Pratyay Banerjee

Neilblaze's activity

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

upvoted an article 36 minutes ago

view article

Article

Safety Evals Should Project Test-Time Compute

• 

Cerru02

•

11 days ago

• 4

upvoted a paper 1 day ago

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Paper • 2605.20668 • Published 3 days ago • 11

upvoted 5 papers 2 days ago

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding

Paper • 2605.02290 • Published 19 days ago • 38

Auditing Agent Harness Safety

Paper • 2605.14271 • Published 9 days ago • 54

Self-Distilled Agentic Reinforcement Learning

Paper • 2605.15155 • Published 9 days ago • 107

Code as Agent Harness

Paper • 2605.18747 • Published 5 days ago • 194

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Paper • 2605.13779 • Published 10 days ago • 217

upvoted an article 5 days ago

view article

Article

Unlocking asynchronicity in continuous batching

• 
• 
• +1

ror, pcuenq, ariG23498

•

9 days ago

• 53

upvoted 10 papers 11 days ago

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference

Paper • 2605.07363 • Published 15 days ago • 12

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

Paper • 2605.06638 • Published 16 days ago • 14

AcademiClaw: When Students Set Challenges for AI Agents

Paper • 2605.02661 • Published 19 days ago • 16

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Paper • 2605.05204 • Published 17 days ago • 27

SkillOS: Learning Skill Curation for Self-Evolving Agents

Paper • 2605.06614 • Published 16 days ago • 45

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Paper • 2605.08083 • Published 15 days ago • 66

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Paper • 2605.06130 • Published 16 days ago • 110

Flow-OPD: On-Policy Distillation for Flow Matching Models

Paper • 2605.08063 • Published 15 days ago • 97

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

Paper • 2605.03042 • Published 19 days ago • 119

Heterogeneous Scientific Foundation Model Collaboration

Paper • 2604.27351 • Published 23 days ago • 217

upvoted a collection 24 days ago

MiMo-V2.5

Collection

4 items • Updated 25 days ago • 86

upvoted an article 27 days ago

view article

Article

Tropical Quivers for Modern AI: A Guided Tour of a Research Program

• 

AmelieSchreiber

•

Mar 22

• 3