STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published Sep 29 • 37
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published Sep 29 • 37
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation Paper • 2610.10429 • Published Oct 7 • 44
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Paper • 2610.07767 • Published Oct 6 • 43
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? Paper • 2403.14624 • Published Mar 21, 2024 • 52