NeurIPS 2026 论文列表

Long-term time-series forecasting (LTSF) underpins applications such as energy-load prediction and traffic-flow forecasting, yet model performance often deteriorates as the horizon extends. In particular, errors accumulate with lead time and systematically amplify toward the end of the predicted sequence, a phenomenon known as tail deterioration. We posit that this instability is driven by weakly constrained fusion of cross-temporal and cross-scale context: aggressive mixing can propagate noise and early-stage bias into distant horizons, ultimately degrading tail accuracy. To address this issue, we propose TailFix, a controllable cross-scale mixing framework for long-horizon forecasting. TailFix selectively gates interactions among multi-scale representations, derives scale-level correction terms from contextual summaries, and injects them via gated residual connections to suppress error diffusion and improve long-horizon stability. We further incorporate adaptive channel enhancement and a lightweight tail-correction module to explicitly refine the error-prone tail region. Finally, we introduce the Tail Amplification Factor (TAF) to quantify tail error amplification relative to the early portion of the sequence. Across diverse benchmarks, TailFix consistently mitigates tail error amplification and improves performance on multiple long-horizon forecasting tasks.

Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regressing novel views from neural networks without reconstructing 3D geometry, while Test-Time Training (TTT) layers can be introduced to save computation, but sacrifice quality. We propose **T**est-**T**ime **B**aking (**TTB**), a strategy that learns to bake global scene information from cross-view attention into a lightweight MLP, enabling fast and high-fidelity novel-view decoding. The first key is to repurpose the fast-weight MLP of TTT to learn the cross-view attention mapping explicitly from its input-output pairs, rather than replacing attention entirely, achieving the same rendering efficiency as TTT while delivering substantially higher quality. The second key addresses a modality misalignment between context prefilling and novel-view rendering: we disentangle context tokens into camera-only context rendering tokens to serve as TTB input, and context ground-truth tokens with image content to serve as the TTB mapping target, ensuring the baked MLPs are relieved of the modality generalization challenge between context and novel-view processing. Our method achieves up to **23x** rendering speedup with quality on par with the state-of-the-art across several benchmarks.

Long-term time-series forecasting requires temporal dependency modeling that remains stable and generalizable under temporal distribution shifts. However, real-world time series are often noisy and non-stationary, making deep learning models prone to fitting incidental temporal interactions in the training data. A key question is whether there exist temporal relationship structures that recur across different temporal positions and variables. We analyze temporal relationship matrices on commonly used time-series datasets and find that samples from different temporal positions and different variables exhibit shared dominant temporal relationship structures. This indicates that temporal relationship structures contain patterns that recur stably across samples and variables. To learn such shared structures, we propose Temporal Structure Network (TStruct), a simple yet effective network for directly learning shared and generalizable temporal dependencies. Specifically, TStruct directly parameterizes a set of shared temporal dependency matrices and generates normalized combination weights using dynamic sample information and static variable priors. These weights represent a soft allocation of each sample-variable pair over shared temporal dependency structures, enabling the model to generate adaptive temporal dependency matrices under shared structural constraints, rather than fitting incidental interactions in a fully unconstrained manner. Notably, this simple structure-aware design consistently outperforms several strong baselines across all datasets, achieving superior accuracy while maintaining high computational efficiency. Our code is available at \url{https://anonymous.4open.science/r/TStruct-NeurIPS2026-1173}.

Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently, large language models (LLMs) have emerged as a promising paradigm for TS quality assessment via pairwise comparison and per-dimension evaluation. However, existing approaches rely on manually predefined quality dimensions and purely text-based reasoning, leaving it unknown whether LLMs can identify truly relevant quality dimensions or perform grounded and quantitative quality comparisons. To investigate this, we construct TSQBench, a dedicated benchmark for evaluating LLMs’ capabilities in TS quality assessment, which measures two progressive capabilities: (i) understanding and identifying relevant quality dimensions, and (ii) performing quality comparison under specific dimensions. Our analysis reveals that both open-source and proprietary LLMs consistently struggle with identifying critical quality dimensions and conducting precise, evidence-grounded reasoning over quality characteristics. To address these limitations, we propose TSQAgent, a novel agentic reasoning framework for dedicated TS data quality rating, comprising three collaborative roles: Perceiver for focused dimension selection, Inspector for dimension-wise quantitative analysis, and Adjudicator that aggregates and refines the final judgment. In particular, we introduce an agentic reasoning strategy that instills the ability to identify and prioritize the most relevant quality dimensions, and further propose an agent workflow equipped with external analytical tools to enable precise quantitative comparisons over selected dimensions. Experiments on both the proposed benchmark and eleven real-world datasets demonstrate that our framework not only substantially improves LLMs’ capabilities in quality understanding and quantitative comparison but also effectively translates these improvements into better quality-aware data selection, leading to enhanced downstream performance and data efficiency.

Time-series segmentation, studied as either \emph{Change Point Detection} (CPD) or \emph{State Detection} (SD), underpins a broad range of monitoring and diagnostic applications. However, the field suffers from a persistent divide between the statistical community (focusing on CPD) and the machine learning and data mining communities (focusing on SD). Consequently, the literature remains fragmented: evaluations typically cover narrow methodological families, datasets are often small or homogeneous, and CPD and SD are rarely evaluated together. We address these gaps with \texttt{TSB-SEG}, a unified benchmark comprising $592$ univariate and multivariate time series across $8$ heterogeneous domains and surveying $27$ algorithms spanning five decades of progress. To ensure a fair comparison, we introduce a two-pool design: a scalable \emph{main pool} of sub-quadratic detectors used for the aggregate ranking, and an \emph{extended-scope pool} for computationally intensive specialized methods. All methods are unified under tsseg, an open-source library to ensure full reproducibility. Our systematic evaluation yields three insights: (a) no single detector dominates across domains, and per-dataset hyperparameter tuning remains decisive for performance, (b) CPD accuracy is a strong proxy for SD accuracy, and (c) data characteristics should guide method selection. We provide actionable guidance based on data properties, error tolerances, and tuning budgets, identify impactful hyperparameters, and characterize algorithm robustness to these choices.

Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models. Yet, current approaches primarily focus on forecasting, while real-world time series are often irregularly and partially observed, requiring models that can jointly forecast, impute missing values, and handle degraded sampling conditions. To address these challenges, we introduce TS-ICL, a novel probabilistic In-Context Learning encoder-regressor Transformer that unifies forecasting and imputation. TS-ICL formulates time series tasks as timestamp-aligned regression and naturally incorporates covariates by training on synthetic dependency structures generated from a novel causal data prior. Empirically, TS-ICL achieves a new state-of-the-art in imputation, while remaining competitive with leading forecasting foundation models across both univariate and covariate-aware benchmarks. It shows particularly strong performance in forecasting with partially observed look-back windows. *Code page*: https://anonymous.4open.science/r/tsicl-D3F1/.

Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step $\Delta$ a learned function of the input. However, in doing so, $\Delta$ ceases to represent a physical sampling interval, limiting its irregular time series modeling capability. Continuous-time SSMs, such as S5, preserve the physical meaning of $\Delta$ and handle irregular timestamps natively, but their dynamics remain linear time-invariant (LTI), limiting per-token expressivity. We propose \textbf{TIDES}, a selective SSM variant that reconciles selective and continuous architectures by moving input-dependence off the step size and onto the diagonal state matrix. As a result, $\Delta$ retains its physical meaning, tied to the state discretization, allowing the model to handle irregular timestamps natively without sacrificing the per-token expressivity that makes selective SSMs effective. We show this on a novel \emph{Fading Flash} experimental benchmark, a compact controlled diagnostic for sequence models that jointly tests input-dependence and extrapolation to out-of-distribution $\Delta$ values, and isolates the distinct failure modes of current state-of-the-art architectures that TIDES avoids by construction. On large-scale benchmarks, TIDES sets the new state-of-the-art average rank on UEA time-series classification and the Physiome-ODE regression benchmark.

In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepancy an unreliable indicator of abnormal system behavior. Since latent-space scoring can mitigate this limitation, we reframe one-class MTSAD as current-point system-state compatibility estimation and propose **TENET**, the **T**ime-point **E**ncoding **Net**work for Multivariate Time Series Anomaly Detection. We define the current-point system state as a latent representation of the target time point, constructed from variable-level temporal context in the input window. TENET constructs this state through a temporal layer that retrieves window context relative to the current point, encodes time with current-point-centered embeddings, and adaptively mixes the retrieved context with the current representation. With this design, TENET treats the input window not as the object to reconstruct, forecast, summarize, or score, but as context for constructing a latent representation evaluated with a fixed standard-normal negative log-likelihood score. Across benchmark datasets, TENET achieves state-of-the-art performance. Additional experiments further show that TENET remains effective under alternative one-class objectives and outperforms substitutions based on generic sequence encoders, suggesting that its advantage comes from decision-aligned representation construction rather than from a specialized scoring rule. These results indicate that one-class MTSAD can be strong when the latent representation is designed around the current time point.

Time series anomaly detection (TSAD) remains challenging not only because anomaly labels are scarce, but also because temporal anomalies are highly context-dependent. Existing methods often rely on unsupervised or surrogate objectives, producing anomaly scores indirectly rather than learning explicit normal--anomalous distinctions. We propose Counterfactual Pairing with Anomaly Semantics (CAPS), a supervision-recovery framework for TSAD. CAPS formulates temporal anomalies as mechanism-induced effects on normal temporal evolution and recovers matched supervision without target-domain anomaly labels. It learns transferable anomaly semantics from simulated normal--anomalous pairs, disentangles them from normal temporal structure, and organizes them into family-wise modes. Instead of directly using simulated anomalies as target positives, CAPS instantiates the learned semantics as residual-form anomaly effects on target-domain reference trajectories via residual MoE generation. The resulting matched counterparts provide supervision-aligned signals for boundary-oriented detector learning. Experiments on nine benchmark datasets show that CAPS outperforms unsupervised and injection-based baselines, is competitive with supervised-reference baselines, and provides interpretable evidence through anomaly-effect generation and expert association.

We study strongly adaptive regret for Online Convex Optimization (OCO) with time-varying movement costs, a setting that evaluates a learner's performance over arbitrary sub-intervals. This framework captures complex sequential decision-making problems where both the environment and the cost of switching decisions fluctuate over time. We propose a novel algorithm which, for any interval $[a,b] \subseteq [T]$, achieves a data-dependent regret bound of $ \widetilde{\mathcal{O}}\left( \sqrt{(D^2+DP_{[a,b]})\sum_{t \in [a,b]}(\\|g_t\\|^2+\lambda_t\\|g_t\\|)} \right) $, where $D$ is the diameter of the decision domain, $P_{[a,b]}$ is the path length of the comparator sequence over $[a,b]$, $g_t$ is the gradient of the loss, and $\lambda_t$ is the movement-cost coefficient at round $t$. Key to our approach is a novel reduction to sleeping experts with movement costs, a previously unexplored variant that is of independent interest. As a result of this development, we further establish the first strongly-adaptive guarantees under delayed feedback. Our approach also naturally extends to OCO with time-varying memory, where we obtain strongly-adaptive guarantees which improve the best-known bounds.

This paper initiates the study of a stochastic approximation approach with the Fully Stochastic Primal Dual Algorithm (FSPDA) framework for decentralized optimization on random and time varying topologies. Our framework relies on a novel observation that randomnesses in time varying topology can be incorporated into a stochastic equality constrained optimization formulation. We derived two new algorithms supporting sparsified communication on time varying topologies --- FSPDA-SA allows agents to execute multiple local gradient steps to accelerate convergence, and FSPDA-STORM further incorporates variance reduction to improve sample complexity. For problems with smooth (possibly non-convex) objective function, within $T$ iterations, FSPDA-SA (resp. FSPDA-STORM) finds an $\mathcal{O}( 1/\sqrt{T} )$-stationary (resp. $\mathcal{O}( 1/T^{2/3} )$) solution. The latter shows the first near-optimal convergence rate over time varying topology.

Time series forecasting aims to predict future values from historical observations and auxiliary features. We propose \textbf{SteerCast}, a retrieval-based latent steering method that improves decoder-only forecaster at inference time, without updating its parameters. SteerCast constructs a database from the training set by storing a representation of each history window together with a \emph{steering vector} computed in the forecaster's latent space, defined as the difference between representations induced by the ground-truth continuation and by the model's own prediction. At test time, SteerCast retrieves nearest neighbors for a query history, aggregates their steering vectors, and injects the resulting signal into the forecaster's hidden states at every step of autoregressive generation, guiding predictions toward trajectories consistent with similar training cases. Experiments across diverse multivariate benchmarks and multiple horizons show that SteerCast consistently improves forecasting accuracy over the fine-tuned backbone and retrieval-based baselines, while requiring no additional training beyond the original fine-tuning and using only the training set as a retrieval corpus.

Resolution invariance is a critical capability for scientific machine learning methods (SciML), however, the ability to sample at any resolution does not guarantee stable emulation at all resolutions. This important distinction underpins one of scientific machine learning's greatest potential: the ability to efficiently emulate complicated and computationally expensive systems on inexpensive coarse grids. Stable numerical solvers are computationally expensive as they attempt to resolve small scales that receive and dissipate spectral energy. Learned coarse-grid forecasters remove the dissipative channel, allowing unresolved frequencies to re-emerge as grid-scale noise (aliasing). We explore stable resolution invariant emulation through physically principled control over entropy dynamics to reinforce the dissipative mechanism within the Neural Discrete Equilibrium (NeurDE) method. Entropically-stabilized NeurDE produces stable long-time rollouts for thousands of forecasting steps on large Reynolds number turbulent flows (Re=50,000) with very coarse grids ($\mathbb{R}^{16\times16}$). Entropically-stabilized NeurDE demonstrates extreme stability at coarse resolutions, outperforming the data-generating stabilized numerical method: a much more challenging baseline than SciML surrogates.

Deep learning has emerged as a powerful paradigm for constructing nonlinear asset pricing factor models. However, temporal distribution shifts such as bull-bear transitions and industry rotations undermine the generalization of models trained under the i.i.d. assumption. As a result, existing models tend to exploit environment-specific correlations that are highly predictive in-sample but unstable across market regimes. To address this challenge, we propose $\textit{\textbf{CASH}}$, a causality-inspired asset pricing factor framework designed to learn invariant and minimally sufficient representations under temporal distribution shifts. CASH formulates an information-theoretic adversarial learning objective that systematically discards transient market noise by optimizing against an adversary designed to exploit spurious correlations, thereby distilling invariant factor-return relationships. The resulting invariant representation is then integrated into a conditional factor pricing model via a dynamic factor exposure network. Experiments on real-world stock datasets across multiple markets demonstrate that CASH consistently outperforms state-of-the-art baselines in out-of-sample return prediction and exhibits superior robustness under pronounced temporal regime shifts.

Looped Transformers --- which repeatedly apply a shared transformer block --- are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong length generalization beyond the length of training sequences, this behavior is brittle, yielding high out-of-distribution (OOD) variance, even across well-performing in-distribution solutions. We trace this variance to the spurious correlation in simple algorithmic tasks between sequence length and number of loops. Introducing stochasticity into the number of loops during training sharply reduces OOD variance and stabilizes predictions across inference-time loop counts. To improve upon heuristic randomization schemes, we further analyze RL-Halting as a learned stochastic schedule and find that it generally improves the accuracy--stability trade-off. Across binary addition, Dyck-1, Unique Set, and Copy, learned stochastic stopping often improves this trade-off but can also stabilize a suboptimal computation. Our work suggests that “when to stop” should be treated as a training-time design choice, not merely an inference-time computation-allocation rule.

AI-generated image detectors often generalize poorly to unseen generators because the classifier latches onto generator-specific feature directions that are predictive only on the training set. We show that simply projecting away generator-discriminative LDA directions fails: these directions also carry genuine real-vs-fake signal, so post-hoc erasure removes evidence along with shortcuts. We introduce StaR, a training-time regularizer that scores each LDA direction by leave-one-generator-out stability and penalizes the classifier only on unstable directions; stable directions are left available for classification. On ResNet-50, StaR reduces the across-seed standard deviation of the four-OOD average AUC by 24x relative to ERM (F-significant on every OOD) while preserving in-distribution-like performance; on CLIP ViT-L/14, StaR improves the four-OOD average AUC by 1.7 points over matched CLIP-ERM and 4.5 over EFFORT, with the largest gains on platform-shift benchmarks. Mechanistic analyses show that StaR rotates the classifier away from unstable generator directions while amplifying generator-discriminative structure in the features---a rotational, not erasive, effect that post-hoc projection cannot reproduce. We additionally find that the conventional ``argmax in-domain validation'' epoch-selection rule is sub-optimal: a deployable ``stop at first in-domain 0.99'' rule beats it by sim0.7 AUC points on average.

Most time-series anomaly detectors ask whether an observation can be predicted or reconstructed. We ask a different question: can a detector’s own spiking dynamics become anomaly evidence? We study this question for periodic and quasi-periodic time series and propose SPIRE, a phase-conditioned spiking anomaly detector. SPIRE uses period-aware current formation to expose phase-aligned cross-period residuals to leaky integrate-and-fire neurons. We refer to this conversion as eventification: after residual injection, recurrence violations induce abnormal bursts, silences, or phase-shifted spike trains. SPIRE then constructs phase-conditioned normal templates of spike states and scores deviations in residual energy, firing-rate patterns, and burst/silence statistics, instead of relying solely on output-space prediction or reconstruction errors. This separates the operational protocol, including causal current-step detection, one-step prediction, and non-causal reconstruction, from the source of anomaly evidence, namely output errors, spike dynamics, or both. On TSB-AD-U and TSB-AD-M, SPIRE establishes new best VUS-PR among neural time-series anomaly detectors. Spike-native scores remain competitive without reconstruction error, hybrid scoring consistently improves error-only scoring, and replacing LIF neurons with continuous activations in matched ANN counterparts reduces detection performance under the same period-aware architecture. Periodicity-stratified analyses and spike-state visualizations further show that the gains are strongest when phase recurrence is reliable, supporting the proposed spike-as-detector mechanism. These results suggest that phase-conditioned spiking dynamics can serve as a first-class anomaly detection signal for periodic time series, rather than merely an efficient computational substrate.

Spiking Neural Networks (SNNs) offer a distinctive paradigm for temporal modeling through their intrinsic membrane potential dynamics. However, existing SNN-based forecasting methods focus exclusively on temporal processing, lacking mechanisms to capture spatial dependencies among variables. To bridge this gap, we propose SpikeSTAG, a neuromorphic spatiotemporal architecture that integrates graph-based spatial reasoning into spike-driven temporal computation. Central to our approach is the Dendritic Graph Module, which reinterprets spectral graph convolutions as biological dendritic integration -- coupling multi-scale spatial aggregation with the temporal dynamics of spiking neurons within a single computational unit. To adaptively fuse the resulting spatial and temporal representations, we further introduce a Dual-Stream Integration Module that employs competitive gating and coincidence-based amplification, selectively enhancing consistent spatiotemporal patterns while suppressing conflicting noise. Extensive experiments demonstrate that SpikeSTAG establishes a new state-of-the-art among SNN-based models and surpasses representative ANN baselines, while reducing theoretical energy consumption by approximately 33.3\% compared to Transformer architectures.

Time series, spatial data, and images are natural applications of Neural Processes. However, when such data exhibit strong periodicity and quasi-periodicity, existing methods often suffer from underfitting and generalise poorly beyond the training distribution. In this work, we propose Spectral Transformer Neural Processes (STNPs), a frequency-aware extension of Transformer Neural Processes (TNPs). STNPs introduce a Spectral Aggregator that estimates an empirical context spectrum, compresses it into a spectral mixture, samples task-adaptive spectral features, and concatenates them with time-domain embeddings, thereby injecting a spectral-mixture-kernel bias into TNPs. This design reshapes the similarity geometry, allowing inputs that are distant in Euclidean space to remain close in an induced periodic manifold while enhancing time--frequency interactions. Extensive experiments on synthetic regression tasks, real-world time-series datasets, and an image dataset demonstrate that STNPs consistently improve predictive performance over existing baselines, extending Neural Processes beyond translation equivariance toward effective modelling of periodicity and quasi-periodicity.