Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Intelligent Multi-Cloud Security Incident Remediation Through Automated Response and Compliance EnforcementMicrosoft · International Conference on Innovations in Cybersecurity and Data Science (ICICDS)Jun 25Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across BenchmarksMicrosoft · arXiv (Cornell University)Jun 25Bridging the Scale Gap: Augmenting Human Red-Teaming to Uncover Latent Risks in T2I ModelsAlphabet · ACM Conference on Fairness, Accountability, and Transparency (FAccT)Jun 25Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web AgentsUpstage · arXiv (Cornell University)Jun 25Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across BenchmarksMicrosoft · arXiv (Cornell University)Jun 25DNSMOS-C: Improving End-to-end Speech Quality Models via Contrastive LearningAlphabet · arXiv (Cornell University)Jun 25How Good Can Linear Models Be for Time-Series Forecasting?Sakana AI · arXiv (Cornell University)Jun 25An Empirical Study of LLM-Generated Specifications for VeriFastMeta · arXiv (Cornell University)Jun 25Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman HierarchyTechnology Innovation Institute · arXiv (Cornell University)Jun 25SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural SkillsMicrosoft · arXiv (Cornell University)Jun 25Diagnosing Task Insensitivity in Language AgentsAlibaba · arXiv (Cornell University)Jun 25Learning Anonymous Pricing for Online Resource AllocationAlphabet · arXiv (Cornell University)Jun 25LMs as Task-Specific Knowledge Bases: An Interpretability AnalysisAlphabet · arXiv (Cornell University)Jun 25Discovering Millions of Interpretable Features with Sparse AutoencodersAlibaba · arXiv (Cornell University)Jun 25Witness expansion: A unified framework for analytical and measurable mixed-state resource detectionTechnology Innovation Institute · arXiv (Cornell University)Jun 25The Red Queen Gödel Machine: Co-Evolving Agents and Their EvaluatorsNVIDIA · arXiv (Cornell University)1 citationJun 24Skim and Skip: Hierarchical Adaptive Inference for Efficient Multimodal RetrievalMicrosoft · arXiv (Cornell University)Jun 24Reasoning Allocation as a Privacy Architecture: Tiered Inference for Trusted Execution Environment DeploymentsMeta · International Journal of Artificial Intelligence and Machine LearningJun 24SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing AlignmentAlibaba · arXiv (Cornell University)Jun 24Verifying Intent and Harm: A Unified Defense Against LLM-Generated ThreatsAlphabet · arXiv (Cornell University)Jun 24ConflictScore: Identifying and Measuring How Language Models Handle Conflicting EvidenceMicrosoft · arXiv (Cornell University)Jun 24At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer GeneralizationMeta · arXiv (Cornell University)Jun 24Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational AgentsMicrosoft · arXiv (Cornell University)Jun 24PolicyAlign: Direct Policy-Based Safety Alignment for Large Language ModelsAlibaba · arXiv (Cornell University)Jun 24BitNet Text EmbeddingsMicrosoft · arXiv (Cornell University)Jun 24