MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
Paper • 2609.36435 • Published • 6
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 16 hours ago
MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization upvoted a paper about 16 hours ago
DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration upvoted a paper about 16 hours ago
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video GenerationOrganizations
None yet
upvoted 6
papers about 16 hours ago
DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration
Paper • 2609.33403 • Published • 10
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
Paper • 2610.00686 • Published • 10
Video Generation Models: A Survey of Post-Training and Alignment
Paper • 2610.00812 • Published • 44
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Paper • 2610.02162 • Published • 72
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
Paper • 2610.01762 • Published • 161
upvoted a paper 1 day ago
upvoted 5
papers 2 days ago
4Director: Controlling Video World Models with Rigid 3D Geometry
Paper • 2610.02160 • Published • 27
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Paper • 2610.01415 • Published • 79
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
Paper • 2610.00906 • Published • 55
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
Paper • 2610.01215 • Published • 48
Hierarchical Continuous Diffusion Language Models
Paper • 2610.02193 • Published • 79
upvoted 8
papers 3 days ago
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
Paper • 2609.39661 • Published • 9
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Paper • 2609.38143 • Published • 80
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
Paper • 2609.40285 • Published • 21
Scaling Laws for Looped Mixture of Experts
Paper • 2609.40316 • Published • 19
AIM: Agentic Idea Management for Automated Research
Paper • 2609.38445 • Published • 49
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Paper • 2609.39982 • Published • 111
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 80
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
Paper • 2609.38537 • Published • 30