Papers
-
Test-Time Training with KV Binding Is Secretly Linear Attention
-
Toward the Thermodynamic Limit: Neural Operators for Non-equilibrium Dynamics of Mott Insulators
-
El Agente Gráfico: Structured Execution Graphs for Scientific Agents
-
EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
-
World Action Models are Zero-shot Policies
-
Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
-
iGRPO: Self-Feedback–Driven LLM Reasonin
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
-
3D-GENERALIST: Vision-Language-Action Models for Crafting 3D Worlds
-
Cosmos World Foundation Model Platform for Physical AI
-
NVLM: Open Frontier-Class Multimodal LLMs
-
Nemotron-4-340B-Instruct
-
ChipNeMo: Domain-Adapted LLMs for Chip Design
-
VOYAGER: An Open-Ended Embodied Agent with Large Language Models
-
Eureka: Human-Level Reward Design via Coding Large Language Models
-
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
-
Neuralangelo: High-Fidelity Neural Surface Reconstruction
-
Voyager: An Open-Ended Embodied Agent with Large Language Models
-
Reflexion: Language Agents with Verbal Reinforcement Learning
-
FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
-
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
