Media
Geo-Diverse Safety Alignment Da Yin
Content W arning: This paper may contain examples of harmful contents by nature.
MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
Dancing to the musical beats or creating a variety of rhythmically synchronized music for a given motion is a fundamental aspect of human creativity.
Who asking User personas and the mechanics of latent misalignment
Studies show that safety-tuned models may nevertheless divulge harmful information.
Zhaoxuan Wu*, Xiaoqiang Lin
On the other hand, the impact of the instruction, another essential component in the prompt given to the LLM, is often overlooked in existing exemplar selection methods.
Extending Video Masked Autoencoders to 128 frames
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs Yue Y u Georgia Tech Wei Ping
Wang et al., 2024) is a widely used technique for customizing large language models (LLMs) to handle
A Synthetic Dataset for Personal Attribute Inference Hanna Y ukhymenko
Recently powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide.
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
As Large Language Models (LLMs) are increasingly deployed in specialized domains with continuously evolving knowledge, the need for timely and precise knowledge injection has become essential.