WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory
Paper • 2607.02517 • Published • 32
🤝 Open to Collab
Xiaoye Qu
Xiaoye08
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Morphing into Hybrid Attention Models upvoted a paper 9 days ago
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive EnvironmentsOrganizations
upvoted 2
papers 8 days ago
upvoted a paper 9 days ago
upvoted 2
papers 30 days ago
upvoted 4
papers about 1 month ago
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics
Paper • 2606.10479 • Published • 20
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
Paper • 2606.05761 • Published • 19
SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects
Paper • 2605.19587 • Published • 10
Draft-OPD: On-Policy Distillation for Speculative Draft Models
Paper • 2605.29343 • Published • 37
upvoted 7
papers about 2 months ago
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Paper • 2605.22791 • Published • 33
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Paper • 2605.16928 • Published • 98
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 108
HRM-Text: Efficient Pretraining Beyond Scaling
Paper • 2605.20613 • Published • 322
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
Paper • 2605.15198 • Published • 19
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
Paper • 2605.13301 • Published • 166
δ-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 131
upvoted 2
papers 2 months ago
upvoted 2
papers 3 months ago