Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable DataGoogle DeepMind · neural information processing systemsJan 1, 2025Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewardsGoogle DeepMind, Meta · neural information processing systemsJan 1, 2025Scalable In-context Ranking with Generative ModelsAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025SegMASt3R: Geometry Grounded Segment MatchingGoogle DeepMind · neural information processing systemsJan 1, 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel OptimizationAlphabet · neural information processing systemsJan 1, 2025IF-Guide: Influence Function-Guided Detoxification of LLMsAnthropic, Google DeepMind · neural information processing systemsJan 1, 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMsAlphabet · neural information processing systemsJan 1, 2025On Traceability in $\ell_p$ Stochastic Convex OptimizationGoogle DeepMind · neural information processing systemsJan 1, 2025Improving LLM General Preference Alignment via Optimistic Online Mirror DescentAlphabet, Microsoft · neural information processing systemsJan 1, 2025Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence AwarenessAlphabet · neural information processing systemsJan 1, 2025Constructing an Optimal Behavior Basis for the Option KeyboardGoogle DeepMind · neural information processing systemsJan 1, 2025Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and ClassificationAlphabet, Microsoft · neural information processing systemsJan 1, 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World ApplicationsAlibaba, Alphabet · neural information processing systemsJan 1, 2025Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and AccelerationAlphabet · neural information processing systemsJan 1, 2025Private Geometric Median in Nearly-Linear TimeAlphabet · neural information processing systemsJan 1, 2025AmorLIP: Efficient Language-Image Pretraining via AmortizationAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm EstimationAlphabet · neural information processing systemsJan 1, 2025Security Signals: Making Web Security Posture Measurable At ScaleAlphabet · Workshop on Measurements, Attacks, and Defenses for the Web (MADWeb)Jan 1, 2025SkillVerse : Assessing and Enhancing LLMs with Tree EvaluationGoogle DeepMind · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1, 2025iTBLS: A Dataset of Interactive Conversations Over Tabular InformationAlphabet · Table Representation Learning Workshop (TRL)Jan 1, 2025Hidden Forms: A Dataset to Fill Masked Interfaces from Language CommandsAlphabet · Workshop for Research on Agent Language Models (REALM)Jan 1, 2025Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation ModelingAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1, 2025Debiasing Online Preference Learning via Preference Feature PreservationAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1, 2025AIOps: the Autonomous Network JourneyAlphabet · Optical Fiber Communication ConferenceJan 1, 2025Interactive Problem Solving in the Classroom: Experiences with Turing Arena Light in Competitive Programming EducationAlphabet · OLYMPIADS IN INFORMATICSJan 1, 2025