1 86 99

Jarrod Barnes PRO

Jarrodbarnes

https://arc.computer

AI & ML interests

Continual Learning, Reinforcement Learning

Recent Activity

submitted a paper about 5 hours ago

Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation

authored a paper about 7 hours ago

Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation

liked a dataset about 21 hours ago

nvidia/Nemotron-AIQ-Agentic-Safety-Dataset-1.0

View all activity

Organizations

upvoted a paper about 23 hours ago

Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation

Paper • 2602.07670 • Published 4 days ago • 1

upvoted an article 4 days ago

Article

Where should test-time compute go? Surprisal-guided selection in verifiable environments

4 days ago

•

upvoted a paper 5 days ago

Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents

Paper • 2601.18217 • Published 16 days ago • 11

upvoted a paper 12 days ago

OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence

Paper • 2601.21083 • Published 14 days ago • 1

upvoted a collection 15 days ago

Nemotron-Post-Training-v3

Collection

Collection of datasets used in the post-training phase of Nemotron Nano v3. • 8 items • Updated 7 days ago • 62

upvoted an article 19 days ago

Article

Frontier Security Agents Don't Lack Detection. They Lack Restraint

19 days ago

•

upvoted a paper 22 days ago

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

Paper • 2601.11087 • Published 26 days ago • 11

upvoted an article 22 days ago

Article

M2.1: Multilingual and Multi-Task Coding with Strong Generalization

Jan 5

•

upvoted a paper 26 days ago

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

Paper • 2601.06487 • Published Jan 10 • 52

upvoted 2 papers 28 days ago

CausalARC: Abstract Reasoning with Causal World Models

Paper • 2509.03636 • Published Sep 3, 2025 • 1

Ministral 3

Paper • 2601.08584 • Published 29 days ago • 53

upvoted an article about 1 month ago

Article

NVIDIA brings agents to life with DGX Spark and Reachy Mini

Jan 5

•

upvoted a collection about 1 month ago

Parakeet

Collection

NeMo Parakeet ASR Models attain strong speech recognition accuracy while being efficient for inference. Available in CTC and RNN-Transducer variants. • 16 items • Updated 7 days ago • 54

upvoted an article about 1 month ago

Article

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance

Apr 16, 2025

•

upvoted a paper about 1 month ago

Web World Models

Paper • 2512.23676 • Published Dec 29, 2025 • 27

upvoted an article about 1 month ago

Article

Deriving the DPO Loss from First Principles

Dec 30, 2025

•

upvoted a paper about 1 month ago

Training AI Co-Scientists Using Rubric Rewards

Paper • 2512.23707 • Published Dec 29, 2025 • 21

upvoted 2 papers about 2 months ago

Reinforcement Learning for Self-Improving Agent with Skill Library

Paper • 2512.17102 • Published Dec 18, 2025 • 35

FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published Oct 20, 2025 • 75

upvoted an article about 2 months ago

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

Dec 18, 2025

•

119

Jarrod Barnes PRO

AI & ML interests

Recent Activity

Organizations

Jarrodbarnes's activity

Where should test-time compute go? Surprisal-guided selection in verifiable environments

Frontier Security Agents Don't Lack Detection. They Lack Restraint

M2.1: Multilingual and Multi-Task Coding with Strong Generalization

NVIDIA brings agents to life with DGX Spark and Reachy Mini

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance

Deriving the DPO Loss from First Principles

Tokenization in Transformers v5: Simpler, Clearer, and More Modular