相关论文: Conditioned Activation Transport for T2I Safety St…

The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather data via vehicle-to-vehicle (V2V) communication, such as processed LIDAR and camera data from other vehicles. In this work, we design an…

Provable safety is one of the most critical challenges in automated driving. The behavior of numerous traffic participants in a scene cannot be predicted reliably due to complex interdependencies and the indiscriminate behavior of humans.…

Current research in Visual Navigation reveals opportunities for improvement. First, the direct adoption of RNNs and Transformers often overlooks the specific differences between Embodied AI and traditional sequential data modelling,…

Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We…

This paper analyzes the community safety guidelines of five text-to-image (T2I) generation platforms and audits five T2I models, focusing on prompts related to the representation of humans in areas that might lead to societal stigma. While…

This paper investigates the use of Infrastructure-To-Vehicle (I2V) communication to generate routing suggestions for drivers in transportation systems, with the goal of optimizing a measure of overall network congestion. We define link-wise…

To prevent Text-to-Image (T2I) models from generating unethical images, people deploy safety filters to block inappropriate drawing prompts. Previous works have employed token replacement to search adversarial prompts that attempt to bypass…

We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying their activations during forward passes. CAA computes "steering vectors" by averaging the difference in residual stream…

We study the use of amortized optimization to predict optimal transport (OT) maps from the input measures, which we call Meta OT. This helps repeatedly solve similar OT problems between different measures by leveraging the knowledge and…

Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations. However, the evaluation of these techniques has so far been limited to…

Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its…

Under a changing driving environment, a Connected Autonomous Vehicle (CAV) platoon relies strongly on the acquisition of accurate traffic information from neighboring vehicles as well as reliable commands from a centralized supervisory…

Text-to-Image (T2I) models have made remarkable progress in generating images from text prompts, but their output quality and safety still depend heavily on how prompts are phrased. Existing safety methods typically refine prompts using…

Neural image classifiers are known to undergo severe performance degradation when exposed to inputs that are sampled from environmental conditions that differ from their training data. Given the recent progress in Text-to-Image (T2I)…

Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and induce…

We introduce Afferent Learning, a framework that produces Computational Afferent Traces (CATs) as adaptive, internal risk signals for damage-avoidance learning. Inspired by biological systems, the framework uses a two-level architecture:…

Training a model-free reinforcement learning agent requires allowing the agent to sufficiently explore the environment to search for an optimal policy. In safety-constrained environments, utilizing unsupervised exploration or a non-optimal…

We present Causal Amortized Active Structure Learning (CAASL), an active intervention design policy that can select interventions that are adaptive, real-time and that does not require access to the likelihood. This policy, an amortized…

Existing models often struggle with complex temporal changes, particularly when generating videos with gradual attribute transitions. The most common prompt interpolation approach for motion transitions often fails to handle gradual…

Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool…