Papers
-
Where can AI be used? Insights from a deep ontology of work activitiesFeatured
-
Developments in Artificial Intelligence markets: New indicators based on model characteristics, prices and providersFeatured
-
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
-
A New Look at AI's Impact on Jobs: Firm-Level AI Spending and Workforce Adjustment
-
Intersection theorems over DG-rings revisited
-
Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents
-
MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents
-
AdaJEPA: An Adaptive Latent World Model
-
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
-
FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
-
DOPD: Dual On-policy Distillation
-
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
-
Convergence of Continual Learning in Homogeneous Deep Networks
-
Orca: The World is in Your Mind
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
-
GPC: Large-Scale Generative Pretraining for Transferable Motor Control
-
Using Local Coding Agents
-
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
-
TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents
-
Towards Automating Scientific Review with Google's Paper Assistant Tool
-
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
-
Qwen-Image-2.0-RL Technical Report
-
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
-
Nemotron-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context
-
DanceOPD: On-Policy Generative Field Distillation
-
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
-
OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation
-
Autodata: An agentic data scientist to create high quality synthetic data
-
MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning
-
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
-
Qwen-AgentWorld: Language World Models for General Agents
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
-
Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning
-
You Don't Need to Run Every Eval
-
Tapered Language Models
-
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
-
Unlimited OCR Works
-
Tmax: A simple recipe for terminal agents
-
Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA
-
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams
-
Inverting the Bellman Equation: From $Q$-Values to World Models
-
Sakana Fugu Technical Report
-
HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization
-
MemoryWAM: Efficient World Action Modeling with Persistent Memory
-
Reinforcement Learning Towards Broadly and Persistently Beneficial Models
-
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
-
Explaining Attention with Program Synthesis
-
Towards an Agent-First Web: Redesigning the Web for AI Agents
-
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
-
Agentic Robot Policy Self-Improvement in the Real World
