Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Boundary Attention: Learning Curves, Corners, Junctions and GroupingAlphabet · Lecture notes in computer science6 citationsJan 1, 2025Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning ProcessAlphabet, Meta · SSRN Electronic Journal6 citationsJan 1, 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMsAlphabet · neural information processing systems5 citationsJan 1, 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize BetterAlphabet, Google DeepMind · neural information processing systems5 citationsJan 1, 20254KAgent: Agentic Any Image to 4K Super-ResolutionAlphabet, Google DeepMind · neural information processing systems5 citationsJan 1, 2025The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed TextAllen Institute for AI, Google DeepMind, Hugging Face · neural information processing systems5 citationsJan 1, 2025TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-JudgeAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting5 citationsJan 1, 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion ModelsAlphabet · neural information processing systems4 citationsJan 1, 2025AI-Generated Video Detection via Perceptual StraighteningGoogle DeepMind · neural information processing systems4 citationsJan 1, 2025Meaningful Pose-Based Sign Language EvaluationGoogle DeepMind · Conference on Machine Translation (WMT)4 citationsJan 1, 2025Scaling RL to Long VideosAlphabet, NVIDIA · neural information processing systems4 citationsJan 1, 2025MLZero: A Multi-Agent System for End-to-end Machine Learning AutomationAlphabet · neural information processing systems4 citationsJan 1, 2025Embedding-Converter: A Unified Framework for Cross-Model Embedding TransformationAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting4 citationsJan 1, 2025MoLA: MoE LoRA with Layer-wise Expert AllocationAllen Institute for AI, Alphabet · Findings of the Association for Computational Linguistics: NAACL4 citationsJan 1, 2025Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math ProblemsAlphabet, Meta · SSRN Electronic Journal4 citationsJan 1, 2025SpermDet: Structure-Aware Network With Local Context Enhancement and Dual-Path Fusion for Object Detection in Sperm ImagesAlphabet · IEEE Transactions on Instrumentation and Measurement4 citationsJan 1, 2025QuArch: A Question-Answering Dataset for AI Agents in Computer ArchitectureAlphabet, Google DeepMind · IEEE Computer Architecture Letters4 citationsJan 1, 2025Multi-target Stain Normalization for Histology SlidesAlphabet · Lecture notes in computer science4 citationsJan 1, 2025Massively Parallel Minimum Spanning Tree in General Metric SpacesAlphabet · Society for Industrial and Applied Mathematics eBooks4 citationsJan 1, 2025Imagine360: Immersive 360 Video Generation from Perspective AnchorGoogle DeepMind · neural information processing systems4 citationsJan 1, 2025Scaling Image Geo-Localization to Continent LevelAlphabet · neural information processing systems3 citationsJan 1, 2025LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient RenderingAlphabet, Google DeepMind · neural information processing systems3 citationsJan 1, 2025Parameter Efficient Fine-tuning via Explained Variance AdaptationGoogle DeepMind · neural information processing systems3 citationsJan 1, 2025Towards Single-Source Domain Generalized Object Detection via Causal Visual PromptsAlphabet · neural information processing systems3 citationsJan 1, 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned GuidanceGoogle DeepMind · neural information processing systems3 citationsJan 1, 2025