Deep Learning
Diffusion Priors for Variational Likelihood Estimation and Image Denoising
Real-world noise removal is crucial in low-level computer vision.
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks .
TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
This lack of rich textual edge annotations significantly limits the exploration of contextual relationships between entities, hindering deeper insights into graph-structured data.
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
Reinforcement Learning from Human Feedback (RLHF) has recently surged in popularity, particularly for aligning large language models and other AI systems with human intentions. At its core, RLHF can be viewed as a specialized instance of Preference-based Reinforcement Learning (PbRL), where the preferences specifically originate from human judgments rather than arbitrary evaluators. Despite this connection, most existing approaches in both RLHF and PbRL primarily focus on optimizing a mean reward objective, neglecting scenarios that necessitate risk-awareness, such as AI safety, healthcare, and autonomous driving. These scenarios often operate under a one-episode-reward setting, which makes conventional risk-sensitive objectives inapplicable.
HW-Aware-GPT-Bench
This energy usage is comparable to that of around 180,000 U.S. households, each
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
We find that a small subset of "cherry" parameters exhibit a
Scaling Laws in Linear Regression: Compute, Parameters, and Data
From the perspective of statistical learning theory, (1) is rather intriguing. Moreover, they do not provide instance-wise matching lower bounds to verify the tightness of the upper bounds.
