We have 6 of 38 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.
Frontier AI systems are increasingly natively multimodal, jointly pretrained on multiple modalities, such as text, vision, and audio. However, the scientific understanding of the multimodal data mixtures used to pretrain these systems --- how much of each modality to mix, and at what potential interference cost to the...
Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-training teaches conditional enactment and makes a helpful Assistant the default, but it does not erase alternative modes from the weights; explicit prompts can therefor...
LLJ Cards is introduced, a framework that synthesizes best practices from measurement theory, natural language generation, and machine learning literature into practical guidelines for LLJ-based evaluations and provides a structured framework for applying these principles in the design and reporting of automated evalua...
This survey presents a two-dimensional taxonomy for IP protection in visual generative models, which systematically review protection methods, align evaluation protocols with protection objectives, and discusses open challenges including proactive model-level safeguards, standardized evaluation, robustness against adap...
It is suggested that even subtle objective misalignment can profoundly affect collective decision-making, highlighting the need for effective mitigation strategies for LLM-based multi-agent systems.
A lightweight Text Encoder Alignment framework that fine-tunes only the text encoder while keeping the generative backbone fully frozen, and achieves state-of-the-art erasure robustness against black-box and white-box adversarial attacks on Stable Diffusion v1.4, while preserving generation quality on benign prompts.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
