Rafael Coelho de Souza Krzonkalla

krzonkalla's activity

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

upvoted 7 papers 3 months ago

Reasoning with Sampling: Your Base Model is Smarter Than You Think

Paper • 2510.14901 • Published Oct 16, 2025 • 48

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

Paper • 2510.20187 • Published Oct 23, 2025 • 19

Accelerating Vision Transformers with Adaptive Patch Sizes

Paper • 2510.18091 • Published Oct 20, 2025 • 7

Unified Reinforcement and Imitation Learning for Vision-Language Models

Paper • 2510.19307 • Published Oct 22, 2025 • 31

olmOCR 2: Unit Test Rewards for Document OCR

Paper • 2510.19817 • Published Oct 22, 2025 • 16

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Paper • 2510.18927 • Published Oct 21, 2025 • 84

Extracting alignment data in open models

Paper • 2510.18554 • Published Oct 21, 2025 • 10

upvoted 9 papers 4 months ago

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16, 2025 • 106

The Art of Scaling Reinforcement Learning Compute for LLMs

Paper • 2510.13786 • Published Oct 15, 2025 • 32

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

Paper • 2510.13554 • Published Oct 15, 2025 • 58

Cautious Weight Decay

Paper • 2510.12402 • Published Oct 14, 2025 • 9

HoneyBee: Data Recipes for Vision-Language Reasoners

Paper • 2510.12225 • Published Oct 14, 2025 • 11

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

Paper • 2510.11496 • Published Oct 13, 2025 • 5

Reinforcing Diffusion Models by Direct Group Preference Optimization

Paper • 2510.08425 • Published Oct 9, 2025 • 12

NorMuon: Making Muon more efficient and scalable

Paper • 2510.05491 • Published Oct 7, 2025 • 9

Fast-dLLM v2: Efficient Block-Diffusion LLM

Paper • 2509.26328 • Published Sep 30, 2025 • 57

upvoted 4 papers 5 months ago

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17, 2025 • 15

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

Paper • 2509.15194 • Published Sep 18, 2025 • 33

A Survey of Reinforcement Learning for Large Reasoning Models

Paper • 2509.08827 • Published Sep 10, 2025 • 190

The Majority is not always right: RL training for solution aggregation

Paper • 2509.06870 • Published Sep 8, 2025 • 15