Rania Bouazizi

rbouazizi's activity

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

upvoted 4 papers about 21 hours ago

Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards

Paper • 2610.22448 • Published 7 days ago • 22

AVC-Reward: Event-Centric Audio-Video Consistency Evaluation

Paper • 2610.22321 • Published 7 days ago • 17

Learning to Think and Explore in 3D World

Paper • 2610.21783 • Published 7 days ago • 177

PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

Paper • 2610.21046 • Published 7 days ago • 728

upvoted 2 papers 2 days ago

EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation

Paper • 2610.17560 • Published 9 days ago • 30

CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation

Paper • 2610.20603 • Published 8 days ago • 43

upvoted 2 papers 3 days ago

Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders

Paper • 2610.17771 • Published 9 days ago • 80

DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision

Paper • 2610.19118 • Published 9 days ago • 23

upvoted 5 papers 6 days ago

Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

Paper • 2610.18356 • Published 9 days ago • 134

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Paper • 2609.38847 • Published 22 days ago • 70

Vela: User Behavior as Supervision Sparks LLM Intelligence

Paper • 2610.14709 • Published 12 days ago • 90

X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning

Paper • 2610.16811 • Published 10 days ago • 82

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

Paper • 2610.18860 • Published 9 days ago • 140

upvoted 2 papers 7 days ago

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published 22 days ago • 316

Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps

Paper • 2610.02740 • Published 20 days ago • 12

upvoted 2 papers 8 days ago

Rethinking Relative Policy Differences Transfer of On-Policy Distillation

Paper • 2610.13205 • Published 13 days ago • 18

Reflex: Visually Grounded Reactive Humanoid Control

Paper • 2610.12772 • Published 14 days ago • 156

upvoted 3 papers 9 days ago

VibeEdit: Image Editing with Canvas Instructions

Paper • 2610.12229 • Published 14 days ago • 26

AgentGarten: Code Worlds for Evolving Agents

Paper • 2610.12374 • Published 14 days ago • 294

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

Paper • 2610.02967 • Published 20 days ago • 44