Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
ARO: A New Lens On Matrix Optimization For Large ModelsMicrosoft · arXiv (Cornell University)Feb 9GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model EditingMicrosoft · arXiv (Cornell University)Feb 9Stress-Testing Alignment Audits With Prompt-Level Strategic DeceptionAlphabet, Google DeepMind · arXiv (Cornell University)Feb 9CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time ComputeGoogle DeepMind · arXiv (Cornell University)Feb 9Dual perception-aware blind image quality assessment with semantic-distortion integration and dynamic global–local refinementAlibaba · DisplaysFeb 9SparseEval: Efficient Evaluation of Large Language Models by Sparse OptimizationMicrosoft · arXiv (Cornell University)1 citationFeb 8UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image CandidatesAlibaba · arXiv (Cornell University)Feb 8Horizon Imagination: Efficient On-Policy Rollout in Diffusion World ModelsMicrosoft · arXiv (Cornell University)Feb 8CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal AttributionAlphabet, Google DeepMind · arXiv (Cornell University)Feb 8SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-NormAlibaba · arXiv (Cornell University)Feb 8Combating Mobile Messaging Spam: Modern Protection Strategies for SMS and Chat PlatformsMicrosoft · Journal of Information Systems Engineering & ManagementFeb 8Reducing Isotropy and Volume to KLS: Faster Rounding and Volume AlgorithmsOpenAI · Journal of the ACM4 citationsFeb 7SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain ManagementAlibaba · arXiv (Cornell University)3 citationsFeb 7A Holistic Framework for Automated Configuration Recommendation for Cloud Service MonitoringMicrosoft · arXiv (Cornell University)Feb 7Compact Conformal SubgraphsAlphabet · arXiv (Cornell University)Feb 7ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon SetsMicrosoft · arXiv (Cornell University)Feb 7ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMsAlibaba · arXiv (Cornell University)Feb 7When Is Enough Not Enough? Illusory Completion in Search AgentsLG AI Research · arXiv (Cornell University)Feb 7Rational TransductorsAlphabet · arXiv (Cornell University)Feb 7How does longer temporal context enhance multimodal narrative video processing in the brain?Microsoft · arXiv (Cornell University)Feb 7Pull Requests as a Training Signal for Repo-Level Code EditingMicrosoft · Research Portal (King's College London)Feb 7An operational reliability and service assurance framework for enterprise IT systems supporting large user populationsMicrosoft · Gulf Journal of Engineering & Technology6 citationsFeb 6KSIQA: A Knowledge-Sharing Model for No-Reference Image Quality AssessmentAlibaba · IEEE Transactions on Neural Networks and Learning Systems4 citationsFeb 6Massive Sound Embedding Benchmark (MSEB)Alphabet · arXiv (Cornell University)2 citationsFeb 6PlugMem: A Task-Agnostic Plugin Memory Module for LLM AgentsMicrosoft · arXiv (Cornell University)1 citationFeb 6