Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
arxiv.org·14h
Progressive Bound Strengthening via Doubly Nonnegative Cutting Planes for Nonconvex Quadratic Programs
arxiv.org·1d
Moral Anchor System: A Predictive Framework for AI Value Alignment and Drift Prevention
arxiv.org·14h
From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents
arxiv.org·14h
Self-Reflective Generation at Test Time
arxiv.org·1d
Loading...Loading more...