Papers

• ReCoSplat: Autoregressive Feed-Forward Gaussian Splatting Using Render-and-Compare

  Hong Kong University of Science and Technology, Shanghai Jiao Tong University, Swiss Federal Institute of Technology in Zurich, University of California, Merced

  Published on: 2026-03-10 6 authors
• MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

  Brown University, University of Illinois Urbana-Champaign, University of Maryland, University of Southern California, Washington University in St. Louis

  Published on: 2026-03-10 11 authors
• Retrieval-Augmented Gaussian Avatars: Improving Expression Generalization

  Bar-Ilan University, OriginAI, Technion – Israel Institute of Technology, The Hebrew University of Jerusalem

  Published on: 2026-03-09 8 authors
• Scalable Training of Mixture-of-Experts Models with Megatron Core

  Published on: 2026-03-08 45 authors
• Scalable Training of Mixture-of-Experts Models with Megatron Core

  Published on: 2026-03-08 1 author
• AI+HW 2035: Shaping the Next Decade

  University of Illinois Urbana-Champaign

  Published on: 2026-03-05 1 author
• FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling

  Princeton University

  Published on: 2026-03-05 1 author
• Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline

  Nanjing University

  Published on: 2026-03-05 1 author
• RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots

  The University of Texas

  Published on: 2026-03-04 1 author
• ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning

  Rice University

  Published on: 2026-03-04 1 author
• V1 : Unifying Generation and Self-Verification for Parallel Reasoners

  UC Berkeley

  Published on: 2026-03-04 1 author
• ROBOMETER: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

  University of Southern California

  Published on: 2026-03-02 2 authors
• CuTe Layout Representation and Algebra

  Published on: 2026-03-02 1 author
• Mode Seeking meets Mean Seeking for Fast Long Video Generation

  Published on: 2026-02-27 1 author
• VGG-T3: Offline Feed-Forward 3D Reconstruction at Scale

  University of Toronto

  Published on: 2026-02-26 1 author
• Test-Time Training with KV Binding Is Secretly Linear Attention

  University of Toronto, Vector Institute

  Published on: 2026-02-24 1 author
• Toward the Thermodynamic Limit: Neural Operators for Non-equilibrium Dynamics of Mott Insulators

  California Institute of Technology, ETH Zurich, University of California

  Published on: 2026-02-23 1 author
• El Agente Gráfico: Structured Execution Graphs for Scientific Agents

  University of Toronto

  Published on: 2026-02-19 1 author
• EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data

  University of California

  Published on: 2026-02-18 1 author
• World Action Models are Zero-shot Policies

  Published on: 2026-02-17 1 author
• Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning

  Georgia Institute of Technology, Massachusetts Institute of Technology, Norwegian University of Science and Technology, Robotics and AI Institute, Swiss Federal Institute of Technology in Zurich, The University of Texas, University of California, University of Southern California, University of Toronto

  1 author
• iGRPO: Self-Feedback–Driven LLM Reasonin

  Published on: 2026-02-09 1 author
• DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

  Hong Kong University of Science and Technology, Korea Advanced Institute of Science & Technology, Stanford University, University of California, University of Toronto, University of Washington

  Published on: 2026-02-06 1 author
• Learning to Discover at Test Time

  Stanford University, UC San Diego

  Published on: 2026-02-05 1 author
• Pretraining Large Language Models with NVFP4

  Published on: 2025-09-29 90 authors
• 3D-GENERALIST: Vision-Language-Action Models for Crafting 3D Worlds

  Stanford University

  Published on: 2025-08-19 1 author
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

  Published on: 2025-05-27 1 author
• Describe Anything: Detailed Localized Image and Video Captioning

  UC Berkeley

  Published on: 2025-04-22 11 authors
• One-Minute Video Generation with Test-Time Training

  Stanford University

  Published on: 2025-04-07 1 author
• Data Scaling Laws for End-to-End Autonomous Driving

  New York University, Stanford University, University of Toronto

  Published on: 2025-04-06 10 authors
• Cosmos World Foundation Model Platform for Physical AI

  Published on: 2025-01-07 1 author
• NVLM: Open Frontier-Class Multimodal LLMs

  Published on: 2024-10-22 1 author
• Nemotron-4-340B-Instruct

  Published on: 2024-10-12 1 author
• ChipNeMo: Domain-Adapted LLMs for Chip Design

  Published on: 2024-04-04 1 author
• Eureka: Human-Level Reward Design via Coding Large Language Models

  California Institute of Technology, The University of Texas, University of Pennsylvania

  Published on: 2023-10-19
• SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

  Published on: 2023-10-09 1 author
• Neuralangelo: High-Fidelity Neural Surface Reconstruction

  Johns Hopkins University

  Published on: 2023-06-05 1 author
• Voyager: An Open-Ended Embodied Agent with Large Language Models

  Caltech, Stanford University

  Published on: 2023-05-25 4 authors
• Reflexion: Language Agents with Verbal Reinforcement Learning

  Stanford University

  Published on: 2023-03-20 8 authors
• FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

  University of Michigan

  Published on: 2022-02-22 1 author
• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

  Published on: 2022-01-16 1 author