Max Vance

mvance's activity

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

upvoted a paper about 10 hours ago

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

Paper • 2610.08430 • Published 5 days ago • 24

upvoted a paper 5 days ago

Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation

Paper • 2609.38024 • Published 12 days ago • 64

upvoted a paper 15 days ago

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 19 days ago • 164

upvoted a paper 17 days ago

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Paper • 2609.24983 • Published 20 days ago • 55

upvoted 2 papers 18 days ago

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts

Paper • 2609.21346 • Published 23 days ago • 101

Calibrating Teacher--Student Discrepancy for On-Policy Distillation

Paper • 2609.21619 • Published 23 days ago • 13

upvoted a paper 19 days ago

UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation

Paper • 2609.12397 • Published 24 days ago • 46

upvoted a paper 20 days ago

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 27 days ago • 215

upvoted a paper 21 days ago

Modality-Autoregressive World-Action Models

Paper • 2609.17524 • Published 26 days ago • 11

upvoted a paper 23 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 27 days ago • 252

upvoted a paper 24 days ago

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Paper • 2609.15973 • Published 27 days ago • 33

upvoted a paper 26 days ago

World in World: Explore the World with World Models

Paper • 2609.11548 • Published Sep 10 • 33

upvoted a paper 27 days ago

Show-Harness: Just a VLM Agent Can Play Robots

Paper • 2609.10522 • Published Sep 9 • 144

upvoted a paper 28 days ago

Omni Interaction Agent Technical Report

Paper • 2609.08977 • Published Sep 8 • 94

upvoted 2 papers 29 days ago

An Empirical Study on Zero-Data Bootstrapping for Conversational Recommender Systems

Paper • 2504.15476 • Published Aug 28 • 2

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Paper • 2609.08084 • Published Sep 8 • 72

upvoted 4 papers about 1 month ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published Sep 8 • 321

The Attention Triangle in Audio-Video Models

Paper • 2609.03586 • Published Sep 3 • 44

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

Paper • 2609.02750 • Published Sep 2 • 145

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published Sep 3 • 104