Related papers: Learning by training: emergent return-point memory…

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural…

As robotics continues to advance, the need for adaptive and continuously-learning embodied agents increases, particularly in the realm of assistance robotics. Quick adaptability and long-term information retention are essential to operate…

Out-of-equilibrium disordered systems may form memories of external driving in a remarkable fashion. The system "remembers" multiple values from a series of training inputs yet "forgets" nearly all of them at long times despite the inputs…

The development of interatomic potentials that can accurately capture a wide range of physical phenomena and diverse environments is of significant interest, but it presents a formidable challenge. This challenge arises from the numerous…

Learning various motor skills for quadrupedal robots is a challenging problem that requires careful design of task-specific mathematical models or reward descriptions. In this work, we propose to learn a single capable policy using deep…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…

Autoregressive language models (ARMs) suffer from the reversal curse: after learning ''$A$ is $B$,'' they often fail on the reverse query ''$B$ is $A$.'' Masked diffusion language models (MDMs) exhibit this failure in a much weaker form,…

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…

Diverse many-body systems, from soap bubbles to suspensions to polymers, learn and remember patterns in the drives that push them far from equilibrium. This learning may be leveraged for computation, memory, and engineering. Until now,…

Model-based Reinforcement Learning and Control have demonstrated great potential in various sequential decision making problem domains, including in robotics settings. However, real-world robotics systems often present challenges that limit…

Adaptive physical and biological systems continually process fluctuating information from their environments. When the environment is nonstationary, inference itself becomes a nonequilibrium process with thermodynamic cost. We analyse a…

Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundamentally limited in continuous operation,…

In order to robustly execute a task under environmental uncertainty, a robot needs to be able to reactively adapt to changes arising in its environment. The environment changes are usually reflected in deviation from expected sensory…

Physical learning is an emerging paradigm in science and engineering whereby (meta)materials acquire desired macroscopic behaviors by exposure to examples. So far, it has been applied to static properties such as elastic moduli and…

Evolutionary accumulation models (EvAMs) are an emerging class of machine learning methods designed to infer the evolutionary pathways by which features are acquired. Applications include cancer evolution (accumulation of mutations),…

Machine learning methods have proved to be useful for the recognition of patterns in statistical data. The measurement outcomes are intrinsically random in quantum physics, however, they do have a pattern when the measurements are performed…

We present that, instead of establishing the equations of motion, one can model-freely reveal the dynamical properties of a black-box system using a learning machine. Trained only by a segment of time series of a state variable recorded at…

Learning unknown dynamics under environmental (or external) constraints is fundamental to many fields (e.g., modern robotics), particularly challenging when constraint information is only locally available and uncertain. Existing approaches…

We study analytically and by computer simulations a complex system of adaptive agents with finite memory. Borrowing the framework of the Minority Game and using the replica formalism we show the existence of an equilibrium phase transition…