SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models Paper • 2610.04875 • Published 6 days ago • 7
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure? Paper • 2609.18605 • Published 26 days ago • 41
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 376
Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation Paper • 2609.06373 • Published Sep 6 • 17
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference Paper • 2609.04971 • Published Sep 4 • 43