Tag
This paper introduces Priority-Constrained Descent (PCD), a gradient-based optimization framework for hierarchical multi-objective problems that preserves primary descent while allowing minimal distortion for secondary objectives.
This paper introduces Newton Matching, a unified framework for fine-tuning and sampling in generative models, which addresses limitations of existing methods by treating learning as an iterative optimization process and leveraging conditional-matching structure.
EvoSafeHarness optimizes deployable safety harnesses for LLM agents by jointly searching natural-language policies and executable logic, improving safety-utility trade-offs across agent benchmarks.