4Director: Controlling Video World Models with Rigid 3D Geometry
Paper • 2610.02160 • Published • 13
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 8 hours ago
4Director: Controlling Video World Models with Rigid 3D Geometry upvoted a paper about 8 hours ago
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States upvoted a paper about 8 hours ago
ActiveSaddler: Automated Curriculum Learning for Agent Harness OptimizationOrganizations
None yet
upvoted 5
papers about 8 hours ago
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Paper • 2610.01415 • Published • 62
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
Paper • 2610.00906 • Published • 34
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
Paper • 2610.01215 • Published • 28
Hierarchical Continuous Diffusion Language Models
Paper • 2610.02193 • Published • 49
upvoted 13
papers 1 day ago
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
Paper • 2609.39661 • Published • 6
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Paper • 2609.38143 • Published • 78
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
Paper • 2609.40285 • Published • 20
Scaling Laws for Looped Mixture of Experts
Paper • 2609.40316 • Published • 17
AIM: Agentic Idea Management for Automated Research
Paper • 2609.38445 • Published • 47
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Paper • 2609.39982 • Published • 108
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 77
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
Paper • 2609.38537 • Published • 29
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 126
StoryEngine: A State-Grounded Agentic Framework for Video Storytelling
Paper • 2609.33627 • Published • 17
TabFM: A Zero-Shot Foundation Model for Tabular Data
Paper • 2609.37959 • Published • 16
EasyPPO: Stabilizing the Critic Is Key
Paper • 2609.36802 • Published • 34
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Paper • 2609.34981 • Published • 118
upvoted 2
papers 2 days ago