Related papers: Beyond Turing: Memory-Amortized Inference as a Fou…
The dominant artificial intelligence paradigm trains neural architectures via gradient descent against proxy objectives and reinforcement learning from human feedback. While remarkably capable, this top-down optimization inherently…
AI-driven recruitment systems, while promising efficiency and objectivity, often perpetuate systemic inequalities by encoding cultural and social capital disparities into algorithmic decision making. This article develops and defends a…
There are two approaches for simulating memory as well as learning in artificial intelligence; the functionalistic approach and the cognitive approach. The necessary condition to put the second approach into account is to provide a model of…
Current AI systems excel at pattern recognition but fail at causal reasoning. We argue this is not an engineering limitation but reveals something fundamental about the nature of understanding itself. We propose that causal cognition…
Recent popular decoder-only text-to-speech models are known for their ability of generating natural-sounding speech. However, such models sometimes suffer from word skipping and repeating due to the lack of explicit monotonic alignment…
The overarching problem in artificial intelligence (AI) is that we do not understand the intelligence process well enough to enable the development of adequate computational models. Much work has been done in AI over the years at lower…
The Helmholtz Machine (HM) is a foundational architecture for unsupervised learning, coupling a bottom-up recognition model with a top-down generative model through alternating inference. However, its reliance on symmetric, data-driven…
Large language models (LLMs) have demonstrated the world with the sparks of artificial general intelligence (AGI). One opinion, especially from some startups working on LLMs, argues that an LLM with nearly unlimited context length can…
Artificial intelligence is increasingly described as a candidate next generation general purpose technology (GPT). However, existing interpretations predominantly emphasize performance scaling rather than structural transformation. This…
Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…
Understanding AI systems' inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computational mechanisms and representations learned by neural networks…
Perceptual estimates exhibit a reversal in bias depending on uncertainty: they shift toward prior expectations under high stimulus noise, but away from them when sensory noise dominates. The normative framework of a Bayesian observer model…
Developmental AI creates embodied AIs that develop human-like abilities. The AIs start with innate competences and learn more by interacting with the world including people. Developmental AIs have been demonstrated, but their abilities so…
Rapid advances in AI are beginning to reshape national security. Destabilizing AI developments could rupture the balance of power and raise the odds of great-power conflict, while widespread proliferation of capable AI hackers and…
We study how artificial intelligence (AI) affects firms' incentives to pursue incremental versus radical knowledge recombinations. We develop a model of recombinant innovation embedded in a Schumpeterian quality-ladder framework, in which…
We consider a remote inference system with multiple modalities, where a multimodal machine learning (ML) model performs real-time inference using features collected from remote sensors. When sensor observations evolve dynamically over time,…
Memory is the process of encoding, storing, and retrieving information, allowing humans to retain experiences, knowledge, skills, and facts over time, and serving as the foundation for growth and effective interaction with the world. It…
The human brain represents the only known example of general intelligence that naturally aligns with human values. On a mere 20-watt power budget, the brain achieves robust learning and adaptive decision-making in ways that continue to…
Due to their uncertainty quantification, Bayesian solutions to inverse problems are the framework of choice in applications that are risk averse. These benefits come at the cost of computations that are in general, intractable. New advances…
We consider amortized Bayesian inference for nonlinear inverse problems in settings where only samples from the joint distribution of parameters and observations are available. Classical methods such as Markov chain Monte Carlo require…