We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By embedding state-action pairs into a latent space in which the true value function is approximately linear, our method supports a single set of hyperparameters across diverse domains -- from continuous control with low-dimensional and pixel inputs to high-dimensional Atari games. We prove that, under mild conditions, the fixed point of our embedding-based temporal-difference updates coincides with that of a corresponding linear model-based value expansion, and we derive explicit error bounds relating embedding fidelity to value approximation quality. In practice, ULD employs synchronized updates of encoder, value, and policy networks, auxiliary losses for short-horizon predictive dynamics, and reward-scale normalization to ensure stable learning under sparse rewards. Evaluated on 80 environments spanning Gym locomotion, DeepMind Control (proprioceptive and visual), and Atari, our approach matches or exceeds the performance of specialized model-free and general model-based baselines -- achieving cross-domain competence with minimal tuning and a fraction of the parameter footprint. These results indicate that value-aligned latent representations alone can deliver the adaptability and sample efficiency traditionally attributed to full model-based planning.
We address the problem of learning reusable state representations from streaming high-dimensional observations. This is important for areas like Reinforcement Learning (RL), which yields non-stationary data distributions during training. We make two key contributions. First, we propose an evaluation suite that measures alignment between latent and true low-dimensional states. We benchmark several widely used unsupervised learning approaches. This uncovers the strengths and limitations of existing approaches that impose additional constraints/objectives on the latent space. Our second contribut…
DeepMind（深度思维）；University of California, Berkeley（加州大学伯克利分校）
Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must now solve two problems: representation learning and task learning. In this work, we tackle these two problems separately, by explicitly learning latent representations that can accelerate reinforcement learning from images. We propose the stochastic latent actor-critic (SLAC) algorithm: a sample-efficient and high-performing RL algorithm for learning policie…
Adobe Research（奥多比研究院）；University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
We present a unified formalism for structure discovery of causal models and predictive state representation (PSR) models in reinforcement learning (RL) using higher-order category theory. Specifically, we model structure discovery in both settings using simplicial objects, contravariant functors from the category of ordinal numbers into any category. Fragments of causal models that are equivalent under conditional independence -- defined as causal horns -- as well as subsequences of potential tests in a predictive state representation -- defined as predictive horns -- are both special cases of…
School of EECS（电子工程与计算机科学学院）；Oregon State University（俄勒冈州立大学）；Intel Labs（英特尔实验室）
Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control tasks. In particular, recent work, for discrete action spaces, demonstrated the effectiveness of latent-space planning via Monte-Carlo Tree Search (MCTS) for bootstrapping MBRL during learning and at test time. However, the potential gains from latent-space tree search have not yet been demonstrated for environments with continuous action spaces. In this work, we propose and explore an MBRL approach for continuous ac…
Reinforcement learning agents need a reward signal to learn successful policies. When this signal is sparse or the corresponding gradient is deceptive, such agents need a dedicated mechanism to efficiently explore their search space without relying on the reward. Looking for a large diversity of behaviors or using Motion Planning (MP) algorithms are two options in this context. In this paper, we build on the common roots between these two options to investigate the properties of two diversity search algorithms, the Novelty Search and the Goal Exploration Process algorithms. These algorithms lo…
Reinforcement learning has shown great potential in developing high-level autonomous driving. However, for high-dimensional tasks, current RL methods suffer from low data efficiency and oscillation in the training process. This paper proposes an algorithm called Learn to drive with Virtual Memory (LVM) to overcome these problems. LVM compresses the high-dimensional information into compact latent states and learns a latent dynamic model to summarize the agent's experience. Various imagined latent trajectories are generated as virtual memory by the latent dynamic model. The policy is learned by…
The framework of variational autoencoders allows us to efficiently learn deep latent-variable models, such that the model's marginal distribution over observed variables fits the data. Often, we're interested in going a step further, and want to approximate the true joint distribution over observed and latent variables, including the true prior and posterior distributions over latent variables. This is known to be generally impossible due to unidentifiability of the model. We address this issue by showing that for a broad family of deep latent-variable models, identification of the true joint …
Diffusion models have achieved unprecedented performance in generative modeling. The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually denoised samples, as opposed to the simpler (e.g., Gaussian) latent space of GANs, VAEs, and normalizing flows. This paper provides an alternative, Gaussian formulation of the latent space of various diffusion models, as well as an invertible DPM-Encoder that maps images into the latent space. While our formulation is purely based on the definition of diffusion models, we demonstrate several intriguing consequences. …
Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks
Department of Statistics, University of California, Berkeley（加州大学伯克利分校统计学系）；Department of Statistics and Data Science, University of Pennsylvania（宾夕法尼亚大学统计学与数据科学系）
We present a general construction for dependent random measures based on thinning Poisson processes on an augmented space. The framework is not restricted to dependent versions of a specific nonparametric model, but can be applied to all models that can be represented using completely random measures. Several existing dependent random measures can be seen as specific cases of this framework. Interesting properties of the resulting measures are derived and the efficacy of the framework is demonstrated by constructing a covariate-dependent latent feature model and topic model that obtain superio…
Digital and Cognitive Musicology Lab（数字与认知音乐学实验室）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Probabilistic context-free grammars (PCFGs) and dynamic Bayesian networks (DBNs) are widely used sequence models with complementary strengths and limitations. While PCFGs allow for nested hierarchical dependencies (tree structures), their latent variables (non-terminal symbols) have to be discrete. In contrast, DBNs allow for continuous latent variables, but the dependencies are strictly sequential (chain structure). Therefore, neither can be applied if the latent variables are assumed to be continuous and also to have a nested hierarchical dependency structure. In this paper, we present Recur…
MPI Tübingen（图宾根马普研究所）；Microsoft Research Cambridge（微软剑桥研究院）；ETH Zürich（苏黎世联邦理工学院）
Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the inference model. We introduce Adversarial Variational Bayes (AVB), a technique for training Variational Autoencoders with arbitrarily expressive inference models. We achieve this by introducing an auxiliary discriminative network that allows to rephrase the maximum-likelihood-problem as a two-player game, hence establishing a principled connection between VA…
Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures
Berlin Institute for the Foundations of Learning（学习与数据基础研究院）；Machine Learning Group, Technical University of Berlin（柏林技术大学机器学习组）；Department of Artificial Intelligence, Korea University（韩国大学人工智能系）；Max Planck Institute for Informatics（信息研究所）；Department of Chemistry, Chemical Physics Theory Group, University of Toronto（多伦多大学化学系、化学物理理论组）；Vector Institute for Artificial Intelligence（人工智能矢量研究所）；Acceleration Consortium, University of Toronto（多伦多大学加速联盟）
Concept activation vectors: a unifying view and adversarial attacks
Department of Computer Science, Aalto University, Espoo, Finland（艾尔沃斯大学计算机科学系）；Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany（弗劳恩霍夫 Heinrich Hertz 研究所人工智能系）；Huawei Noah’s Ark Lab, Huawei Technologies, Paris, France（华为诺亚实验室）；Department of Electrical Engineering and Computer Science, Technical University Berlin, Germany（柏林技术大学电气工程与计算机科学系）
Understanding Self-Supervised Learning via Latent Distribution Matching
Friedrich Miescher Institute for Biomedical Research, 4056 Basel, Switzerland（弗里德里希·迈斯彻生物医学研究所）；Faculty of Science, University of Basel, 4033 Basel, Switzerland（巴塞尔大学科学学院）
Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey
Chair of Information Theory and Data Analytics (INDA), RWTH Aachen University（亚琛工业大学信息理论与数据分析教席）；AIT Austrian Institute of Technology GmbH（奥地利技术研究所）；Automation and Control Institute, Technische Universität Wien (TUW)（维也纳工业大学自动化与控制研究所）
Since the invention of word2vec, the skip-gram model has significantly advanced the research of network embedding, such as the recent emergence of the DeepWalk, LINE, PTE, and node2vec approaches. In this work, we show that all of the aforementioned models with negative sampling can be unified into the matrix factorization framework with closed forms. Our analysis and proofs reveal that: (1) DeepWalk empirically produces a low-rank transformation of a network's normalized Laplacian matrix; (2) LINE, in theory, is a special case of DeepWalk when the size of vertices' context is set to one; (3) …
We propose a technique for increasing the efficiency of gradient-based inference and learning in Bayesian networks with multiple layers of continuous latent vari- ables. We show that, in many cases, it is possible to express such models in an auxiliary form, where continuous latent variables are conditionally deterministic given their parents and a set of independent auxiliary variables. Variables of mod- els in this auxiliary form have much larger Markov blankets, leading to significant speedups in gradient-based inference, e.g. rapid mixing Hybrid Monte Carlo and efficient gradient-based opt…
Rice University（莱斯大学）；Georgia Institute of Technology（佐治亚理工学院）；Nanjing University（南京大学）
Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention layers make it possible to embed information globally across the overall image. Nevertheless, computing and storing such attention matrices incurs a quadratic cost dependency on the number of patches, limiting its achievable efficiency and scalability and prohibiting more extensive real-world ViT applications on resource-constrained devices. Sparse attention has been shown to be a promising direction for improving ha…
Neural architecture search (NAS) has gained immense popularity owing to its ability to automate neural architecture design. A number of training-free metrics are recently proposed to realize NAS without training, hence making NAS more scalable. Despite their competitive empirical performances, a unified theoretical understanding of these training-free metrics is lacking. As a consequence, (a) the relationships among these metrics are unclear, (b) there is no theoretical interpretation for their empirical performances, and (c) there may exist untapped potential in existing training-free NAS, wh…
Higher-order proximity (HOP) is fundamental for most network embedding methods due to its significant effects on the quality of node embedding and performance on downstream network analysis tasks. Most existing HOP definitions are based on either homophily to place close and highly interconnected nodes tightly in embedding space or heterophily to place distant but structurally similar nodes together after embedding. In real-world networks, both can co-exist, and thus considering only one could limit the prediction performance and interpretability. However, there is no general and universal sol…
Unifying Detection and Adaptation in Task-Free Continual Learning
School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；The Hong Kong University of Science and Technology（香港科技大学）；Shandong University（山东大学）；Qilu Hospital of Shandong University（山东大学齐鲁医院）
Evaluating the Efficiency of Latent Spaces via the Coupling-Matrix
Faculty of Engineering（工程学院）；Natural Sciences Işık University, İstanbul, Türkiye（自然科学学院，伊斯坦布尔大学）；Natural Sciences Sabancı University, İstanbul, Türkiye（自然科学学院，萨班奇大学）
Multi-Objective Latent Space Optimization of Generative Molecular Design Models
Texas A&M University（德克萨斯农工大学）；Brookhaven National Laboratory（布鲁克海文国家实验室）；Frederick National Laboratory（弗雷德里克国家实验室）；Argonne National Laboratory（阿贡国家实验室）
PixelFlowCast: Latent-Free Precipitation Nowcasting via Pixel Mean Flows
Department of Automation, Southeast University（东南大学自动化系）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）
