We have 4 of 28 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
RoleQ is introduced, a quantization framework that places scales by the functional roles of Transformer units rather than by the layout of the weight matrix, as conventional formats do, and leads every post-training ternary method at matched or lower memory-resident bits on perplexity, zero-shot accuracy and MMLU.
Through ALLUDE's end-to-end differentiable rendering, adversarial attacks can be optimized against shifting real-world deployment conditions, and can be optimized against shifting real-world deployment conditions.
Adversarial Robustness with Manifold-Oriented Training (ARMOR), a novel defense that realizes the core insights of on-manifold adversarial training (OMAT) in low-data regimes and translates insights from manifold-based training to defend object detectors amidst training data scarcity.
Flow Reasoning Models is introduced, a novel framework for structured reasoning that adapts continuous flows over discrete structured outputs with a simple recurrent refinement mechanism by self-conditioning a flow model on its own past outputs, to turn one-shot denoising into iterative solution refinement.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
