English
Related papers

Related papers: Manifold Trajectories in Next-Token Prediction: Fr…

200 papers

Reasoning over long sequences of observations and actions is essential for many robotic tasks. Yet, learning effective long-context policies from demonstrations remains challenging. As context length increases, training becomes increasingly…

Robotics · Computer Science 2025-05-21 Marcel Torne , Andy Tang , Yuejiang Liu , Chelsea Finn

Next-token prediction serves as the dominant component in current neural language models. During the training phase, the model employs teacher forcing, which predicts tokens based on all preceding ground truth tokens. However, this approach…

Computation and Language · Computer Science 2024-10-28 Yongjing Yin , Junran Ding , Kai Song , Yue Zhang

Diffusion models have transformed image synthesis through iterative denoising, by defining trajectories from noise to coherent data. While their capabilities are widely celebrated, a critical challenge remains unaddressed: ensuring…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Andreas Floros , Seyed-Mohsen Moosavi-Dezfooli , Pier Luigi Dragotti

Multi-dimensional data completion is a critical problem in computational sciences, particularly in domains such as computer vision, signal processing, and scientific computing. Existing methods typically leverage either global low-rank…

Machine Learning · Computer Science 2025-08-07 Wenwu Gong , Lili Yang

Given measurements of a linear time-invariant system, the McMillan degree is the dimension of the smallest such system that reproduces these observed dynamics. Using impulse response measurements where the system has been started in some…

Numerical Analysis · Mathematics 2023-03-24 Jeffrey M. Hokanson

Many complex systems have natural representations as multi-layer networks. While these formulations retain more information than standard single-layer network models, there is not yet a fully developed theory for computing network metrics…

Social and Information Networks · Computer Science 2017-03-17 Daryl R. DeFord , Scott D. Pauls

We present a framework for modeling complex, high-dimensional distributions on convex polytopes by leveraging recent advances in discrete and continuous normalizing flows on Riemannian manifolds. We show that any full-dimensional polytope…

Machine Learning · Computer Science 2025-03-18 Tomek Diederen , Nicola Zamboni

Predicting the future behavior of human road users is an important aspect for the development of risk-aware autonomous vehicles. While many models have been developed towards this end, effectively capturing and predicting the variability…

Robotics · Computer Science 2025-06-30 Anna Mészáros , Julian F. Schumann , Javier Alonso-Mora , Arkady Zgonnikov , Jens Kober

Normalizing flows are a promising tool for modeling probability distributions in physical systems. While state-of-the-art flows accurately approximate distributions and energies, applications in physics additionally require smooth energies…

Machine Learning · Statistics 2021-12-01 Jonas Köhler , Andreas Krämer , Frank Noé

A longstanding challenge for self-driving development is simulating dynamic driving scenarios seeded from recorded driving logs. In pursuit of this functionality, we apply tools from discrete sequence modeling to model how vehicles,…

Machine Learning · Computer Science 2024-04-16 Jonah Philion , Xue Bin Peng , Sanja Fidler

The relaxation rate of a Maxwellian velocity distribution function that has an initially anisotropic temperature $(T_\parallel \neq T_\perp)$ is an important physical process in space and laboratory plasmas. It is also a canonical example…

Plasma Physics · Physics 2017-06-07 Scott D. Baalrud , Jerome Daligault

Transformers excel through content-addressable retrieval and the ability to exploit contexts of, in principle, unbounded length. We recast associative memory at the level of probability measures, treating a context as a distribution over…

Machine Learning · Statistics 2026-02-03 Ryotaro Kawata , Taiji Suzuki

This paper introduces ManiFlow, a visuomotor imitation learning policy for general robot manipulation that generates precise, high-dimensional actions conditioned on diverse visual, language and proprioceptive inputs. We leverage flow…

To generalize across tasks, an agent should acquire knowledge from past tasks that facilitate adaptation and exploration in future tasks. We focus on the problem of in-context adaptation and exploration, where an agent only relies on…

Machine Learning · Computer Science 2023-05-05 Chentian Jiang , Nan Rosemary Ke , Hado van Hasselt

We study the convergence to equilibrium of an underdamped Langevin equation that is controlled by a linear feedback force. Specifically, we are interested in sampling the possibly multimodal invariant probability distribution of a Langevin…

Optimization and Control · Mathematics 2022-01-12 Tobias Breiten , Carsten Hartmann , Lara Neureither , Upanshu Sharma

We propose a computationally efficient random walk on a convex body which rapidly mixes and closely tracks a time-varying log-concave distribution. We develop general theoretical guarantees on the required number of steps; this number can…

Machine Learning · Statistics 2013-09-25 Hariharan Narayanan , Alexander Rakhlin

We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design as inference. Specifically, we minimize a KL-regularized expected trajectory cost, which…

Machine Learning · Computer Science 2026-05-12 Heng Yang

For a manifold-with-boundary moving by mean curvature flow, the entropy at a later time is bounded by the entropy at an earlier time plus a boundary term. This paper controls the boundary term in a geometrically natural way. In particular,…

Differential Geometry · Mathematics 2023-08-08 Brian White

We initiate the study of game dynamics in the population protocol model: $n$ agents each maintain a current local strategy and interact in pairs uniformly at random. Upon each interaction, the agents play a two-person game and receive a…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-21 Dan Alistarh , Krishnendu Chatterjee , Mehrdad Karrabi , John Lazarsfeld

The aim of this work is to study the convergence to equilibrium of an $(h,\rho)$-subelliptic random walk on a closed, connected Riemannian manifold $(M,g)$ associated with a subelliptic second-order differential operator $A$ on $M$. In such…

Analysis of PDEs · Mathematics 2025-11-25 Davide Tramontana
‹ Prev 1 8 9 10 Next ›