相关论文: PRISM: Perspective Reasoning for Integrated Synthe…

Background: What counts as violence is neither self-evident nor universally agreed upon. While physical aggression is prototypical, contemporary societies increasingly debate whether exclusion, humiliation, online harassment or symbolic…

The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act…

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.…

Aligning large language models with humans is challenging due to the inherently multifaceted nature of preference feedback. While existing approaches typically frame this as a multi-objective optimization problem, they often overlook how…

In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in…

Research in AI evaluation has grown increasingly complex and multidisciplinary, attracting researchers with diverse backgrounds and objectives. As a result, divergent evaluation paradigms have emerged, often developing in isolation,…

Systems thinking provides us with a way to model the algorithmic fairness problem by allowing us to encode prior knowledge and assumptions about where we believe bias might exist in the data generating process. We can then encode these…

Populating our world with hyperintelligent machines obliges us to examine cognitive behaviors observed across domains that suggest autonomy may be a fundamental property of cognitive systems, and while not inherently adversarial, it…

Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle…

Large Multimodal Models (LMMs) are increasingly applied to scientific research, yet it remains unclear whether they can reliably understand and reason over the multimodal complexity of papers. A central challenge lies in detecting and…

Game-theoretic concepts have been extensively studied in economics to provide insight into competitive behaviour and strategic decision making. As computing systems increasingly involve concurrently acting autonomous agents, game-theoretic…

Numerous fairness metrics have been proposed and employed by artificial intelligence (AI) experts to quantitatively measure bias and define fairness in AI models. Recognizing the need to accommodate stakeholders' diverse fairness…

Increasing interest in ensuring the safety of next-generation Artificial Intelligence (AI) systems calls for novel approaches to embedding morality into autonomous agents. This goal differs qualitatively from traditional task-specific AI…

Although LLMs and other artificial intelligence systems demonstrate cognitive skills similar to humans, like concept learning and language acquisition, the way they process information fundamentally differs from biological cognition. To…

A critical aspect of human visual perception is the ability to parse visual scenes into individual objects and further into object parts, forming part-whole hierarchies. Such composite structures could induce a rich set of semantic concepts…

As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical. While achieving high accuracy on knowledge benchmarks, LLMs lack validated assessment for navigating ethical trade-offs in…

We present PRISM (Policy Reuse via Interpretable Strategy Mapping), a framework that grounds reinforcement learning agents' decisions in discrete, causally validated concepts and uses those concepts as a zero-shot transfer interface between…

While much research in artificial intelligence (AI) has focused on scaling capabilities, the accelerating pace of development makes countervailing work on producing harmless, "aligned" systems increasingly urgent. Yet research on alignment…

With AI systems becoming more powerful and pervasive, there is increasing debate about keeping their actions aligned with the broader goals and needs of humanity. This multi-disciplinary and multi-stakeholder debate must resolve many…

Efficiently enhancing the reasoning capabilities of Vision-Language Models (VLMs) by merging them with Large Reasoning Models (LRMs) has emerged as a promising direction. However, existing methods typically operate at a coarse-grained layer…