Predictive Representation Learning

Ask about this topic

Overview

Predictive representation learning studies how models can build useful internal states by predicting masked, future, or cross-view representations rather than reproducing every input detail. Common approaches include joint-embedding predictive architectures such as JEPA, contrastive predictive coding, masked latent prediction, and models that forecast temporal dynamics; they are used in vision, speech, health data, and robotics. Researchers evaluate learned features with transfer tasks, linear probes, forecasting benchmarks, and measures of control or planning performance. A central open tension is that predictability alone may discard rare but important information, so preventing collapse and aligning representations with causal, clinical, or action-relevant structure remain key challenges.

Latest papers

CardsList

176 papers40 papers in the last four weeks, up 111% on the four weeks before. 0.2% of all new papers.

Jun 5, 2026

Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning

Self-supervised methods that learn representations and predict dynamics fully in the latent space, such as JEPA, have been shown to confuse slowly varying noise with the dynamical signals they aim to capture. Specifically, when noise features remain approximately constant within each trajectory, contrastive predictive objectives preferentially encode these features instead of the true latent variables governing the system. The learned representation then becomes dominated by trajectory-specific noise, so downstream performance degrades with noise strength and does not improve even as the number and duration of training trajectories increase. We argue that this failure is a property of the objective itself, shared by a long line of contrastive predictive objectives that sample negatives across trajectories. To illustrate this generality, we study the failure mode and its remedy in two settings: a standard SimCLR-style JEPA on a synthetic moving-dot dataset, and DySIB, a recently introduced method designed for extracting physically interpretable representations of dynamics, on movies of a rigid-body pendulum. When negatives are instead sampled within a single trajectory, the slow noise can no longer distinguish frames within that trajectory, removing the predictive shortcut. Training one encoder simultaneously on many such trajectories then forces it to encode the variables relevant for the dynamics, with longer trajectories yielding better representations even for strong slow noise. Our results point toward principles for designing contrastive predictive objectives in dynamical representation learning, especially for physical systems with noisy experimental observations.

Paarth Gulati, Ilya Nemenman

Department of Physics, and Initiative in Theory and Modeling of Living Systems, Emory University, Atlanta, GA

Contrastive LearningRepresentation LearningPredictive Representation LearningShortcut LearningTemporal Representation Learning
AskPDF
Jun 5, 2026

What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction

Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces. We study this question through a unified probe-based evaluation across diverse encoder families, including image-only self-supervision, video pretraining with and without latent prediction, reconstruction-based autoencoders, diffusion models, and shortcut-forcing dynamics models. Using a common inverse-dynamics probing objective, we find that action-relevant structure is driven primarily by temporal video pretraining rather than pixel reconstruction fidelity: models with strong pixel decoding quality can exhibit near-zero action recoverability, while video-pretrained self-supervised encoders consistently achieve the best Pareto trade-off between visual fidelity and action prediction. Comparing V-JEPA and VideoMAE further shows that most gains arise from natural-video temporal context, with feature-level latent prediction providing a smaller additional benefit. These trends transfer across robotic benchmarks, though CALVIN reveals that static-environment tasks can partially mask the importance of temporal structure by allowing strong image priors to suffice. Finally, inverse-dynamics supervision substantially improves robustness to visual corruption, suggesting that action-aware objectives regularize latent geometry beyond clean-setting performance. Our results identify temporal predictive structure -- not reconstruction fidelity -- as the primary ingredient underlying action-relevant video representations.

Jewon Yeom, Hanseul Kim, Jeongjae Park +3

Graduate School of Data Science, Seoul National University

Video Representation LearningPredictive Representation LearningVideo World Models
AskPDF
Jun 2, 2026

Video-Mirai: Autoregressive Video Diffusion Models Need Foresight

Causal video generators must predict from the past, but they need not learn only from it. In streaming autoregressive video diffusion, each emitted segment becomes a commitment that future segments must preserve. Standard training, however, only asks each causal state to explain the present. This creates what we call a representation-level planning gap: states that fit the current segment may discard identity, layout, and motion information needed for a consistent future. We introduce Video-Mirai, a training-only method that closes this gap without changing causal inference: the generator rolls out causally, a frozen foresight encoder reads the completed rollout non-causally, and a lightweight predictor distills the resulting stopped-gradient targets into causal states. Future frames supervise representations, never generator inputs. At inference, the encoder and predictor are discarded, leaving the original architecture, per-step FLOPs, and KV-cache behavior unchanged. Video-Mirai improves a strong Causal-Forcing baseline on 5-second VBench from 83.8 to 84.6 in terms of Total Score. On 30-second rollouts beyond the training horizon, subject consistency improves from 84.9 to 88.5 and background consistency from 90.2 to 91.9. Ablations identify future-conditioned targets as the key ingredient, and probes show that future frames become more decodable from current features. Causality should constrain inference, not representation supervision. Our study highlights that visual autoregressive models need foresight. Project page: https://y0uroy.github.io/Video-Mirai.

Yonghao Yu, Lang Huang, Runyi Li +2

The University of Tokyo · National Institute of Informatics · Peking University

Temporal Consistency in Video GenerationAutoregressive DiffusionLong Video GenerationStreaming Video GenerationPredictive Representation LearningAutoregressive Video Generation+2
AskPDF
Jun 2, 2026

GeoSem-WAM: Geometry- and Semantic-Aware World Action Models

Recent World Action Models (WAMs) have demonstrated impressive capabilities in embodied decision-making. However, whether their effectiveness stems from explicit future imagination during inference or representation learning induced by predictive training remains an open question. Emerging evidence suggests the primary advantage lies in learning robust latent representations rather than generating future observations at test time. Nevertheless, existing WAMs mainly rely on RGB-based future prediction, which provides limited structural and spatial understanding of complex environments. To address this, we propose a structured world modeling framework that enhances latent representations through geometric and semantic supervision. Alongside future RGB prediction, our model introduces two auxiliary prediction branches for future geometry and semantic representations, enabling it to jointly capture scene dynamics, spatial geometry, and semantic context within a unified latent space. Crucially, our approach preserves efficient inference by avoiding explicit future rollout or video generation at test time. Extensive experiments show that incorporating structured world supervision consistently improves action prediction accuracy, scene understanding, and robustness under challenging embodied scenarios, highlighting its potential for advancing scalable and efficient WAMs.

Fulong Ma, Daojie Peng, Wenjun Yue +4

HKUST(GZ) · OC · HKU +4

World Models for RoboticsNext-Action PredictionWorld ModelsPredictive Representation LearningWorld Action Models
AskPDF
May 27, 2026

Exploratory Experience Shapes the Geometry of Predictive Representations

Active sensing links behavior and learning through an action-perception loop: actions determine the observations used to update internal predictive models of perception, which subsequently guide the next actions. Predictive-coding frameworks provide a natural way to model this process, since internal representations are continuously updated to predict future observations. Here, we ask how exploratory and exploitative behavioral strategies shape these internal predictive representations. We build an online learning agent in a tree-like maze with a controllable parameter regulating the balance between exploratory and exploitative regimes. The agent updates a predictive-coding-based perception model from experience generated by its own behavior. The model predicts both future maze states and reward probability, allowing the agent to select actions either by expected information gain during exploration or by predicted reward during exploitation. We show that the resulting internal predictive representations depend strongly on the agent's behavioral regime. Exploratory agents develop representations that are more spatially organized and better preserve the structure of maze transitions in latent space. In contrast, exploitative agents learn less organized representations. We then train this predictive model on natural trajectories of water-deprived mice navigating the same maze and compare the resulting representations with those learned from agent trajectories. More exploratory mice show representational geometries that closely match those of exploratory agents, whereas mice with more restricted visitation patterns resemble reward-driven, exploitative agents. Together, these findings suggest that exploration enables predictive models to form generalized internal representations by organizing latent space around both spatial location and transition context in artificial agents and animals.

Kseniia Shilova, Abdelrahman Sharafeldin, Advay Balakrishnan +1

School of Mathematics Georgia Institute of Technology Atlanta, GA 30332 · College of Computing Georgia Institute of Technology Atlanta, GA 30332

Computational Cognitive ModelingPredictive CodingRL ExplorationPredictive Representation LearningState Representation Learning
AskPDF
May 26, 2026

Learn from your own latents and not from tokens: A sample-complexity theory

Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which networks are trained to predict their own latent representations of related views or masked regions, as in data2vec and JEPA -- an idea related to predictive-coding accounts of the cortex. Despite strong empirical results, the theoretical understanding of these methods remains limited. Central questions include: by how much does latent prediction actually improve data efficiency? Is there a benefit to stacking such methods into multi-scale hierarchies? We answer both using as data a tractable probabilistic context-free grammar that captures the compositional structure of natural language and images. Such a grammar generates strings of visible tokens by recursively applying production rules along a tree of hidden symbols of depth LL. For such data, supervised or token-level SSL require a number of samples exponential in LL to recover the latent tree; we prove that latent prediction achieves this with a number of samples constant in LL, up to logarithmic factors. We confirm this bound with (i) a hierarchical clustering algorithm, (ii) an end-to-end neural network whose predictor-clusterer modules predict their own latents at each level via gradient descent, and (iii) the first sample-complexity analysis of data2vec, which we show implicitly performs hierarchical latent prediction. This suggests that explicit stacking such as H-JEPA is largely redundant.

Daniel J. Korchinski, Alessandro Favero, Matthieu Wyart

Department of Physics & Institute of Physics Johns Hopkins University & EPFL Baltimore, MD USA & Lausanne, VD Switzerland

Unsupervised LearningSelf-Supervised LearningSample ComplexityHierarchical Representation LearningPredictive Representation Learning
AskPDF
May 25, 2026

On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series

Clinical time-series learning is routinely constrained by small, heterogeneous cohorts and protocol drift, while its downstream use spans both classification (e.g., pathology diagnosis) and regression (e.g., temporal forecasting). These constraints make foundation-model pretraining appealing, but raises an important question of which inductive biases should the pretraining objective impose so that representations transfer across task types and subjects. We study this question in pathological gait analysis for spinal cord injury (SCI) via PathoFM, an encoder-centric transformer pretrained on multivariate gait windows with three complementary objectives: Local Completion (reconstruct contiguous masked spans to enforce local structure), Temporal Continuity (predict a masked mid-horizon continuation from an observed prefix to enforce smoothness and causal consistency), and Unsupervised In-Context Dynamics (support-query reconstruction conditioned on subject exemplar windows via attention). Empirically comparing objective families (grouping/contrastive, dynamics-based, and generative reconstruction), we find that dynamics-centric mixtures produce the most balanced transfer: grouping objectives favor discriminative margins but can degrade magnitude fidelity needed for continuous targets, whereas reconstruction-only objectives preserve waveform structure but may underperform on classification. Overall, combining local reconstruction with temporal continuity, and adding in-context conditioning when exemplar access is realistic, yields robust subject-generalizing representations.

Sharmita Dey, Diego Paez-Granados

ETH Zurich, Zurich, Switzerland · Swiss Paraplegic Research, Nottwil

Self-Supervised Time Series Representation LearningGait AnalysisPredictive Representation LearningTime Series Transformers
AskPDF
May 23, 2026

Word-Class and Construction-Like Structure Emerges in Neural Successor Representations Trained on Natural Language

Neural language models are typically trained on next-token prediction, although linguistic structure spans multiple temporal scales. Successor representations (SRs) make this horizon explicit by encoding discounted distributions over future states. Here, we ask whether such predictive representations can recover not only word classes, but also finer functional and construction-like structure from natural language. A residual network trained on WikiText-103 predicts SR distributions at three horizons without part-of-speech supervision. At the shortest horizon, unsupervised clustering robustly recovers nouns, verbs, and adjectives, while directed inter-cluster transitions reproduce familiar syntactic asymmetries. At finer resolutions and across 13 part-of-speech categories, the same geometry reveals semantic-functional groupings that cross category boundaries and directed relations tracing candidate date, measurement, and title-name constructions. Part-of-speech agreement declines as the predictive horizon lengthens. These results suggest that word classes are coarse regions within a richer predictive geometry in which categorical and construction-like linguistic structure emerge from future-word distributions.

Mathis Immertreu, Achim Schilling, Thomas Kinfe +1

Cognitive Computational Neuroscience Group, Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Germany · Neuromodulation and Neuroprosthetics, University Hospital Mannheim, University Heidelberg, Germany · Neuroscience Lab, University Hospital Erlangen, Germany +1

Predictive Representation LearningRepresentation Geometry in Language ModelsSuccessor Representations
AskPDF
May 21, 2026

Towards a General Intelligence and Interface for Wearable Health Data

While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable of characterizing higher-level states is difficult due to high phenotypic diversity and variation in individual baseline health, physiology, and lifestyle factors. Moreover, collecting wearable data paired with health outcome annotations is laborious and expensive, and retrospective annotation remains practically unfeasible, contributing to a scarcity of data with high-quality labels. To overcome these limitations, we propose a foundation model for wearable health that is pretrained on more than one trillion minutes of unlabeled sensor signals drawn from a large cohort of five million participants. We demonstrate that the joint scaling of model capacity and pretraining data volume leads to systematic improvements in performance, as evaluated on a diverse set of 35 health prediction tasks, spanning cardiovascular, metabolic, sleep, and mental health, as well as lifestyle choices and demographic factors. We find that this population scale representation unlocks label-efficient few-shot learning and generative capabilities for robust daily metric estimation. To further leverage this learned representation, we deploy a classroom of LLM agents to autonomously search the space of downstream predictive heads built on the model embeddings, showing broad performance improvements that increase with LLM model capacity. Finally, we show how integrating these downstream predictors into a Personal Health Agent can support model responses that are more relevant, contextually aware, and safe, and we validate this via 1,860 ratings from a cohort of clinicians.

Girish Narayanswamy, Maxwell A. Xu, A. Ali Heydari +37

1Google Research · University of Washington · University of Illinois Urbana-Champaign +2

Self-Supervised Pre-TrainingClinical Outcome PredictionPredictive Representation LearningWearable Health Monitoring
AskPDF
May 17, 2026

PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment

Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predict the learned representations of two views of the data from one another, and fully characterize its stability: non-collapsed stable equilibria align with leading nonlinear canonical correlation subspaces, while collapsed equilibria may also be stable attractors. Motivated by this result, we introduce PEIRA, a non-contrastive SSL method with an explicit objective defined through the trace of the optimal linear regressor. We show that its only stable equilibria are nontrivial global minimizers and recover the same canonical correlation subspaces, with regularization selecting the effective dimension. Experiments on ImageNet-1K and CIFAR-10 show PEIRA is competitive with VICReg and LeJEPA baselines, and qualitative empirical results support the theory.

Michael Arbel, Basile Terver, Jean Ponce

Univ. Grenoble Alpes, Inria · CNRS, Grenoble INP, LJK · Ecole Normale Supérieure / PSL +2

Unsupervised LearningVisual Representation LearningSelf-Supervised LearningJoint-Embedding Predictive ArchitecturePredictive Representation LearningCanonical Correlation Analysis
AskPDF
May 17, 2026

Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework

With the rapid progress of multimodal foundation models and predictive pre-training, an important open question is how to equip 3D point clouds with a pre-training paradigm that is better aligned with next-token and next-embedding learning. Existing point-cloud self-supervised methods are largely built on masked reconstruction or explicit geometric generation, and thus remain tied to input recovery rather than predictive dependency modeling. In this paper, we introduce PointNTP, which reformulates point cloud pre-training as a fully causal, decoder-free latent Next-Token Prediction problem. Specifically, each point cloud is first partitioned into local patches and serialized into a structured 3D token sequence according to patch-center geometry. The resulting sequence is then modeled by a causal Transformer under prefix-only conditioning, and trained with a shift-based prediction objective stabilized by stop-gradient targets. This design enables the model to learn structural dependencies directly in latent space, without reconstruction decoders or explicit geometric recovery. Extensive experiments demonstrate that the proposed PointNTP is highly competitive across multiple downstream tasks: it achieves 93.8%(+0.5%), 92.6%(+0.3%), and 89.3%(+1.1%) on OBJ_BG, OBJ_ONLY, and PB_T50_RS of ScanObjectNN, respectively; obtains 85.0%(+0.1%) in Cls.mIoU on ShapeNetPart; and reaches 71.1% mAcc on S3DIS Area 5. Overall, decoder-free causal latent prediction provides a simple, scalable, and potentially modality-agnostic paradigm for point-cloud self-supervised learning, offering a new 3D perspective on foundation-style predictive learning for 3D data.

Yumeng Yao, Jingzhi Dong, Haowen Gu +4

Nanjing University of Science and Technology · Hangzhou City University · East China Normal University +1

Point Cloud Learning3D ViTsSelf-Supervised Pre-TrainingSequence ModelingNext-Token PredictionPredictive Representation Learning+1
AskPDF
May 15, 2026

Constrained latent state modeling: A unifying perspective on representation learning under competing constraints

Learning latent representations from temporal, multimodal, and partially observed data requires specifying what information a latent state should retain, discard, and organize. Existing approaches encode these requirements through heterogeneous objectives, making methods difficult to compare and learned representations difficult to interpret. We propose Constrained Latent State Modeling (CLSM), a conceptual framework that characterizes latent states through six complementary properties: predictive sufficiency, minimality, temporal coherence, observation compatibility, invariance to nuisance factors, and structural constraints. CLSM separates these properties from the surrogate objectives used to induce them and from the diagnostics used to evaluate them, and clarifies how combinations of constraints can improve identifiability by restricting the space of admissible representations. We reinterpret major representation-learning families through this common design space and illustrate the framework with a controlled synthetic benchmark. The experiments show how objectives produce distinct latent organizations and empirical trade-offs depending on the prediction target, surrogate formulation, parameterization, and optimization. Companion repository containing the reference implementation, reproducible experiments, documentation, and model cards: https://github.com/gwenole-quellec/clsm

Gwenolé Quellec

LaTIM UMR 1101, Inserm, Brest, 29200, France.

Representation LearningPredictive Representation LearningState Representation LearningInvariant Representation Learning
AskPDF
May 15, 2026

Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model

Humans abstract experiences into structured representations to facilitate pattern inference and knowledge transfer. While the hippocampal-entorhinal (HPC-MEC) circuit is known to represent both spatial and conceptual spaces, the mechanisms for concurrently extracting abstract structures from continuous, high-dimensional dynamics remain poorly understood. We propose a brain-inspired hierarchical model that simultaneously infers latent transitions and constructs a predictive visual world model. Our architecture employs an inverse model for structural extraction alongside an HPC-MEC coupling model that dissociates relational structures (MEC) from integrated episodic scenes (HPC). Using primitive transformation dynamics as a benchmark, we demonstrate the model's capacity for structural abstraction. By leveraging velocity-driven path integration, the framework enables robust prediction and structural reuse across diverse contexts, thereby achieving structural generalization. This work provides a novel computational framework for understanding how brain-inspired, self-supervised learning of world models facilitates the acquisition of reusable abstract knowledge.

Tianqiu Zhang, Muyang Lyu, Xiao Liu +1

Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, IDG/McGovern Institute for Brain Research, Center of Quantitative Biology, School of Psychological and Cognitive Sciences, Key Laboratory of Machine Perception (Ministry of Education), Peking University. · HHMI Janelia.

Computational Cognitive ModelingWorld Model LearningHierarchical Representation LearningPredictive Representation Learning
AskPDF
May 13, 2026

CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision

Channel state information (CSI) provides a widely available sensing modality for human and environment perception, but existing CSI sensing models usually rely on task-specific supervised training and require substantial labeled data for each task, device, user, or environment. This limits their scalability in practical deployments where unlabeled CSI is abundant but labeled data is costly to collect. In this paper, we present CSI-JEPA, a self-supervised predictive representation learning framework for label-efficient, multi-task Wi-Fi sensing. CSI-JEPA learns reusable temporal-spectral representations from unlabeled CSI samples by predicting latent features of masked channel regions from visible context. To better match the physical structure of CSI, CSI-JEPA tokenizes channel-response amplitude windows along the time and subcarrier dimensions. It then introduces a channel variation-aware masking strategy that samples predictive targets from regions with stronger local temporal and subcarrier-domain variations. After pretraining, the encoder is frozen and used as a backbone, with lightweight task-specific adapters added for downstream sensing tasks. We evaluate CSI-JEPA on seven real-world Wi-Fi sensing tasks spanning diverse objectives and deployment settings. The results show that CSI-JEPA improves downstream sensing performance over competitive baselines, achieving up to 10.64 percentage points mean accuracy gain over state-of-the-art supervised Transformer and matched-budget label savings of up to 98.0%.

Xuanhao Luo, Zhizhen Li, Yuchen Liu

North Carolina State University, USA

Self-Supervised Pre-TrainingSelf-Supervised Time Series Representation LearningMulti-Task LearningPredictive Representation LearningWi-Fi Sensing
AskPDF
May 12, 2026

TRACE: Temporal Routing with Autoregressive Cross-channel Experts for EEG Representation Learning

Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stationary. Channels observed at the same time provide coupled measurements of neural activity, while the relevant temporal dynamics vary across contexts. This structure is poorly matched by architectures that apply uniform computation across time or route each channel patch independently. To this end, we propose TRACE, an autoregressive EEG pre-training framework that predicts future EEG patches from causal context while performing temporally adaptive and cross-channel coherent computation. At each temporal step, TRACE derives an expert routing decision from the causal cross-channel history and applies it jointly to all channels at that step. This preserves instantaneous cross-channel coherence while allowing different temporal regimes to activate different computation. Since routing is defined over the available channel set and causal temporal context, TRACE is compatible with heterogeneous pre-training across corpora with different channel counts, montages, sequence lengths, and recording domains. Across eight downstream EEG benchmarks, TRACE is evaluated in both settings: when downstream domains are seen only as unlabeled pre-training data and when downstream datasets are completely unseen during pre-training. It obtains the best results on several benchmarks while remaining competitive on motor imagery and clinical event classification tasks, with ablations supporting the importance of cross-channel temporal routing.

Fan Ma, Qier An, Peng Chen +6

Department of Biomedical Informatics and Data Science, Yale University

Representation LearningSelf-Supervised Pre-TrainingMixture-of-Experts InferencePredictive Representation LearningEEG Foundation Models
AskPDF
May 11, 2026

Forecast-aware Gaussian Splatting for Predictive 3D Representation in Language-Guided Pick-and-Place Manipulation

We introduce Forecast-aware Gaussian Splatting (Forecast-GS), a predictive 3D representation framework for language-conditioned robotic manipulation. While recent manipulation systems have made progress by grounding language instructions into robot affordances, value maps, or relational keypoint constraints, they usually reason over the current scene and do not explicitly model the task-completed state. This limitation is critical when success depends on satisfying spatial and semantic goals under partial observations, where the robot must evaluate whether a candidate action leads to a feasible task-consistent outcome. We validate Forecast-GS on real-world pick-and-place manipulation tasks, including Cutter-to-Box, Apple-to-Bowl, and Sponge-to-Tray. For each task, we conduct 25 real-world trials under varied initial object configurations using the same robot platform and sensing setup. Forecast-GS with automatic candidate selection achieves success rates of 21/25, 23/25, and 16/25 on the three tasks, respectively, outperforming the ReKep baseline, which achieves 15/25, 19/25, and 10/25. A diagnostic human-assisted setting further improves success rates to 23/25, 24/25, and 19/25, suggesting that candidate generation is effective while automatic ranking remains imperfect. These results suggest that explicitly forecasting task-completed 3D states enables more reliable action evaluation, while the gap between automatic and human-assisted selection indicates that robust final-state ranking remains an important challenge for fully autonomous manipulation. Overall, Forecast-GS provides an interpretable bridge between language understanding, 3D perception, and robotic manipulation planning.

Kaixin Jia, Jiacheng Xu

KTH Royal Institute of Technology, Stockholm, Sweden.

3D Gaussian Splatting3D Scene PredictionLanguage-Conditioned Robot ManipulationRobotic ManipulationPredictive Representation Learning
AskPDF
May 11, 2026

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

Joint-embedding predictive architectures (JEPA) learn representations by predicting in latent space, as in computer vision; retaining the action-conditioned predictor at inference turns them into latent world models, enabling planning in robotics (V-JEPA 2-AC). Bringing this design to EHR patient trajectories---a predictor that simulates a patient's trajectory in latent space---has not been explored. We use an LLM as the encoder, reading the hourly record as text, avoiding feature engineering and vocabulary harmonisation. But an LLM adapted by supervised fine-tuning does not organise its latent space around physiological dynamics, and freezing it to train the predictor, as in V-JEPA 2-AC, leaves the encoder unaware of the rollout signal: the predictor degrades under rollout. We instead co-train encoder and predictor under one latent-prediction objective, grounding the encoder in the dynamics its predictor must follow. Naïve co-training, however, is unstable: the untrained predictor drags the encoder toward collapse, and the predictor's rollout diverges as its target space moves. We present Clin-JEPA, a five-phase curriculum that stably co-trains an LLM encoder with a latent trajectory predictor on MIMIC-IV. Three evaluations support the design: (1) under 48-hour autoregressive rollout the co-trained predictor degrades least (predictor degradation ×\times1.06, against ×\times1.23--1.36 for two-stage designs and ×\times6.3--66 for curriculum ablations) while the co-trained encoder resolves the progression of patient state most sharply (largest state displacement); (2) the co-trained encoder separates deteriorating from stable patients in its latent space with Cohen's d=1.59d{=}1.59, against ≤\leq0.50 for two-stage encoders; (3) one set of embeddings serves 34 downstream tasks across three benchmarks, outperforming strong per-task tuned baselines and a pretrained EHR foundation model.

Yixuan Yang, Mehak Arora, Ryan Zhang +10

Duke University, Durham, NC, USA

Self-Supervised Pre-TrainingHealthcareJoint-Embedding Predictive ArchitecturePredictive Representation LearningLongitudinal EHR Modeling
AskPDF
May 10, 2026

MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward scenarios, learning representations that align state and goal latents is a challenge, as the encoder can learn goal-agnostic features that destabilize policy learning. We address this issue by learning the encoder's representation with alignment objectives that capture the environment across multiple scales, from local physical dynamics to long-horizon goal-directed structure. Concretely, we propose MSPR, a framework that leverages multi-scale predictive supervision to enforce goal-directed alignment within the latent space. We demonstrate that MSPR leads to strong performance on both vision and state-based tasks. Furthermore, we show that our approach is resilient under realistic, challenging data regimes, maintaining state-of-the-art performance across a wide variety of tasks.

Valliappan Chidambaram Adaikkappan, Sai Rajeswar, Pietro Mazzaglia +1

Mila, McGill University · Qualcomm Research

Offline RLPredictive Representation LearningState Representation LearningSparse-Reward RLGoal-Conditioned RL
AskPDF
May 10, 2026

Towards Effective Theory of LLMs: A Representation Learning Approach

We propose Representational Effective Theory (RET), a framework for describing large language model computation in terms of learned macrostates rather than microscopic details. RET learns these macrostates from hidden-state trajectories using a BYOL/JEPA-style self-supervised objective, coarse-graining activations into macrovariables that preserve higher-level structure relevant for prediction and interpretation. We evaluate whether these macrovariables are practically relevant for interpretability: RET yields temporally consistent states that reveal "mental-state" trajectories of reasoning, capture high-level semantic structure, support early prediction of behavioral outcomes such as sycophancy, and provide causal handles for steering generations toward interpretable computational phases. Together, these results suggest that LLM computation admits useful effective descriptions via RET: high-level, dynamically meaningful variables that support interpretation, prediction, and intervention.

Muhammed Ustaomeroglu, Guannan Qu

Carnegie Mellon University Pittsburgh, PA 15213

LLM InterpretabilityMechanistic InterpretabilityLanguage ModelingPredictive Representation Learning
AskPDF
May 7, 2026

3D MRI Image Pretraining via Controllable 2D Slice Navigation Task

Self-supervised pretraining has become the mainstream approach for learning MRI representations from unlabeled scans. However, most existing objectives still treat each scan primarily as static aggregations of slices, patches or volumes. We ask whether there exists an intrinsic form of self-supervision signal that is different from reconstructing the masked patches, through transforming the 3D volumes into controllable 2D rendered sequences: by rendering slices at continuous positions, orientations, and scales, a 3D volume can be converted into dense video-action sequences whose controls are the action trajectories. We study this formulation with an action-conditioned pretraining objective, where a tokenizer encodes slice observations and a latent dynamics model predicts the evolution of latent features. Across representative anatomical and spatial downstream tasks, the proposed pretraining is evaluated against standard static-volume baselines, tokenizer-only pretraining, and dynamics variants without aligned actions. These results suggest that controllable MRI slice navigation provides a useful complementary pretraining interface for learning anatomical and spatial representations from large unlabeled MRI collections.

Yu Wang, Qingchao Chen

Beijing University of Posts and Telecommunications · Peking University

Visual Representation LearningSelf-Supervised Pre-Training3D Medical ImagingPredictive Representation LearningMedical Image Representation Learning
AskPDF
May 7, 2026

AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling

High-fidelity CFD is essential for aerodynamic design, but repeated simulations are computationally expensive, motivating surrogate models for rapid evaluation across geometries and operating conditions. Most existing surrogates are designed for direct field regression, requiring the evaluation of millions of field points even when only an aerodynamic quantity or a localized region is needed, while their internal representations are not intended for direct use in downstream tasks. We introduce AeroJEPA, a framework inspired by joint-embedding predictive architectures that represents the problem in two distinct latent spaces: context tokens encode geometry, while predicted tokens encode the aerodynamic state. Both representations remain directly accessible for downstream tasks, such as linear readouts of design variables and aerodynamic quantities without decoding and integrating the full field. When spatial detail is needed, a continuous implicit decoder evaluates the field only at the requested coordinates while reusing the encoded geometry. We evaluate AeroJEPA on HiLiftAeroML, with multi-million-point fields, and SuperWing, which spans a broad family of transonic wings. Compared with state-of-the-art direct-regression surrogates, AeroJEPA trades peak full-field accuracy for compact, reusable representations. In our selective-decoding experiment, however, AeroJEPA substantially outperforms the evaluated direct-regression surrogates while avoiding predictions over the remainder of the aircraft. The learned representations further support controlled interpolation, concept-vector arithmetic, and preliminary constrained latent-space optimization. These results show how predictive representations can support aerodynamic analysis with or without full-field reconstruction.

Francisco Giral, Abhijeet Vishwasrao, Andrea Arroyo Ramo +8

Universidad Politécnica de Madrid · University of Michigan · Universitat Politècnica de València +3

Joint-Embedding Predictive ArchitecturePDE Surrogate ModelingPredictive Representation LearningComputational Fluid Dynamics
AskPDF
May 6, 2026

The Predictive-Causal Gap: An Impossibility Theorem and Large-Scale Neural Evidence

We report a systematic failure mode in predictive representation learning. Across 2695 neural network configurations trained to predict linear-Gaussian dynamics, the optimal encoder tracks the environment rather than the system it is meant to model. The mean causal fidelity -- the fraction of encoder sensitivity allocated to system degrees of freedom -- is 0.49, and only 2.5% of configurations exceed 0.70. The failure intensifies with dimension: at N=100, the optimal encoder becomes causally blind (fidelity ~10^{-8}) while achieving 92% lower prediction error than the causal representation. We prove this is not an optimization artifact but a structural property of the predictive objective: when environment modes are slower or less noisy than system modes, every minimizer of the population risk encodes the former. The set of dynamics exhibiting this predictive-causal gap is open and of positive measure in parameter space. In a nonlinear Duffing-GRU sweep, unconstrained predictors learn environment-dominant representations in 55% of tasks (95% CI 41--68%) versus 24% under operational grounding (p=2.3e-3); the median out-of-distribution MSE inflation under environment shift is 1.82x versus 1.00x. Operational grounding -- restricting the loss to system observables -- partially suppresses the gap, but causal fidelity is never recovered without an explicit system-environment boundary. The results identify the predictive-causal gap as a structural limit of learning, with implications for self-supervised representation learning, world models, and the scaling paradigm.

Kejun Liu

State Key Laboratory of Bioinspired Interface Material Science, Institute of Nano & Functional Materials, Soochow University, Suzhou 215123, China

Causal Representation LearningPredictive Representation LearningTime Series Representation Learning
AskPDF
May 5, 2026

Understanding Self-Supervised Learning via Latent Distribution Matching

Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones. We cast SSL as latent distribution matching (LDM): learning representations that maximize their log-probability under an assumed latent model (alignment), while maximizing latent entropy to prevent collapse (uniformity). This view unifies independent component analysis with contrastive, non-contrastive, and predictive SSL methods, including stop gradient approaches. Leveraging LDM, we derive a nonlinear, sampling-free Bayesian filtering model with a Kalman-based predictor for high-dimensional timeseries. We further prove that predictive LDM yields identifiable latent representations under mild assumptions, even with nonlinear predictors. Overall, LDM clarifies the assumptions behind established SSL methods and provides principled guidance for developing new approaches.

Fabian A Mikulasch, Friedemann Zenke

Friedrich Miescher Institute for Biomedical Research, 4056 Basel, Switzerland · Faculty of Science, University of Basel, 4033 Basel, Switzerland

Representation LearningSelf-Supervised LearningDistribution MatchingPredictive Representation Learning
AskPDF
May 5, 2026

Text-Conditional JEPA for Learning Semantically Rich Visual Representations

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature prediction remains challenging and may fail to learn semantic representations. In this work, we propose Text-Conditional JEPA (TC-JEPA) that uses image captions to reduce the prediction uncertainty. Specifically, we modulate the predicted patch features using a fine-grained text conditioner that computes sparse cross-attention over input text tokens. With such conditioning, patch features become predictable as a function of text, thus are more semantically meaningful. We show TC-JEPA improves downstream performance and training stability, with promising scaling properties. TC-JEPA also offers a new vision-language pretraining paradigm based on feature prediction only, outperforming contrastive methods on diverse tasks, especially those requiring fine-grained visual understanding and reasoning.

Chen Huang, Xianhang Li, Vimal Thilak +2

Apple, Cupertino, United States

Joint-Embedding Predictive ArchitecturePredictive Representation LearningSelf-Supervised Visual Representation LearningVision-Language Pretraining
AskPDF
May 3, 2026

Latent State Design for World Models under Sufficiency Constraints

A world model matters to an agent only through the state it constructs. That state must preserve some information, discard other information, and support some future function: prediction, control, planning, memory, grounding, or counterfactual reasoning. This paper treats world-model research as latent state design under sufficiency constraints. We propose a functional taxonomy that groups methods by what their latent state is for, rather than by architecture or application domain: predictive embedding, recurrent belief state, object/causal structure, latent action interface, grounded planning interface, and memory substrate. These roles expose distinctions that architecture-based groupings hide, including the gap between predictive sufficiency and control sufficiency, and the gap between passive video prediction and counterfactual action modeling. The taxonomy supports an evaluation framework that judges a model by the sufficiency constraint its latent state was built to satisfy. We compare methods along seven axes: representation, prediction, planning, controllability, causal/counterfactual support, memory, and uncertainty. We use the resulting matrix as a diagnostic for what a latent state preserves, discards, and enables. The conclusion that follows is that an actionable world model is the one whose state construction matches the task, not the one that preserves the most information.

Keon Woo Kim

Om Labs

Representation LearningPredictive Representation LearningLatent World ModelsState Representation LearningWorld Model Evaluation
AskPDF
May 1, 2026

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining

Continuous Glucose Monitoring (CGM) can detect early metabolic subphenotypes (insulin resistance, IR; ββ-cell dysfunction), but population-scale deployment faces two coupled problems. First, the same physiological state appears through multiple views (CGM time series, venous OGTT, Glucodensity summaries), so single-view representations fail to transfer when deployment shifts the modality or setting. Second, baselines perform inconsistently across these shifts. Both problems point to one remedy: representations that abstract away from any single view to capture higher-level temporal and distributional structure. We propose CGM-JEPA, a self-supervised pretraining framework which predicts masked latent representations rather than raw values, yielding abstraction that transfers across modalities. X-CGM-JEPA adds a masked Glucodensity cross-view objective for complementary distributional information. We pretrain on ∼\sim389k unlabeled CGM readings from 228 subjects and evaluate on two clinical cohorts (N=27N=27 and N=17N=17 public-release subsets) across three regimes (cohort generalization, venous-to-CGM transfer, home CGM) under 20-iteration ×\times 2-fold cross-validation. X-CGM-JEPA ranks first or second on AUROC for both endpoints across all three regimes while no baseline does, exceeding the strongest baseline by up to +6.5+6.5 pp in cohort generalization and +3.6+3.6 pp in venous-to-CGM transfer (paired Wilcoxon, p<0.001p<0.001). Under modality shift, it matches mean AUROC while redistributing toward weaker subgroups (ethnicity AUROC gap shrinks 25-54%); on sparse in-domain venous data, the distributional view lifts label-aware clustering (ARI +39%+39\%, NMI +40%+40\%). Code and weights: https://github.com/cruiseresearchgroup/CGM-JEPA

Hada Melino Muhammad, Zechen Li, Flora Salim +1

University of New South Wales · Google Research

Cross-Modal Representation LearningSelf-Supervised Time Series Representation LearningJoint-Embedding Predictive ArchitecturePredictive Representation LearningTime Series Representation LearningContinuous Glucose Monitoring
AskPDF
Apr 30, 2026

Why Self-Supervised Encoders Want to Be Normal

Self-supervised learning has achieved remarkable empirical success in learning robust representations without explicit labels, most recently demonstrated within the framework of Joint-Embedding Predictive Architectures (JEPA). However, a fundamental question remains: what analytical principles drive these encoders toward specific distributional states? In this paper, we demonstrate that the preference for normal distributions in self-supervised encoders is a direct consequence of the Information Bottleneck (IB) principle. By recasting the IB objective as a rate-distortion problem over the predictive manifold, we provide a theoretical basis for why optimal, target-neutral, latent representations should tend towards isotropic Gaussian states. Under this framework, we show that latent representations correspond to soft clustering of inputs sharing similar predictive distributions, organized within a natural simplex structure. This perspective unifies a wide range of existing supervised and less-supervised objectives and provides a principled explanation for commonly used regularization schemes. Furthermore, we derive practical loss objectives that approximate this structure and demonstrate their effectiveness on standard benchmarks. Ultimately, our framework offers a geometric lens to understanding representation collapse and it establishes a mathematical system for regularization strategies to be used to ensure high-entropy, informative embeddings in modern self-supervised models.

Yuval Domb

Representation CollapseSelf-Supervised LearningRate-Distortion TheoryJoint-Embedding Predictive ArchitectureInformation BottleneckPredictive Representation Learning
AskPDF
Apr 27, 2026

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data

Identifying the dynamical state variables of a system from high-dimensional observations is a central problem across physical sciences. The challenge is that the state variables are not directly observable and must be inferred from raw high-dimensional data without supervision. Here we introduce DySIB (Dynamical Symmetric Information Bottleneck) as a method to learn low-dimensional representations of time-series data by maximizing predictive mutual information between past and future observation windows while penalizing representation complexity. This objective operates entirely in latent space and avoids reconstruction of the observations. We apply DySIB to an experimental video dataset of a physical pendulum, where the underlying state space is known. The method, with hyperparameters of the learning architecture set self-consistently by the data, recovers a two-dimensional representation that matches the dimensionality, topology, and geometry of the pendulum phase space, with the learned coordinates aligning smoothly with the canonical angle and angular velocity. These results demonstrate, on a well-characterized experimental system, that predictive information in latent space can be used to recover interpretable dynamical coordinates directly from high-dimensional data.

K. Michael Martini, Eslam Abdelaleem, Paarth Gulati +1

Department of Physics, Emory University, Atlanta, GA, USA · Schools of Physics and Psychology, Georgia Institute of Technology, Atlanta, GA, USA · Initiative in Theory and Modeling of Living Systems, Emory University, Atlanta, GA, USA +1

Dynamical SystemsInformation BottleneckPredictive Representation LearningState Representation Learning
AskPDF
Apr 26, 2026

A General Representation-Based Approach to Multi-Source Domain Adaptation

A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to learn latent representations of the observations, which facilitate knowledge transfer in the latent space. However, existing approaches often rely on restrictive assumptions to establish identifiability of the joint distribution in the target domain, such as independent latent variables or invariant label distributions, limiting their real-world applicability. In this work, we propose a general domain adaptation framework that learns compact latent representations to capture distribution shifts relative to the prediction task and address the fundamental question of what representations should be learned and transferred. Notably, we first demonstrate that learning representations based on all the predictive information, i.e., the label's Markov blanket in terms of the learned representations, is often underspecified in general settings. Instead, we show that, interestingly, general domain adaptation can be achieved by partitioning the representations of Markov blanket into those of the label's parents, children, and spouses. Moreover, its identifiability guarantee can be established. Building on these theoretical insights, we develop a practical, nonparametric approach for domain adaptation in a general setting, which can handle different types of distribution shifts.

Ignavier Ng, Yan Li, Zijian Li +3

Carnegie Mellon University · Mohamed bin Zayed University of Artificial Intelligence

Multi-Source Domain AdaptationUnsupervised Domain AdaptationDomain AdaptationPredictive Representation Learning
AskPDF
Apr 24, 2026

Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs

Self-supervised learning in healthcare has largely relied on invariance-based objectives, which maximize similarity between different views of the same patient. While effective for static anatomy, this paradigm is fundamentally misaligned with clinical diagnosis, as it mathematically compels the model to suppress the transient pathological changes it is intended to detect. We propose a shift towards Action-Conditioned World Models that learn to simulate the dynamics of disease progression, or Event-Conditioned. Adapting the LeJEPA framework to physiological time-series, we define pathology not as a static label, but as a transition vector acting on a patient's latent state. By predicting the future electrophysiological state of the heart given a disease onset, our model explicitly disentangles stable anatomical features from dynamic pathological forces. Evaluated on the MIMIC-IV-ECG dataset, our approach outperforms fully supervised baselines on the critical triage task. Crucially, we demonstrate superior sample efficiency: in low-resource regimes, our world model outperforms supervised learning by over 0.05 AUROC. These results suggest that modeling biological dynamics provides a dense supervision signal that is far more robust than static classification. Source code is available at https://github.com/cljosegfer/lesaude-dynamics

Jose Geraldo Fernandes, Luiz Facury, Pedro Robles Dutenhefner +1

Department of Computer Science Universidade Federal de Minas Gerais Belo Horizonte, Brazil

Predictive Representation LearningHealthcareElectrocardiographySelf-Supervised Time Series Representation LearningWorld ModelsAction-Conditioned World Models+3
AskPDF