Noam Halevi

NHalevi's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

Paper • 2611.04870 • Published 4 days ago • 11

upvoted a paper 2 days ago

Advancing SVD-based LLM Compression via Layer-Wise Error Model Search

Paper • 2610.32878 • Published 15 days ago • 7

upvoted a paper 4 days ago

Your Benchmark Is an Empirical Measure Over Difficulty

Paper • 2610.29927 • Published 17 days ago • 26

upvoted a paper 5 days ago

HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience

Paper • 2610.34186 • Published 13 days ago • 5

upvoted a paper 7 days ago

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Paper • 2610.32749 • Published 15 days ago • 29

upvoted 2 papers 9 days ago

Can LLMs Uncover Hidden Physical Laws through Free Exploration?

Paper • 2610.37649 • Published 11 days ago • 8

Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

Paper • 2610.35193 • Published 12 days ago • 23

upvoted a paper 10 days ago

On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models

Paper • 2610.32770 • Published 15 days ago • 31

upvoted a paper 13 days ago

CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction

Paper • 2610.13177 • Published 29 days ago • 4

upvoted 2 papers 15 days ago

RealMe: Immersive Volumetric Video from Minimal Captures

Paper • 2610.30023 • Published 17 days ago • 11

Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On

Paper • 2610.25060 • Published 20 days ago • 8

upvoted a paper 16 days ago

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

Paper • 2610.18784 • Published 24 days ago • 119

upvoted a paper 18 days ago

Cortex: Consolidating Context into Parametric Memory

Paper • 2610.20399 • Published 24 days ago • 69

upvoted a paper 19 days ago

GreenWAM: A World Foundation Model for Robotics

Paper • 2610.18774 • Published 25 days ago • 89

upvoted a paper 20 days ago

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

Paper • 2609.33304 • Published Sep 27 • 11

upvoted a paper 21 days ago

Multics: Generative Multi-Player World Model with Hierarchical Communication

Paper • 2610.17201 • Published 26 days ago • 57

upvoted a paper 22 days ago

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Paper • 2610.13166 • Published 29 days ago • 127

upvoted a paper 25 days ago

Semifactual Credit-Augmented Policy Optimization

Paper • 2609.40360 • Published Sep 30 • 15