Related papers: Frictional Agent Alignment Framework: Slow Down an…

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…

Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference…

In recent years, instruction fine-tuning (IFT) on large language models (LLMs) has garnered considerable attention to enhance model performance on unseen tasks. Attempts have been made on automatic construction and effective selection for…

Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples. Adversarial training is used to mitigate this problem by increasing…

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

The rapid advancement of Large Language Models (LLMs) and their integration into autonomous agent systems has created unprecedented opportunities for document analysis, decision support, and knowledge retrieval. However, the complexity of…

In natural vision, feedback connections support versatile visual inference capabilities such as making sense of the occluded or noisy bottom-up sensory information or mediating pure top-down processes such as imagination. However, the…

Human action-reaction synthesis, a fundamental challenge in modeling causal human interactions, plays a critical role in applications ranging from virtual reality to social robotics. While diffusion-based models have demonstrated promising…

Traditional hearing aids often rely on static fittings that fail to adapt to their dynamic acoustic environments. We propose CAFA, a Context-Adaptive Fitting Advisor that provides personalized, real-time hearing aid adjustments through a…

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Foundation models (FMs) such as large language models have revolutionized the field of AI by showing remarkable performance in various tasks. However, they exhibit numerous limitations that prevent their broader adoption in many real-world…

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Methods for building fair predictors often involve tradeoffs between fairness and accuracy and between different fairness criteria, but the nature of these tradeoffs varies. Recent work seeks to characterize these tradeoffs in specific…

Emerging efforts in AI alignment seek to broaden participation in shaping model behavior by eliciting and integrating collective input into a policy for model finetuning. While pluralistic, these processes are often linear and do not allow…

Federated learning enables institutions to train predictive models collaboratively without sharing raw data, addressing privacy and regulatory constraints. In the standard horizontal setting, clients hold disjoint cohorts of individuals and…

The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives. However, finding such functions remains a research challenge, while in RL, setting rewards by hand is a fairly…

As AI systems become embedded in everyday practice, value misalignment has emerged as a pressing concern. Yet, dominant alignment approaches remain model centric, treating users as passive recipients of prespecified values rather than as…

Distributed reinforcement learning policies face network delays, jitter, and packet loss when deployed across edge devices and cloud servers. Standard RL training assumes zero-latency interaction, causing severe performance degradation…

Conventional automated decision-support systems often prioritize predictive accuracy, overlooking the complexities of real-world settings where stakeholders' preferences may diverge or conflict. This can lead to outcomes that disadvantage…

While Generative AI (GenAI) systems draw users away from (Q&A) forums, they also depend on the very data those forums produce to improve their performance. Addressing this paradox, we propose a framework of sequential interaction, in which…