Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection SamplingAlibaba · arXiv (Cornell University)Jun 10TreeSeeker: Tree-Structured Trial, Error, and Return in Deep SearchMicrosoft · arXiv (Cornell University)Jun 10HALO: Half-Frame-Rate Adaptive Learnable Operator for Lightweight STFT-Based Speech EnhancementHorizon Robotics · arXiv (Cornell University)Jun 10Revisiting InternVL: A Systematic Technical Framework for Building Powerful Open-Source Vision-Language ModelsSenseTime · IEEE Transactions on Pattern Analysis and Machine IntelligenceJun 10Efficient Quantum Hermite TransformAlphabet · ACM Symposium on Theory of Computing (STOC)2 citationsJun 9SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-RefinementMicrosoft · arXiv (Cornell University)1 citationJun 9Improved Pseudorandom Codes from Permuted PuzzlesMicrosoft · ACM Symposium on Theory of Computing (STOC)1 citationJun 9No Exponential Quantum Speedup for SIS∞ AnymoreAlphabet · ACM Symposium on Theory of Computing (STOC)1 citationJun 9Brushing and Interpretive Linking for Knowledge WorkMicrosoft · Graphics InterfaceJun 9ReliveMeet: Interactive Visual Storyboards and Chat-Based Guide for Engaging Experiences Reliving Missed MeetingsMicrosoft · Graphics InterfaceJun 9Mudra: Enabling Microgesture Recognition on COTS SmartwatchesAlphabet · Graphics InterfaceJun 9From Reactive to Autonomous: Evolution of AI Operations in Cloud Network InfrastructureMicrosoft · arXiv (Cornell University)Jun 9Probabilistic Contrastive Pretraining for Multi-task ADME Property PredictionNVIDIA · arXiv (Cornell University)Jun 9Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization SensitivityAlphabet · arXiv (Cornell University)Jun 9Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and TranslationZhipu AI · arXiv (Cornell University)Jun 9How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMsAlibaba · arXiv (Cornell University)Jun 9Express Language ModelingMicrosoft · arXiv (Cornell University)Jun 9Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual ArtifactsMicrosoft · arXiv (Cornell University)Jun 9Benchmarking and Exploring the Capabilities of LLMs for Attack InvestigationsAlphabet · arXiv (Cornell University)Jun 9From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMsAlibaba · arXiv (Cornell University)Jun 9CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMsGoogle DeepMind · arXiv (Cornell University)Jun 9Role-Agent: Bootstrapping LLM Agents via Dual-Role EvolutionAlibaba · arXiv (Cornell University)Jun 9K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language ModelingAlibaba · arXiv (Cornell University)Jun 9Towards Diverse Scientific Hypothesis Search with Large Language ModelsMicrosoft · arXiv (Cornell University)Jun 9Advancing the State-of-the-Art in Empirical Privacy AuditingAlphabet · arXiv (Cornell University)Jun 9