Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement LearningAlibaba · arXiv (Cornell University)Jun 28Evidence-Informed LLM Beliefs for Continual Scientific DiscoveryAllen Institute for AI · arXiv (Cornell University)Jun 28A Self-Supervised Learning Framework for Video Encoding Complexity ClusteringMeta · arXiv (Cornell University)Jun 28A Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure DiagnosisAlibaba · arXiv (Cornell University)Jun 28When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial AnalysisLG AI Research · arXiv (Cornell University)Jun 28Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMsNVIDIA · arXiv (Cornell University)Jun 28CornerCase: Automated Extremal Testing of Protocol Implementations using LLMsMicrosoft · arXiv (Cornell University)Jun 28Energy-Efficient Multimodal Inference Serving with Tri-serveNVIDIA · arXiv (Cornell University)Jun 28NEXT: Reasoning-Driven Video Recommendation via a Vision-Language ModelMeta · arXiv (Cornell University)Jun 27Formal Security Analysis of Agent Protocol CompositionMeta · arXiv (Cornell University)Jun 27Formal Security Analysis of Agent Protocol CompositionMeta · arXiv (Cornell University)Jun 27Agentic Abstention: Do Agents Know When to Stop Instead of Act?Allen Institute for AI · arXiv (Cornell University)Jun 27Phonological Perception of Sign Language ModelsMicrosoft · arXiv (Cornell University)Jun 27SEATauBench: Progressively Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian LanguagesCohere · arXiv (Cornell University)Jun 27MedP-CLIP: Medical CLIP with region-aware prompt integrationAlibaba · Medical Image AnalysisJun 27Intuition-Guided Latent Reasoning for LLM-Based RecommendationMeta · arXiv (Cornell University)Jun 26DeVAR: Low-Dose CT Denoising via Visual Autoregressive ModelingSenseTime · arXiv (Cornell University)Jun 26Intuition-Guided Latent Reasoning for LLM-Based RecommendationMeta · arXiv (Cornell University)Jun 26Linear-size $\ell_1$ sparsifiersMicrosoft · arXiv (Cornell University)Jun 26Agentic Hardware Design as Repository-Level Code EvolutionNVIDIA · arXiv (Cornell University)Jun 26HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-SpeechAlibaba · arXiv (Cornell University)Jun 26SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysisSenseTime · Medical Image AnalysisJun 26Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agentsMicrosoft · ACM Conference on Fairness, Accountability, and Transparency (FAccT)1 citationJun 25OpenMHC: Accelerating the Science of Wearable Foundation ModelsAlphabet · arXiv (Cornell University)Jun 25Enterprise Workload Migration Using a Multi-Cloud Decision Framework for AWS and AzureMicrosoft · International Conference on Innovations in Cybersecurity and Data Science (ICICDS)Jun 25