Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling
Paper • 2609.36529 • Published • 29
달빛개발자
dal-bit
·
AI & ML interests
None yet
Recent Activity
Organizations
None yet
upvoted 5
papers 2 days ago
Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production
Paper • 2609.39963 • Published • 20
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 274
VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
Paper • 2610.00972 • Published • 50
LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
Paper • 2609.39071 • Published • 57
upvoted 4
papers 7 days ago
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 324
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
Paper • 2609.37686 • Published • 70
Think Before You Score: Thinking Reward Model for Visual Generation
Paper • 2609.37372 • Published • 101
LEGO-Anything: Coding Agents for 3D Scene Reconstruction
Paper • 2609.36380 • Published • 138