Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Consensus or Conflict? Fine-Grained Evaluation of Conflicting Answers in Question-AnsweringAlphabet · Workshop on Uncertainty-Aware NLP (UncertaiNLP)Jan 1, 2025Findings of the WMT25 Multilingual Instruction Shared Task: Persistent Hurdles in Reasoning, Generation, and EvaluationAlphabet · Conference on Machine Translation (WMT)Jan 1, 2025Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCoAlphabet · neural information processing systemsJan 1, 2025Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics DataAlphabet · neural information processing systemsJan 1, 2025Training-free Online Video Step GroundingAlphabet · neural information processing systemsJan 1, 2025Zero-Shot Performance Prediction for Probabilistic Scaling LawsAlphabet · neural information processing systemsJan 1, 2025Infinite Neural Operators: Gaussian processes on functionsGoogle DeepMind · neural information processing systemsJan 1, 2025LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert SpaceAlphabet, OpenAI · neural information processing systemsJan 1, 2025Emergence of Linear Truth Encodings in Language ModelsAlphabet · neural information processing systemsJan 1, 2025Layer as Puzzle Pieces: Compressing Large Language Models through Layer ConcatenationAlphabet · neural information processing systemsJan 1, 2025AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-PlayGoogle DeepMind · neural information processing systemsJan 1, 2025Dense SAE Latents Are Features, Not BugsGoogle DeepMind · neural information processing systemsJan 1, 2025Tracing the Representation Geometry of Language Models from Pretraining to Post-trainingAlphabet, Cohere, Google DeepMind · neural information processing systemsJan 1, 2025Reverse Engineering Human Preferences with Reinforcement LearningCohere, Google DeepMind · neural information processing systemsJan 1, 2025Self-Boost via Optimal Retraining: An Analysis via Approximate Message PassingAlphabet · neural information processing systemsJan 1, 2025Hierarchical Retrieval: The Geometry and a Pretrain-Finetune RecipeAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025Gaze Analysis in Early Warning Visual Feedback System for Hand Tracking Failures in Virtual RealityAlphabet · IEEE AccessJan 1, 2025Plasticity as the Mirror of EmpowermentAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video GenerationAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of RandomnessAlphabet · neural information processing systemsJan 1, 2025Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal RatesAlphabet · neural information processing systemsJan 1, 2025Privacy Reasoning in Ambiguous ContextsAlphabet · neural information processing systemsJan 1, 2025Gatekeeper: Improving Model Cascades Through Confidence TuningAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025Meta-learning how to Share Credit among Macro-ActionsGoogle DeepMind · neural information processing systemsJan 1, 2025MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow GenerationAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025