Large Language Model
ReFT: Representation Finetuning for Language Models
We pursue this hypothesis by developing a family of Representation Finetuning (ReFT) methods.
Supplementary Material for: T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
Warning: This paper contains data and model outputs which are offensive in nature. Institutional Review Board (IRB) and obtained an exempt decision. Additionally, potential bias may arise due to the high cultural specificity of human reviewers. For instance, "explicit sexual content" is defined as "including Each video was evaluated by at least three volunteers. Following the initial assessment, we conduct a secondary cross-validation.
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models Yibo Miao
The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its safety risks.
Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
However, although these techniques have been widely adopted in single-task scenarios, research is scarce in multi-task scenarios.
Alignment for Honesty Y uqing Y ang
However, a pivotal aspect of alignment for honesty involves discerning an LLM's
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their
