Related papers: Test-Time Training Undermines Safety Guardrails
Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful…
Graph-based learning excels at capturing interaction patterns in diverse domains like recommendation, fraud detection, and particle physics. However, its performance often degrades under distribution shifts, especially those altering…
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret. However, recent advances in machine learning involve larger neural networks with…
As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand,…
Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the…
Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a…
Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine…
Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and…
Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn directly from their environment. In this work, we propose…
With the recent proliferation of large language models (LLMs), enterprises have been able to rapidly develop proof-of-concepts and prototypes. As a result, there is a growing need to implement robust guardrails that monitor, quantize and…
Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design…
Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving…
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…
Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines, making them costly to train and difficult to adapt to new…
Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data.…
As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…
Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating…
Deep learning models often struggle when deployed in real-world settings due to distribution shifts between training and test data. While existing approaches like domain adaptation and test-time training (TTT) offer partial solutions, they…
On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences in evolving environments. Test-time adaptation (TTA)…
An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however,…