NeurIPS 2026 Papers

Average-reward reinforcement learning requires estimating the gain and the bias, which is defined only up to an additive constant. This makes direct distributional analogues ill-posed on the real line. We introduce a quotient-space formulation in which state-indexed bias laws are identified up to a common translation, together with a categorical parameterization that respects this symmetry. On this quotient-categorical space, we define a projected average-reward distributional operator and show that it is well-defined, non-expansive in a coordinate Cram\'er metric, and admits fixed points. We then study sampled recursions whose mean-field maps are asynchronous relaxations of this operator. In an idealized centered-reward setting, a one-state temporal-difference update enjoys almost sure convergence together with finite-iteration residual bounds under both i.i.d. and Markovian sampling. When the gain is unknown, we augment the recursion with an online gain estimator, and prove non-expansiveness and Markovian convergence of the resulting coupled scheme. Finally, we show that synchronous exact updates are gain-independent at the quotient-law level, isolating a structural contrast between ideal quotient distributions and practical fixed-grid categorical representations.

As language models are increasingly deployed in long-context and streaming workflows, deciding when to stop context processing is central to inference efficiency. While recent research has shown that a subset of attention heads encodes sufficiency signals, these markers are typically detected via static, task-agnostic global features. In this paper, we demonstrate that stop signals are inherently query-relevant and introduce \textsc{QueryStop}, an attention-aggregation method that systematically identifies query-focused attention heads whose hidden features effectively align with the input query. Driven primarily by query-focused heads, this tailored ensemble yields high-fidelity representations that significantly improve sufficiency prediction. Across four benchmarks on eleven datasets, our method improves sufficiency stop prediction by 3.52\% F1 on average. Under comparable token reduction, it raises Sufficiency Reach Rate (SRR), our proposed stopping-adequacy metric, from 87.12\% to 94.73\% and yields a 7.09\% average gain in downstream task accuracy over the prior baseline. Collectively, these results show that \textsc{QueryStop} effectively eliminates unnecessary context processing while simultaneously improving downstream answer quality.

Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by minimizing the number of score evaluations, yet the information-theoretic limits of such acceleration remain unclear. In this work, we establish the first score query lower bounds for diffusion sampling. We prove that for $d$-dimensional distributions, given access to score estimates with polynomial accuracy $\varepsilon=d^{-O(1)}$ (in any $L^p$ sense), any sampling algorithm requires $\widetilde{\Omega}(\sqrt{d})$ adaptive score queries. In particular, our proof shows that any sampler must search over $\widetilde{\Omega}(\sqrt{d})$ distinct noise levels, providing a formal explanation for why multiscale noise schedules are necessary in practice.

We study the query complexity of approximating the top eigenvector of an asymmetric matrix in the matrix-vector product model. Our main result gives a gap-dependent lower bound for this problem in the adaptive query setting. Prior lower bounds for symmetric matrices already imply weaker hardness guarantees for the more general asymmetric problem, whereas our result yields a sharper dependence on the eigen-gap in the asymmetric case. In the inverse polynomial accuracy regime, this lower bound matches the benchmark upper bound of the power method up to lower-order factors. Our proof is based on an asymmetric spiked random matrix that serves as a hard instance. The key random-matrix ingredient is an analysis of the spike model, including both its asymptotic eigen-gap and the alignment between its top eigenvector and the planted spike. Building on an information-theoretic framework for query lower bounds, we then obtain the stated hardness result.

Decomposing surface electromyography (EMG) into the spike trains of individual motor neurons is a long-standing inverse problem and a key step toward motor-neuron-driven neural interfaces such as prosthetics and exoskeletons. The standard approach, independent component analysis (ICA) of the multichannel signal, assumes that the mixing from neurons to electrodes is stationary in time. This assumption fails during movement, when volume-conductor deformation makes the mixing time-varying, and current decomposition algorithms are correspondingly restricted to isometric contractions. We introduce a quasi-linear ICA formulation in which a static linear separator is preceded by a learned, low-rank, time-varying invertible transformation. The separator is trained with an independence loss on the uncompensated projection, and the transformation with a stationarity loss on the recovered source. Gradients are not shared between the two, so the source-extraction step reduces to classical linear ICA and inherits its identifiability guarantee, while non-stationary distortion is absorbed by the transformation. The closed-form inverse of the transformation enables per-spike subtraction with a time-varying template during sequential peel-off. On a public benchmark of dynamic high-density EMG with ground-truth spike trains, the method outperforms five adaptive ICA baselines at every recall threshold, recovering more units at a higher accuracy.

Quantile-based distributional reinforcement learning methods learn return distributions through sampled quantile regression, but their bootstrapped target quantiles may induce distorted or degenerate distribution estimates. We propose Robust Quantile-based Implicit Quantile Networks (RQIQN), a lightweight Wasserstein distributionally robust enhancement boosted from a quantile estimation perspective. We first reinterpret a snapshot of IQN loss as a collection of local empirical quantile estimation problems over sampled current fractions. We then robustify each local slot with a Wasserstein distributionally robust quantile estimation formulation, yielding a closed-form, fraction-dependent correction to the Bellman target. This correction directly mitigates distributional degeneration: its median-antisymmetry preserves the risk-neutral quantile average, while its monotonicity enlarges upper--lower quantile gaps and counteracts collapsed distributional spread. RQIQN thus regularizes quantile geometry without changing the underlying value objective or requiring additional sample-set reconstruction. Finally, we empirically show that the proposed RQIQN outperforms other existing quantile-based distributional reinforcement learning algorithms in risk-sensitive navigation and Atari games.

Analyzing complex data across a wide range of scientific fields often requires identifying central or typical elements, distinguishing them from atypical ones, and constructing central or "normal" regions at prespecified levels of centrality. We introduce centrality scores (C-scores) based on distance profiles for random objects taking values in general metric spaces. The proposed C-scores are defined through weighted optimal transport of distance profiles and provide a unified framework for constructing central or "normal" regions for complex data. We show that, for Euclidean data, the limiting behavior of the proposed C-scores is asymptotically equivalent to the underlying probability density function. The practical merits of the proposed method are illustrated using gene expression data, distributions of recorded temperatures, handwritten digit recognition, and taxi trip records. These examples demonstrate the effectiveness of C-scores in identifying central and peripheral elements and in yielding meaningful insights for non-Euclidean and high-dimensional data.

Series decomposition aims to separate long-term trajectories and periodic patterns in time series, thereby improving the specificity and interpretability of forecasting models. However, mainstream approaches usually equate this functional separation with an operational split between a smoothed baseline and fluctuating residuals. One line of methods approximates the trend via low-pass smoothing, which assumes long-term trajectories to be purely smooth and may misassign nonlinear evolution, stage-wise transitions, and structural fluctuations to the residual. The other relies on heuristic nonlinear decompositions to capture complex dynamics, but is sensitive to noise and hyperparameters, leading to unstable and mixed component boundaries. To address this issue, we propose a forecasting framework, QWaveNet. It employs a quantum convolutional neural network to learn Dynamic Evolution, a long-term structural representation beyond low-pass smoothing priors, which preserves nonlinear evolution, stage-wise transitions, and structural fluctuations more coherently, while its complementary Evolutionary Residual captures localized variations and periodic dynamics. Guided by these complementary components, QWaveNet further performs adaptive multi-scale decomposition and reconstruction to support forecasting. Experiments on multiple benchmark datasets demonstrate the effectiveness of QWaveNet.

Robots deployed for active search must decide where to sense while uncertainty, teammates, and remaining mobility change online. In active search, each waypoint decision also commits the robot to a route through the map, making efficient localization a long-horizon problem over belief, topology, robot state, and traversal budget rather than a sequence of independent next-best sensing decisions. We present QUEST, a shared-belief graph neural framework for multi-agent active search with noisy sensors, a shared posterior, and finite decision and path budgets. Rather than learning a myopic policy that values only the next route, QUEST trains Q-functions whose targets include both reward collected along the executed path and the downstream value of the resulting belief, robot positions, team coverage, and remaining budget. The same formulation supports single robots, homogeneous robot teams, and heterogeneous UAV--UGV teams with different sensors and motion budgets. During execution, each robot acts independently using the shared posterior and knowledge of teammates' positions and search plans. Across simulated search environments, QUEST reaches $0.913$ F-score with four UGVs, versus $0.853$ for the strongest learned baseline, and keeps above $0.90$ F-score under communication outage and two mid-mission robot failures without retraining. On out-of-distribution UAV--UGV teams, it improves early F-score ($0.759$ vs.\ $0.728$) while using $10\%$ less path length and $12\%$ less duplicate coverage than the same baseline. The same policies transfer across map shape, variable team size, communication outage, and mid-mission robot failure, and show sensing-mode adaptation after UGV failure.

Reliable quantum control in the presence of decoherence requires policies that combat the effect of environmental noise on the controlled dynamics. Open quantum systems under continuous monitoring generate classical measurement records whose drift depends on the noise experienced by the system; the records of two evolutions sharing the same decoherence channels differ only in this drift, so Girsanov's theorem yields a closed-form, differentiable estimator of the KL divergence between their trajectory distributions. We instantiate this estimator with two physically motivated reference measures, yielding two regularizers that both drive the system toward states where the effects of decoherence are minimal: the *Wiener KL* (KL_W), which is empirically more effective under certain conditions on the noise model, and the *drift-variance regularizer* (R_DV), which works for all noise models. Both are qualitatively distinct from existing penalties on control fluence or smoothness: they penalize the observable consequences of control on the decoherence channels rather than the control amplitude itself. The regularizers outperform unregularized gradient-based and reinforcement-learning baselines across a range of open quantum systems — including single- and multi-qubit benchmarks and a multi-qubit chain calibrated to a published snapshot of the IBM Kingston processor — along several axes of evaluation: final-state fidelity, robustness to mismatch in the assumed noise model (gains grow from +17 pp at training noise to +27 pp under 2.5× noise mismatch), and occupation of forbidden states. The regularizers reduce infidelity by up to 50%, with ~16% gains on the calibrated IBM Kingston chain. Our code can be found at https://anonymous.4open.science/r/QMaxCal-6E71/.

3D Gaussian Splatting (3DGS) enables high-quality real-time novel-view synthesis, but practical scenes often contain millions of Gaussians, making compression essential for deployment on limited hardware. Existing reduction methods are effective but mostly heuristic: they provide no multiplicative approximation guarantee for the rendered objective, and thus rely heavily on costly post-pruning finetuning to recover quality. We ask a basic question: can a 3DGS scene be provably replaced by a much smaller weighted subset (coreset) while preserving the objective of interest? We first show that, in the unrestricted setting, no non-trivial multiplicative 3DGS coreset exists. We then show that multiplicative guarantees are not impossible, but resolution-dependent. For a prescribed rendering resolution, such as representative views or grids of views/rays, we provide the first weighted coreset construction theorem for 3DGS. The construction samples Gaussians by sensitivity: provable importance scores measuring each Gaussian’s role in the full-scene objective. Finally, under explicit validity and log-transmittance stability assumptions, we turn this objective guarantee into a rendering guarantee. Empirically, our method is strongest where deployment needs it most: aggressive compression with no or minimal recovery compute. In prune-only and very short finetuning regimes, it achieves state-of-the-art performance, showing that principled importance estimation can be both theoretically meaningful and practically useful.

Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audited models, reported performance can be inflated and cross-model comparisons become unreliable. A broad line of training-data detection work designs scores to quantify how strongly a model memorizes a given data point, but these score-based methods lack theoretical guarantees. Recent conformal approaches provide provable false-identification control for a single model; however, applying them separately to each model can produce model-specific benchmarks, undermining fair comparison across models. In this work, we formalize multi-model benchmark decontamination as a joint selection problem and propose Joint Envelope Conformal Selection (JECS), a conformal procedure that enables global contamination rate (GCR) control under stated assumptions. Specifically, JECS computes per-model conformal p-values, aggregates them by the per-item maximum, and reconstructs a conservative envelope of the max-p null distribution from right-tail observations above a data-driven threshold. By applying the adaptive Benjamini-Hochberg (BH) procedure to the envelope-rescaled values, we select a benchmark with provable GCR control. Extensive experiments across various models and benchmarks demonstrate that JECS achieves higher power than the max-p baseline while consistently maintaining the target GCR control.

Visible-Infrared Lifelong Person Re-Identification (VI-LReID) requires a model to sequentially acquire cross-modal person retrieval capabilities across sequentially arriving tasks while retaining performance on previously learned ones.Existing methods face two fundamental problems.First, new-task gradient updates disrupt each instance's assignment ranking over historical class prototypes, which is the direct mechanism behind past-task retrieval performance degradation. At the same time, the feature manifold inevitably undergoes global drift as a necessary byproduct of new-task adaptation. Effective anti-forgetting should target the detrimental ranking disruption while permitting this necessary drift.Second, visible RGB and thermal infrared (TIR) imaging capture fundamentally different physical cues: texture-and-color reflectance versus heat radiation contours. This causes the two modalities to form inherently inconsistent inter-class similarity structures that conventional cross-modal supervision cannot resolve, manifesting as highly asymmetric forgetting across modalities under shared-backbone continual training.We propose S-PTC (Stage-wise Prototype Topology Consistency), which preserves each instance's relative distribution over the frozen historical prototype set, protecting assignment rankings while leaving the overall feature manifold free to evolve for new-task adaptation.We further propose CM-PTC (Cross-Modal Prototype Topology Consistency), which aligns the inter-class topology matrices of RGB and IR prototypes, mitigating the structural inconsistency rooted in their imaging physics.Both modules require no stored exemplars.Extensive experiments on the VI-LReID benchmark verify the effectiveness and superiority of our approach against state-of-the-art methods.

On-policy distillation (OPD) improves language-model post-training by letting the student learn from its own sampled trajectories under teacher supervision, aligning the training process with inference-time behavior. However, the rollout policy in OPD is usually treated as fixed: each round samples directly from the current student. We show that this choice can create a compounding teacher-student mismatch, because it requires the teacher to provide effective supervision on whichever trajectories the student samples, including ones less reachable by the teacher itself. On such trajectories, teacher supervision can become noisy or even misleading, leading to undesirable student patterns such as repetition. Moreover, since the updated student in turn defines the rollout policy of subsequent rounds, these patterns persist and potentially amplify over training. This failure mode suggests that improving OPD requires treating the rollout policy itself as an optimization target, rather than only modifying the distillation objective. We propose *Mixture Proposal On-Policy Distillation* (MPOPD), which derives a student-anchored, teacher-guided rollout distribution from a local trust-region objective based on relative teacher support. The resulting target is a geometric mixture of the student and teacher policies, and we introduce a proposal policy that approximates this mixture, enabling rollout generation in a single forward pass. Experiments on 16 math, knowledge, and medical reasoning benchmarks show consistent gains over OPD and recent variants. On math reasoning, our method improves average accuracy by 6.91 over OPD on Qwen3-4B-Base while reducing average generation length by 41\%, suggesting that rollout policy design provides an effective way to improve OPD.

Language-model agents increasingly emit uncertainty signals throughout a trajectory, but existing agentic UQ evaluations often conflate ranking usefulness with probabilistic truthfulness. AUROC, AUPRC, risk-coverage, Trajectory ECE, and scalarized trajectory scores evaluate discrimination, binwise calibration, or collapsed summaries, but do not strictly elicit the full prefix-conditioned success-probability trace $q_t=\mathbb{P}^{\pi}(Y{=}1\mid\mathcal{H}_t)$. Building on prequential proper scoring, we introduce the Trajectory Proper Score (TPS), a predictor-agnostic family of strictly proper trajectory-level scoring rules for any per-step uncertainty signal calibrated into a probability of eventual success. We prove that TPS strictly elicits the success-probability process under complete observation, within the chosen score family and weight schedule. We extend the construction to administratively censored trajectories by projecting the complete-data score onto the observable stopped prefix, yielding an exact $q_Z$-weighted reduced score and a tractable approximation when $q_Z$ is unestimated. We further show that common trajectory evaluators target weaker objects than the full prefix-conditioned probability process: Trajectory ECE is resolution-blind, while scalarized Trajectory Brier elicits only the collapsed scalar, not the full trace. Experiments on StrategyQA, Tau2-Bench, HotpotQA, and WebShop show that these theoretical distinctions are operationally visible: probability recalibration can substantially change TPS while leaving rank metrics nearly unchanged, and the tractable censored approximation can change the verdict relative to complete-only evaluation.

Accident anticipation aims to recognize anomalous driving cues before a crash while avoiding false alarms during normal driving. Existing approaches typically formulate this task as binary classification, focusing on whether an accident will occur rather than when it will occur. We propose PRE-ACT, a framework that models accident risk as a continuously evolving signal that increases as the crash approaches. By explicitly enforcing temporal ordering and distance-to-accident awareness, our method progressively raises risk while suppressing premature alarms, leading to significant improvements on MM-AU subsets and Nexar. We further introduce a Separation Score to evaluate the global behavior of predicted risk curves beyond local temporal windows. Code and visualizations are available.

Transformer architectures serve as the backbone for most modern Large Language Models, therefore their pretraining stability and convergence speed are of central concern. Motivated by the logical dependency of sequentially stacked layers, we propose Progressive Residual Warmup (ProRes) for language model pretraining. ProRes implements an "early layer learns first" philosophy by multiplying each layer's residual with a scalar that gradually warms up from 0 to 1, with deeper layers taking longer warmup steps. In this way, deeper layers wait for early layers to settle into a more stable regime before contributing to learning. We demonstrate the effectiveness of ProRes through pretraining experiments across various model scales, as well as normalization and initialization schemes. Comprehensive analysis shows that ProRes not only stabilizes pretraining but also introduces a unique optimization trajectory, leading to faster convergence, stronger generalization and better downstream performance. Our code is available in supplementary materials.

Time-series carry structure simultaneously at multiple scales (fine-grained variation, mid-range motifs, and global properties) and downstream tasks operate at correspondingly different scales. Most existing self-supervised learning approaches supervise representations globally via instance-level contrastive losses and limited temporal neighborhood supervision, but do not explicitly exploit the structural hierarchy. We propose a learning framework that explicitly enforces a structural hierarchy across three scales independently: a local objective for token continuity, a mid-range objective for window-level motifs, and a global objective for sequence-level agreement. Realizing this framework requires the backbone to expose a representation at each scale; we introduce \textbf{Progressive Memory Transformer} (PMT), which augments a transformer with writable, window-aligned memory that exposes the mid-range scale alongside the token and sequence-level representations conventional transformers already provide. Across seven UCR/UEA/UCI classification benchmarks, a cue-retention probe, and two forecasting benchmarks, PMT learns representations that probe well at the global, mid-range, and local scales---strong low-label classification (1--5\% labels), competitive forecasting performance across multiple horizons, and quantitative and qualitative evidence that memory states capture mid-range motifs.

Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose *fuzzy-function programming*: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input *problem solver* into a *tool builder*: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline.