strengthening Robustness of Black-box DNN Watermarking via Specificity EnhancementAlibaba · arXiv (Cornell University)Feb 3STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling ModelsAlibaba · arXiv (Cornell University)Feb 3WebSplatter: Enabling Cross-Device Efficient Gaussian Splatting in Web Browsers via WebGPUAlibaba · arXiv (Cornell University)Feb 3Inference-time Unlearning Using Conformal PredictionAlphabet · arXiv (Cornell University)Feb 3RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling AgentsMicrosoft · arXiv (Cornell University)Feb 3Accelerating the Tesseract Decoder for Quantum Error CorrectionAlphabet · arXiv (Cornell University)Feb 3FARTrack: Fast Autoregressive Visual Tracking with High PerformanceAlibaba · arXiv (Cornell University)Feb 3IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement LearningAlibaba · arXiv (Cornell University)Feb 3Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill SynthesisAlibaba · arXiv (Cornell University)Feb 3