Related papers: Dynamically Scaled Activation Steering
Relational database management systems (RDBMS) are widely used for the storage of structured data. To derive insights beyond statistical aggregation, we typically have to extract specific subdatasets from the database using conventional…
Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…
Adaptive simulated annealing (ASA) is a global optimization algorithm based on an associated proof that the parameter space can be sampled much more efficiently than by using other previous simulated annealing algorithms. The author's ASA…
As Large Langue Models have been shown to memorize real-world facts, the need to update this knowledge in a controlled and efficient manner arises. Designed with these constraints in mind, Knowledge Editing (KE) approaches propose to alter…
Diffusion models show promise for image restoration, but existing methods often struggle with inconsistent fidelity and undesirable artifacts. To address this, we introduce Kernel Density Steering (KDS), a novel inference-time framework…
In this paper, a human-machine adaptive shared control method is proposed for automated vehicles (AVs) under automation performance degradation. First, a novel risk assessment module is proposed to monitor driving behavior and evaluate…
Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered…
State-of-the-art approaches for autonomous driving integrate multiple sub-tasks of the overall driving task into a single pipeline that can be trained in an end-to-end fashion by passing latent representations between the different modules.…
Monitoring the integrity of object detection for errors within the perception module of automated driving systems (ADS) is paramount for ensuring safety. Despite recent advancements in deep neural network (DNN)-based object detectors, their…
Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning methods suffer from issues such as high computational costs, hyperparameter…
This work introduces the Drag-Aware Aerodynamic Manipulability (DAAM), a geometric framework for control allocation in redundant multirotors. By equipping the propeller spin-rate space with a Riemannian metric based on the remaining…
The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the…
Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offers high acceleration…
Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for…
The focus of this paper is to propose a driver model that incorporates human reasoning levels as actions during interactions with other drivers. Different from earlier work using game theoretical human reasoning levels, we propose a dynamic…
A growing number of vehicles are being transformed into semi-autonomous vehicles (Level 2 autonomy) by relying on advanced driver assistance systems (ADAS) to improve the driving experience. However, the increasing complexity and…
This study underscores the vital importance of intelligent driving functions in enhancing road safety and driving comfort. Central to our research is the challenge of obtaining sufficient test data for evaluating these functions, especially…
Task robust adaptation is a long-standing pursuit in sequential decision-making. Some risk-averse strategies, e.g., the conditional value-at-risk principle, are incorporated in domain randomization or meta reinforcement learning to…
Object manipulation is a fundamental challenge in robotics, where systems must balance trade-offs among manipulation capabilities, system complexity, and throughput. Distributed manipulator systems (DMS) use the coordinated motion of…
Adaptive sampling results in dramatic improvements in the recovery of sparse signals in white Gaussian noise. A sequential adaptive sampling-and-refinement procedure called Distilled Sensing (DS) is proposed and analyzed. DS is a form of…