WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Paper • 2609.24984 • Published • 140
Rania Bouazizi
rbouazizi
·
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
upvoted a paper about 8 hours ago
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory upvoted a paper about 8 hours ago
StudentSim: Training LLM-based Student Simulators upvoted a paper about 8 hours ago
VideoGen-Agent: Reinforcing Video Generation AgentsOrganizations
None yet
upvoted 4
papers about 8 hours ago
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 364
VideoGen-Agent: Reinforcing Video Generation Agents
Paper • 2609.24997 • Published • 52
One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
Paper • 2609.23377 • Published • 42
liked 3
datasets 1 day ago
liked 3
models 1 day ago
upvoted 5
papers 1 day ago
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
Paper • 2609.21788 • Published • 13
BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence
Paper • 2609.20886 • Published • 28
MintAct: A Unified Visual Agent for Digital Environments
Paper • 2609.22083 • Published • 32
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
Paper • 2609.21465 • Published • 124
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Paper • 2609.22068 • Published • 131
liked 2
datasets 2 days ago
upvoted 3
papers 2 days ago
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2609.20784 • Published • 56
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Paper • 2609.20715 • Published • 42
Self-Evolving Search Index
Paper • 2609.19656 • Published • 60