Related papers: Dynamically Scaled Activation Steering
Advanced driver assistance systems (ADAS) can be significantly improved with effective driver action prediction (DAP). Predicting driver actions early and accurately can help mitigate the effects of potentially unsafe driving behaviors and…
Generative multimodal models based on diffusion models have seen tremendous growth and advances in recent years. Models such as DALL-E and Stable Diffusion have become increasingly popular and successful at creating images from texts, often…
In the rapidly evolving field of autonomous driving, reliable prediction is pivotal for vehicular safety. However, trajectory predictions often deviate from actual paths, particularly in complex and challenging environments, leading to…
The deep neural network (DNN) models are widely used for object detection in automated driving systems (ADS). Yet, such models are prone to errors which can have serious safety implications. Introspection and self-assessment models that aim…
To improve the execution speed and efficiency of neural networks in embedded systems, it is crucial to decrease the model size and computational complexity. In addition to conventional compression techniques, e.g., weight pruning and…
We develop a new method which extends Dynamic Mode Decomposition (DMD) to incorporate the effect of control to extract low-order models from high-dimensional, complex systems. DMD finds spatial-temporal coherent modes, connects local-linear…
While autonomous driving technologies continue to advance, current Advanced Driver Assistance Systems (ADAS) remain limited in their ability to interpret scene context or engage with drivers through natural language. These systems typically…
This paper presents an adaptive haptic shared control framework wherein a driver and an automation system are physically connected through a motorized steering wheel. The automation system is modeled as an intelligent agent that is not only…
Simulation-based testing is widely used to assess the reliability of Autonomous Driving Systems (ADS), but its effectiveness is limited by the operational design domain (ODD) conditions available in such simulators. To address this…
Distributed optimization has been widely used as one of the most efficient approaches for model training with massive samples. However, large-scale learning problems with both massive samples and high-dimensional features widely exist in…
Training data attribution (TDA) methods ask which training documents are responsible for a model behavior. However, models often learn broad concepts shared across many examples. Moreover, existing TDA methods are supervised -- they require…
When predicting a target variable $Y$ from features $X$, the prediction $\hat{Y}$ can be performative: an agent might act on this prediction, affecting the value of $Y$ that we eventually observe. Performative predictions are deliberately…
Deep learning is reshaping mobile applications, with a growing trend of deploying deep neural networks (DNNs) directly to mobile and embedded devices to address real-time performance and privacy. To accommodate local resource limitations,…
Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…
Multi-agent LLM orchestration systems suffer from context pollution: when N concurrent agents compete for the orchestrator's context window, each agent's task state, partial outputs, and pending questions contaminate the steering…
Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant activation vectors with scalars? We argue that successfully…
Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model's representations. Thus, one…
In this paper, we present a novel learning-based shared control framework. This framework deploys first-order Dynamical Systems (DS) as motion generators providing the desired reference motion, and a Variable Stiffness Dynamical Systems…
Advanced driver assistance systems (ADAS) are often used in the automotive industry to highlight innovative improvements in vehicle safety. However, today it is unclear whether certain automation (e.g., adaptive cruise control, lane…
We aim to tackle a novel task in action detection - Online Detection of Action Start (ODAS) in untrimmed, streaming videos. The goal of ODAS is to detect the start of an action instance, with high categorization accuracy and low detection…