ICML 2026 Papers

Planning with a learned model remains a key challenge in model-based reinforcement learning (RL). In decision-time planning, state representations are critical as they must support local cost computation while preserving long-horizon structure. In this paper, we show that the Laplacian representation provides an effective latent space for planning by capturing state-space distances at multiple time scales. This representation preserves meaningful distances and naturally decomposes long-horizon problems into subgoals, also mitigating the compounding errors that arise over long prediction horizons. Building on these properties, we introduce ALPS, a hierarchical planning algorithm, and demonstrate that it outperforms commonly used baselines on a selection of offline goal-conditioned RL tasks from OGBench, a benchmark previously dominated by model-free methods.

Cross-subject generalization in biomedical time-series aims to learn representations that generalize to unseen subjects while suppressing subject-specific variability. Most existing methods implicitly suppress the variability through model building or subject adversarial learning, but rarely model it explicitly. We introduce \textbf{spectral drift} as a new perspective to characterize subject specific variability. Specifically, BTS signals under the same label often share consistent oscillatory structure, yet exhibit subject-dependent magnitude or phase shifts in specific frequency components, which we interpret as subject-specific variability. Building on this insight, we propose \textit{BioFormer}. At its core is a Frequency-Band Alignment Module (FBAM) that generates band-wise modulation factors from the spectral distribution and adaptively adjusts amplitude and phase to align spectral structure, thereby mitigating variability. We further pair FBAM with Sample Conditional Layer Normalization, which infers normalization parameters from intrinsic signal statistics rather than subject identity, stabilizing cross-subject representations. Extensive experiments on six datasets demonstrate that BioFormer outperforms 12 baselines, yielding absolute F1-score improvements of 6\%.

We study the robustness of stochastic mirror descent (SMD) under heavy-tailed noise, focusing on whether the method retains its convergence guarantees when run with infinite-variance stochastic gradient input. To address this question in a principled manner, we begin by introducing a continuous-time model of SMD as a stochastic differential equation (SDE) driven by a centered Lévy noise process with finite $p$-th order moments, $1 < p \leq 2$. This scheme—which we call the Lévy mirror flow (LMF)—arises naturally as the scaling limit of SMD in the presence of heavy-tailed noise. In particular, when $p < 2$—the heavy noise regime—the trajectories of LMF generically exhibit jump discontinuities of arbitrary magnitude which, if frequent enough, lead to infinite variance. Nonetheless, despite this highly singular behavior, we show that LMF attains $\epsilon$-optimality within $\mathcal{O}(\epsilon^{-p/(p-1)})$ time in the convex case, and within $\tilde{\mathcal{O}}(\epsilon^{-1/(p-1)})$ time for (relatively) strongly convex objectives. These guarantees provide a transparent characterization of the impact of frequent long jumps on the convergence of the process, and percolate to a series of matching discrete-time guarantees for several variants of SMD under heavy-tailed noise.

Time-series foundation models (TSFMs) deliver strong cross-domain generalization, but their scale makes deployment costly. Knowledge distillation is a natural compression route, yet prior TSFM distillation typically imitates teacher outputs, features, or pairwise relations, and therefore remains tightly coupled to teacher-specific training trajectories while underutilizing two empirical properties: (i) high-level representations across model scales tend to converge toward a shared, approximately low-rank geometry, and (ii) layer-wise utility follows a long-tail pattern. We propose consensus subspace distillation, which reframes distillation as aligning a student to a model-agnostic geometric object: a scale-invariant low-rank consensus subspace together with its center statistics. Offline, we screen high-contribution layers via drop-layer marginal loss, estimate a shrinkage-stabilized covariance from their embeddings, and derive a truncated eigensubspace that defines a consensus projector. Online, we project student embeddings into this subspace and match the teacher’s projected mean and covariance using a lightweight mean--covariance objective, enabling stable optimization without rigid pointwise feature binding. To mitigate subset-induced bias, we further introduce a frequency-domain uncertainty injection mechanism that inflates spectral density based on characteristic-function discrepancies and injects dispersion only within the consensus directions. Across forecasting and imputation, the distilled student matches or slightly improves upon the teacher, while exhibiting a predictable trade-off under strict zero-shot classification. With MOMENT-Large as teacher, we achieve about 90% parameter reduction and substantial distillation-time savings while retaining comparable performance across multiple time-series tasks. Code and compressed weights are available at anonymous.4open.science/r/CSD-13C3/.

Effective time series forecasting enables various real-world applications, benefiting from the proliferation of mobile devices. However, the volume of time series data may vary significantly across domains due to high data acquisition costs and data regulations. To maximally create value from sparse data, this study focuses on a new problem of source-free time series forecasting, aiming to adapt a pretrained model from sufficient source time series to the sparse target time series without access to the source data, enabling data protection. To achieve this, we propose TimeID, a novel source-free time series forecasting framework with a large language model (LLM) centric proxy denoising inspired by the powerful generalization capabilities of LLMs. Specifically, TimeID consists of three key components: (1) dual-branch invariant disentangled feature learning that enforces representation- and gradient-wise invariance by means of season-trend decomposition; (2) lightweight, parameter-free proxy denoising that dynamically calibrates systematic biases of LLMs; and (3) knowledge distillation that bidirectionally aligns the denoised prediction and the original target prediction. Extensive experiments on real-world datasets demonstrate that TimeID outperforms state-of-the-art baselines, improving MSE and MAE by 10.7\% and 9.3\% on average. The code is available at https://github.com/decisionintelligence/TimeID.

Spatial-temporal time series forecasting is challenging due to complex lead-lag dependencies, which are often ignored or inadequately modeled by existing methods. Thus, we propose LagLLM, the first LLM-empowered framework that explicitly models lead–lag dependencies by unifying data-driven dynamics modeling and knowledge-driven semantic reasoning. Specifically, LagLLM constructs a lead-lag graph by integrating learnable embeddings, spatial proximity, and prompt-guided reasoning from a frozen LLM, which can capture lead-lag dependencies informed by the underlying data structure and semantic knowledge. In addition, LagLLM introduces structural token sorting based on the graph, which can make a fine-tuned LLM explicitly perceive directional and delayed interactions. Experiments on eight real-world datasets show that LagLLM achieves the state-of-the-art performance with improved accuracy, robustness, and interpretability. The code is available at https://github.com/w2obin/LagLLM-2026.

Expert-annotated time series datasets often suffer from low agreement, especially in medical applications where decisions rely on subjective criteria and inconsistent thresholds. Such variability degrades annotation quality and thus limits the reliability of supervised classification models. To address this, we propose to rely on a pairwise comparison-based approach, which provides a more robust alternative to individual annotation, since relative judgments are typically easier and yield higher consistency. The problem is thus transformed into a ranking problem and we introduce an ideal point model adapted to time series data using elastic similarity measures such as Dynamic Time Warping (DTW) and Time Warp Edit Distance (TWED). We prove Lipschitz continuity of these distances and demonstrate several convergence guarantees for this model. To facilitate gradient-based optimization, we also introduce a differentiable version of the TWED. Finally, we show through multiple experiments that our approach produces accurate and robust rankings under noisy annotation conditions.

Conventional time-series discriminative forecasting relies on point-wise regression, which inherently induces over-smoothing and fails to capture stochastic volatility in complex systems. While first-order generative flow matching methods mitigate this issue, they ignore system inertia, resulting in phase-space ambiguities and high sensitivity to noise. We introduce KineFlow, a generative time-series forecasting framework that augments flow matching with a phase-space Neural Acceleration Field, treating exogenous inputs as driving forces that produce gradual momentum shifts rather than abrupt state perturbations. This second-order formulation serves as a structural filter via double integration, suppressing high-frequency noise and producing robust, physically consistent predictions. Extensive experiments on six real-world benchmarks demonstrate that KineFlow achieves an average 15% MSE improvement over discriminative baselines and an 8% gain in CRPS compared to state-of-the-art generative methods.

Point forecasting for graph-structured multivariate time series is a fundamental problem, but rigorous uncertainty quantification for such predictions is still underexplored. Conformal prediction (CP) offers uncertainty estimation with a solid coverage guarantee under the exchangeability assumption, which requires the joint data distribution to be unchanged under permutation. However, in graph-structured time series, inherent cross-node coupling can violate the exchangeability condition, making direct application of CP unreliable. Inspired by the spectral graph theory, such coupling resides in global trends and can be characterized by the low-frequency components, while high-frequency components are nearly exchangeable. Therefore, we propose a novel concept named **S**pectral **G**raph **C**onditional **E**xchangeability (SGCE), which conditions exchangeable high-frequency components on low-frequency ones to preserve global trends and enable effective CP in the spectral domain. Based on SGCE, we further propose **S**pectral **C**onformal prediction via w**A**ve**LE**t transform (SCALE). SCALE uses graph wavelets to decompose low/high-frequency components and conformalizes high-frequency residuals via adaptive gating over a low-frequency embedding. Experimental results on real-world benchmark datasets across multiple application domains show that SCALE not only achieves valid coverage but also consistently improves the coverage-efficiency trade-off over the state-of-the-art CP methods.

Self-supervised learning for time-series representation aims to reduce reliance on labeled data while maintaining strong downstream performance, yet many existing approaches incur high computational costs or rely on assumptions that do not hold across diverse temporal dynamics. In this work, we introduce Divide and Contrast (Di-COT), an unsupervised framework that avoids data augmentation and multiple encoder passes by contrasting informative substructures within a window rather than individual timesteps. Di-COT stochastically partitions each window into a small number of overlapping sub-blocks per iteration, enabling efficient and meaningful contrast while mitigating false positives during temporal transitions. To further improve scalability, we adopt a contrastive objective whose computation depends on the batch size and the number of sub-blocks, making loss computation independent of sequence length. Extensive experiments on six large-scale real-world datasets, as well as the UCR and UEA benchmarks, demonstrate that Di-COT learns transferable representations while achieving state-of-the-art performance with substantially reduced training time.

Generative models that transport a simple source distribution to a complex data distribution—such as diffusion and flow-based models—are central to high‑fidelity data generation. Test-time guidance can further steer pretrained models toward user-specified high-reward regions without costly retraining. However, existing guidance methods face critical limitations: they struggle with non-differentiable rewards, fail to navigate complex landscapes, and often lack theoretical guarantees on generation performance. We propose {\it Source Parallel Tempering (SPT)}, a gradient‑free test‑time guidance framework that operates entirely in source space, leveraging its simpler geometry to avoid the complexities of the data manifold. SPT couples a local exploration kernel with parallel tempering, enabling efficient barrier crossing and robust discovery of high‑reward modes. Theoretically, we provide a new error bound linking training-time approximation error to test-time guidance performance.Empirically, SPT significantly improves over state-of-the-art methods on benchmark tasks in conditional image synthesis and dynamical system trajectory sampling.

While deep neural network-based long-term time series forecasting (LTSF) has become indispensable for critical infrastructures such as smart grids and IoT platforms, the deployment of these models as black-box APIs introduces severe security vulnerabilities that remain largely underexplored. In this paper, we propose TSFAdv, a query-efficient adversarial framework for LTSF models. The framework systematically analyzes model sensitivity to spectral perturbations in both magnitude and phase of the frequency domain. By embedding frequency-domain priors into Natural Evolution Strategies, we achieve sensitivity-guided gradient estimation that improves perturbation efficacy without violating practical query constraints. To overcome ambiguities inherent to point-wise regression metrics, we adopt a trajectory-level evaluation protocol based on Dynamic Time Warping (DTW) and Slope Misalignment Error (SME), enabling the capture of complex geometric and directional deviations. Extensive experiments across seven state-of-the-art architectures demonstrate that TSFAdv achieves substantial performance gains, with median DTW improvements of 38.78\% and median SME improvements of 26.47\% under 200-query budget. These findings reveal that existing defense mechanisms are ineffective against frequency-domain manipulation, underscoring an urgent necessity for robust LTSF models.

Time series modeling increasingly demands high-quality supervision, yet target observations remain scarce—exogenous inputs are broadly available, but target measurements are often unavailable due to cost, infrastructure, or accessibility constraints. Can models trained on observed locations reconstruct target time series where measurements have never been collected? We term this zero-shot time series reconstruction. A naive approach—directly mapping exogenous inputs to targets—can yield predictions at unobserved locations, but without target signals, such models fail to capture the intrinsic dynamics of the target variable, producing overly smooth outputs that underestimate extremes. This reveals systematic errors that call for explicit modeling and calibration. We propose ZeroDiff, which constructs an informed prior from exogenous variables alone, then learns to calibrate reconstruction errors through diffusion—training on observed locations and generalizing to unobserved ones. Experiments across diverse real-world datasets demonstrate significant improvements over existing approaches. Our code is available at https://github.com/YingdaFan/ZeroDiff-ICML2026.

Real-world time-series data often suffer from missing observations, hindering long-range temporal modeling. However, most existing imputation methods formulate imputation as conditional reconstruction over limited context, which restricts temporal information propagation and fails to explicitly model temporal evolution. To overcome this limitation, we propose the Conditional Temporal Inference Paradigm (CTIP), which formulates time-series imputation as conditional inference along temporal evolution. Under this paradigm, we introduce CBiT, which leverages a history compression mechanism to encode long-range history into a compact latent space for history-conditioned temporal imputation. In addition, we adopt a partitioned modeling strategy that distinguishes historical context and temporal imputation targets with only linear-time complexity. Extensive experiments on multiple public benchmarks show that CBiT improves imputation accuracy by reducing Masked MAE and Masked RMSE by 27.3% and 18.6%, respectively, across different missing rates.

Diffusion models have achieved remarkable success in generative modeling, yet their application to time series forecasting remains suboptimal. Existing approaches apply uniform Gaussian noise across all time steps, assuming all frequency components should be corrupted at the same rate. However, energy distribution across frequencies in time series is highly non-uniform: when uniform noise is added, high-frequency components are disproportionately overwhelmed while low-frequency trends remain inadequately diffused. We propose EADiff, an energy-adaptive diffusion framework operating in the wavelet domain to address this frequency-energy imbalance. Our key insight is that high-energy components require stronger perturbation while low-energy details need gentler corruption to preserve informative structures. We introduce a learnable modulation mechanism that automatically adjusts noise levels for each frequency band on a per-instance basis. Built upon this adaptive scheduler, we design a conditional diffusion framework where low-frequency trends serve as generation conditions, and noise-level-aware loss weighting naturally emphasizes different frequency components according to their signal characteristics. This cohesive design enables the model to respect the intrinsic multi-scale structure throughout both forward and reverse processes. Extensive experiments demonstrate that EADiff consistently outperforms existing diffusion-based and state-of-the-art deterministic methods.

Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving sample complexity on test tasks, many real-world applications, such as robotics and healthcare, impose safety constraints during testing. Constrained meta RL provides a promising framework for integrating safety into meta RL. An open question in constrained meta RL is how to ensure safety of the policy on the real-world test task, while reducing the sample complexity and thus, enabling faster learning of optimal policies. To address this gap, we propose an algorithm that refines policies learned during training, with provable safety and sample complexity guarantees for learning a near optimal policy on the test tasks. We further derive a matching lower bound, showing that this sample complexity is tight.

Many fields collect large-scale temporal data through repeated measurements (`trials’), where each trial is labeled with a set of metadata variables spanning several categories. For example, a trial in a neuroscience study may be linked to a value from category (a): task difficulty, and category (b): animal choice. A critical challenge in time-series analysis is to understand how these labels are encoded within the multi-trial observations, and disentangle the distinct effect of each label entry across categories. Here, we present MILCCI, a novel data-driven method that i) identifies the interpretable components underlying the data, ii) captures cross-trial variability, and iii) integrates label information to understand each category's representation within the data. MILCCI extends a sparse per-trial decomposition that leverages label similarities within each category to enable subtle, label-driven cross-trial adjustments in component compositions and to distinguish the contribution of each category. MILCCI also learns each component’s corresponding temporal trace, which evolves over time within each trial and varies flexibly across trials. We demonstrate MILCCI’s performance through both synthetic and real-world examples, including voting patterns, online page view trends, and neuronal recordings.

We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as "black boxes." Unlike existing benchmarks, TFRBench provides a protocol for evaluating the reasoning generated by forecasting systems--specifically their analysis of cross-channel dependencies, trends, and external events. To enable this, we propose a systematic multi-agent framework that utilizes an iterative verification loop to synthesize numerically grounded reasoning traces. Spanning ten datasets across five domains, our evaluation confirms that this reasoning is causally effective; useful for evaluation; and prompting LLMs with our generated traces significantly improves forecasting accuracy compared to direct numerical prediction (e.g., avg. $\sim40.2$% $\rightarrow$ $\sim56.6$%), validating the quality of our reasoning. Conversely, benchmarking experiments reveal that off-the-shelf LLMs consistently struggle with both reasoning (lower LLM-as-a-Judge scores) and numerical forecasting, frequently failing to capture domain-specific dynamics. TFRBench thus establishes a new standard for interpretable, reasoning-based evaluation in time-series forecasting. Our benchmark is available at: https://tfrbench.github.io

Many real-world systems exhibit both context- and time-dependent causal dynamics, where the dynamical system state also influences its context. For instance, soil moisture is driven by precipitation, yet also provides the context for heat-flux realization. We capture such dynamics in Structural Causal Models (SCMs) by introducing endogenous and time-dependent discrete context variables, also allowing for possibly lagged dependencies with the system variables. While context variables are discrete, they may also be proxies of continuous variables. The enabling assumptions for causal discovery of our model are either persistence of the context or sparsity of the context–system dependencies. We design two new PCMCI-based algorithms for causal discovery with endogenous context variables for time series and prove their soundness. A systematic evaluation on synthetic benchmarks and an application to a real-world land-atmosphere feedback problem demonstrate their effectiveness and applicability.