Milton Montiel

miltmont's activity

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

liked a Space about 11 hours ago

Running

Featured

81

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

📝

81

Who needs 1T parameters? Olympiad proofs with a 4B model

upvoted a collection about 12 hours ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 227 items • Updated 2 days ago • 51

upvoted 3 papers about 12 hours ago

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published May 7 • 86

Visual Contrastive Self-Distillation

Paper • 2607.21556 • Published 4 days ago • 43

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published 4 days ago • 140

upvoted 2 papers 5 days ago

Group Entropy-Controlled Policy Optimization

Paper • 2607.16850 • Published 9 days ago • 29

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

Paper • 2607.18213 • Published 7 days ago • 76

liked a dataset 6 days ago

allenai/tulu-3-sft-mixture

Viewer • Updated Dec 2, 2024 • 939k • 30.1k • 255

upvoted 2 papers 6 days ago

Understanding Reasoning from Pretraining to Post-Training

Paper • 2607.16097 • Published 10 days ago • 28

DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation

Paper • 2607.13365 • Published 12 days ago • 19

upvoted a paper 7 days ago

On-Policy Delta Distillation

Paper • 2607.15161 • Published 11 days ago • 37

upvoted 3 papers 8 days ago

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Paper • 2602.08354 • Published Feb 9 • 267

Heterogeneous Agent Collaborative Reinforcement Learning

Paper • 2603.02604 • Published Mar 3 • 199

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published Jun 26 • 112

upvoted 2 papers 9 days ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published 11 days ago • 201

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published 11 days ago • 102

upvoted an article 12 days ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 173

upvoted a paper 12 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 19 days ago • 138

upvoted 2 papers 13 days ago

Trust Region Policy Distillation

Paper • 2607.04751 • Published 21 days ago • 34

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published 19 days ago • 26