NeurIPS 2026 论文列表

Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that highlight influential regions but do not explain how evidence from different tissue regions is combined to produce a prediction. This limits interpretability, especially when decisions depend on interactions between tissue features. We introduce Symbolic explainable MIL (Symb-xMIL), a post-hoc explanation framework that quantifies how a MIL model’s behavior aligns with human-readable decision rules, expressed as logical relationships (e.g., AND, OR, NOT) between input features. These alignment scores reveal semantic patterns underlying the model’s predictions. We evaluate Symb-xMIL on synthetic and real-world histopathology datasets. On synthetic MIL data, Symb-xMIL reliably recovers ground-truth logical rules. In a clinical tumor detection task, the best-aligned rules uncover heterogeneous decision patterns and expose hidden model errors. On an HPV-prediction task on TCGA-HNSCC, a cohort of head and neck cancer, our framework refines patient survival stratification beyond HPV status with potential clinical relevance. Overall, Symb-xMIL extends MIL explainability beyond visual attribution toward structured, rule-based reasoning, enabling more transparent and semantically grounded interpretation of model predictions.

Neural networks that are trained on data arising from a physical system must somehow learn regularities induced by the underlying physical laws. In this setting, concepts from statistical physics provide powerful tools for analysing how physical laws influence the learning process. In this paper we explain how *susceptibilities* --- which measure the response of a neural network to perturbations of a parameter of the data distribution --- can be applied when learning from physical data. We show that such susceptibilities can identify the conditions under which specific input features are most informative for learning, guiding data selection, a prediction we validate experimentally. For distributions lacking a natural parameter, we propose introducing one via an arbitrary scalar function of the physical state, and demonstrate that susceptibilities track the emergence of specific capabilities (such as collision detection) during training.

We analyze support mismatch in language-model in-context prediction as a frozen-prior Bayes benchmark with finite discrete support. The goal is diagnostic rather than literal: we do not identify production LMs with exact Bayesian updating, but characterize a failure mode whose signatures can be checked in learned in-context predictors. Our main theorem gives the finite-sample predictor-risk bound $R_k^\pi \le C e^{-k\rho_{\min}} + 2\varepsilon_{\mathrm{approx}}^2$, so risk decomposes into an exponentially decaying transient and a nonvanishing support-mismatch floor under exponential-moment control of log-likelihood ratios. In scalar and aligned Gaussian location families, exact two-component analyses match the upper exponent up to a tight factor 2 and show a regime change at $\mu_2=3\mu_1$. Controlled learned-model experiments track the benchmark near crossover. Decoder-only LM diagnostics then test the benchmark signatures: restricted support creates a persistent high-error regime; restoring the missing support sharply lowers error; and modern size-matched distractor controls on Qwen and Llama show that adding a wrong same-cardinality candidate does not reproduce this gain. Multiple-choice, instruction-tuned, cross-family, calibration, null-control, and near-tie checks preserve the same diagnostic picture.

Secure LLM agents should take actions for authorized users in authorized environments. However, current agents' (e.g., OpenClaw) runtimes expose neither user nor environment authorization and existing agent security benchmarks similarly evaluate models without relevant authorization context. We propose SudoBench, a benchmark of 135 paired scenarios in a synthetic consulting universe with a static access control list, spanning user authorization (confused deputy), environment authorization (source-label indirect prompt injection), and both (scope-check indirect prompt injection). For each pair of scenarios, the authorization context is flipped such that an identical prompt should be appropriately complied with or refused. We score each pair as a joint pass requiring the model to produce the correct outcome on both paired scenarios. Across ten frontier closed- and open-weight LLMs, joint pass rate without authorization context sits below 16\% on every model. Adding user and environment authorization raises joint pass to as high as 67--73\%. Even with this authorization context, frontier models remain far from reliably handling contextual authorization, framing authorization context as an important research agenda for agent security.

Exemplar-Free Class-Incremental Learning (EFCIL) is a challenging continual learning paradigm where a model must learn new classes sequentially without access to old data, making it susceptible to catastrophic forgetting. The core difficulty lies in balancing stability (preserving old knowledge) and plasticity (acquiring new knowledge). We propose Subspace-Guided Continual Learning (SGCL), a novel method that tackles this dilemma from a geometric perspective. SGCL decomposes the feature space into two orthogonal subspaces: a ```stable subspace``` containing directions critical for previous tasks, and a ```plastic subspace``` where new knowledge can be learned with minimal interference. This decomposition is efficiently identified via the feature-space Hessian, where high-curvature eigendirections define the stable subspace. Building on this, SGCL introduces two synergistic components: 1) Subspace-Guided Regularization (SGR), which imposes curvature-weighted penalties on feature drifts within the stable subspace, and 2) Subspace-Guided Prototype Alignment (SGPA), which adaptively corrects the shift of old-class prototypes to recalibrate the classifier. Extensive experiments on standard benchmarks show that SGCL consistently achieves competitive or superior performance compared to existing state-of-the-art methods, offering a principled approach to mitigating forgetting through loss landscape analysis.

Missing modalities reduce observations to arbitrary subsets, challenging robust multimodal inference. Existing methods recover missing views or align cross-subset representations, implicitly equating feature completeness with decision accuracy—leaving subset-specific decision boundary variation structurally unaddressed. Empirical analysis reveals that misclassification patterns are highly subset-specific, stable across initializations, and concentrated near decision boundaries—a persistent boundary misalignment distinct from information attenuation, which we define as Subset-Conditioned Boundary Shift (SCBS). To address this, we propose Subset-Conditioned Boundary Compensation (SCBC): a modality-factorized violation memory accumulates historical records of subset-specific margin violations, and a subset-adaptive head converts them into targeted logit corrections at inference, with a direction-consistency loss enforcing alignment during training. We prove that these corrections, built entirely from forward-pass statistics without backpropagating through the correction path, satisfy the descent condition of the surrogate loss, to our knowledge the first such guarantee in incomplete multimodal learning. Across five benchmarks, SCBC achieves state-of-the-art-level performance, averaging a 3.4 Macro-F1 point gain under random missingness and peaking at 7.4 points on the IEMOCAP-4 {v, a} setting. Source code is available at https://anonymous.4open.science/r/SCBC_neurips-50B5.

We investigate the problem of uncertainty quantification in the mean estimation framework. Given an i.i.d. sample from a distribution with unknown mean $\mu$ and variance $\sigma^2$, we want to construct an estimator $\hat{\mu}_n$ and provide a computable and size-optimal upper bound for the error $|\hat{ \mu}_n - \mu|$. While estimators possessing strong deviation guarantees are well known, no data-dependent non-asymptotic upper bounds for their performance exist in general. We show that this gap can be bridged by introducing a parameter that characterizes the "effective sample size" available for uncertainty quantification. This parameter captures the difficulty of the problem, interpolating between "easy" cases where sub-Gaussian confidence intervals exist and "hard" cases where their construction is impossible. Using this characterization, we design confidence intervals of optimal length that are fully adaptive to the unknown variance. Numerical experiments confirm that our approach maintains nominal coverage even in asymmetric and heavy-tailed regimes where other existing methods fail.

Encoding classical data into quantum states is a central bottleneck in quantum machine learning: many widely used encodings are circuit-inefficient, requiring deep circuits and substantial quantum resources, which limits scalability on quantum hardware. In this work, we propose TNQE, a circuit-efficient quantum data encoding framework built on structured unitary tensor network (TN) representations. TNQE first represents each classical input via a TN decomposition and then compiles the resulting tensor cores into an encoding circuit through two complementary core-to-circuit strategies. To make this compilation trainable while respecting the unitary nature of quantum operations, we introduce a unitary-aware constraint that parameterizes TN cores as learnable block unitaries, enabling them to be directly optimized and directly encoded as quantum operators. The proposed TNQE framework enables explicit control over circuit depth and qubit resources, allowing the construction of shallow, resource-efficient circuits. Across a range of benchmarks, TNQE achieves encoding circuits as shallow as $0.04\times$ the depth of amplitude encoding, while naturally scaling to high-resolution images ($256 \times 256$) and demonstrating practical feasibility on real quantum hardware.

In joint multiuser decoding, a receiver recovers a set of messages from a single noisy aggregate of many simultaneous transmissions. Classical decoders rely on rule-based mechanisms such as successive interference cancellation, joint belief propagation, or list recovery, all of which become brittle or expensive as ambiguity increases. We propose CIDER, a learned multiuser decoder with masked-diffusion refinement steps. CIDER uses demixing to prevent duplicate-row collapse and uses parity-aware propagation to provide soft guidance from the code constraints. In higher-load regimes, we further improve reliability via a lightweight quality-guided remasking step that selectively re-decodes low-confidence sequences. On commonly used error correcting codes, CIDER matches or improves on FFT-accelerated joint belief propagation-style decoding in symbol error rate while running more than $6\times$ to over $100\times$ faster, with the speedup widening as the blocklength grows. Code is available at https://anonymous.4open.science/r/CIDER_2026/.

Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice generative quality. We bridge this gap by proposing Structured Coupling for Flow Matching (SCFM), a cooperative framework that augments flow matching with structured latent representation learning. By introducing structured latent variables and exogenous noise into the source, SCFM jointly learns a structured prior (via latent variable modeling) and a continuous transport map (via flow matching). It uses a shared time-dependent recognition network for both latent variable model variational inference and intermediate-time flow velocity estimation. This yields a structurally informed yet unconditional, simulation-free flow model, where the latent variable model can also assist flow sampling. Empirically, SCFM facilitates unsupervised latent representation learning for clustering, disentanglement and downstream tasks, while remaining competitive with flow matching in sample quality, showing that meaningful structure can be learned without sacrificing generative fidelity.

Modern scientific discovery systems can propose more mechanistic hypotheses than laboratories can test. We study the downstream selection problem: after upstream retrieval, extraction, expert modeling, or curation has fixed a finite locally factorized posterior over admissible mechanisms, when does the posterior evidence justify acting on one structural hypothesis rather than its rivals? For a query $A\rightsquigarrow B$, we define *structural support* as the posterior mass of mechanisms in which $A$ reaches $B$ by a directed path. This is not a retrieval rank, direct-edge score, or MAP graph decision: support can be distributed across many compatible mechanisms. Our main result is a local certificate for this global support quantity. For path cutoff $L$ and locality radius $m$, truncated support is a convex combination of exact boundary-conditioned local supports. Optimizing over locally admissible blanket states gives a boundary range $[\\ell_{L,m},u_{L,m}]$, and a certified tail bound $\bar r_L$ accounts for longer witnesses: $p_{AB}\in[\\ell_{L,m},\min\{1,u_{L,m}+\bar r_L\}]$. For coupled rivals, the same boundary-conditioned calculations yield a joint feasible set rather than only independent coordinate intervals. We convert these certificates into resolve-or-abstain decisions: an action is resolved only when it wins throughout the certified support set. Under valid certificates, a resolved action is the unique strict utility maximizer inside the declared fixed model, action set, and utilities; otherwise, the solver abstains and reports whether boundary, tail, computation, evidence, or outer-model uncertainty blocks resolution. On controlled and biologically scaffolded finite-posterior records, the implementation has zero endpoint containment misses and zero false fixed-model resolutions. In a coupled-rival diagnostic, joint feasible sets resolve $14/24$ cases versus $6/24$ for scalar boxes, with no false commitments.

Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language models to manifest their own internal structures as well. While interpretability research has investigated how models compute representations mechanistically through attention patterns and Sparse AutoEncoders, the organization of the resulting representations is overlooked. To address this gap, we introduce StructLens, a framework to analyze representations through a holistic structural view. StructLens constructs maximum spanning trees based on the semantic representations in residual streams, inspired by tree representation in dependency parsing, and provides summaries of token relationships in representation space. We analyze how contiguous tokens are also nearby in representation space and find that middle layers show the strongest local-span organization. Moreover, analysis of pre-training checkpoints reveals that smaller local units become detectable earlier in pre-training, and larger units later. Our findings demonstrate that StructLens provides insights into how models organize token representations across layers and training.

Stroke-based rendering is often optimized as a pixel-level reconstruction task. This over-reliance on global error reduction not only degrades strokes into fragmented curves due to a lack of structured planning, but also allows locally defective primitives to be concealed by overlapping layers. To address these issues, we introduce a model-guided framework for stroke-audited rendering. Our framework uses Quadratic Bezier Splatting to analytically model continuous curved strokes with efficient differentiable alpha compositing. Built on this renderer, a feedforward multi-scale stroke decoder provides a structural initialization with learned stroke-scale allocation, while test-time stroke optimization supplies the reconstruction capacity needed for high-fidelity refinement. We further propose a single-stroke audit mechanism that explicitly evaluates local stroke quality, preventing defective primitives from surviving optimization through layer-wise compensation. Experiments demonstrate our approach achieves highly coherent layouts, improving PSNR by up to 20\% and yielding a 58.8$\times$ renderer speedup with a 16\% more compact representation compared to representative SBR baselines.

Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as $\pi_{0.5}$ operate under a single-frame paradigm, limiting their ability to retain past observations and develop precise spatial perception. In this paper, we propose StreamPI, a streaming multimodal temporal modeling framework that equips single-frame VLA with temporal reasoning capability without introducing any additional parameters. One core design is instruction-anchored temporal modeling. It treats each (visual observation, language instruction) pair as an atomic temporal unit: bidirectional attention within each pair enables cross-modal fusion, while causal attention across pairs preserves autoregressive streaming inference. This ensures the language instruction serves as a persistent semantic anchor throughout task execution. To bridge the gap between synchronous training and asynchronous real-robot deployment, we introduce a random-interval streaming training strategy: a proper inter-frame interval (e.g., every 3 frames) enables faster and smoother action execution. Beyond this, randomizing the interval further improves robustness to frame-timing perturbations, supporting asynchronous deployment in practice. Furthermore, by leveraging the length extrapolation capability of the LLM backbone, StreamPI seamlessly inherits pretrained single-frame weights and supports flexible single-frame and multi-frame inference. Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms $\pi_{0.5}$ across diverse tasks.

Sampling from complex, unnormalized probability densities is a fundamental challenge in Bayesian inference and probabilistic modeling. While Markov chain Monte Carlo (MCMC) methods provide asymptotic guarantees, they often suffer from slow mixing and high computational costs due to fixed or manually tuned trajectory lengths. In this work, we propose a novel framework that treats trajectory termination as a learnable component of the sampling dynamics. By framing MCMC within the theory of non-acyclic Generative Flow Networks (GFlowNets), we train state-dependent neural classifiers to decide when a trajectory has reached a high-density region and should terminate. We theoretically establish the connection between optimal classifiers and the target density via detailed balance conditions and introduce a multilevel training scheme to facilitate exploration in complex geometries. Experimental results across various benchmark densities demonstrate that our approach significantly reduces average trajectory lengths while improving mode coverage and mixing compared to standard MCMC baselines.

This paper argues that the NeurIPS community should prioritize AI-for-Quantum (AI4Q) over Quantum Machine Learning (QML) on classical data, and should review the two directions by different evidentiary standards. We argue that QML on classical data has not earned high priority because its leading advantage claims rely on strong input assumptions, face trainability and noise barriers, and still lacks persuasive wall-clock wins on the standard benchmarks. By contrast, AI4Q has already produced concrete gains in decoding, compilation, neural-state representation, tomography and readout, and error mitigation. We make the evidentiary standard explicit through falsification criteria and concrete review-process recommendations.

Stochastic reconfiguration (SR) is the standard optimizer for neural quantum states (NQS), but modern NQS often have far more parameters than Monte Carlo samples. We show that in this regime the diagonal shift is more than a numerical stabilizer. It acts as a statistical filter for finite-sample generalization. At a fixed wave function, SR is ridge regression from tangent features to the centered local energy. Its residual is the expressivity gap, the part of imaginary-time evolution outside the current tangent space. This gap is orthogonal to the tangent space in population, but finite batches make it act as noise that SR can overfit. The shift therefore balances shrinkage of useful update directions against variance from fitting sampled residuals. Exact $4\times4$ $J_1$-$J_2$ experiments separate two effects of overparameterization. Larger tangent spaces help when they reduce the expressivity gap, but they can hurt when they overfit a fixed gap. In a $100$-site transverse-field Ising family trained with a foundation NQS, validation risk is U-shaped in the shift while variance decreases, matching the noisy-ridge model. This view leads to multi-shift SR (MS-SR), which averages independent ridge solves at data-adaptive shifts to form a richer, lower-variance spectral filter. MS-SR lowers validation risk and stays closer to the ideal tangent-space imaginary-time update compared to other competitive NQS optimizers.

Conformal prediction offers a distribution-free coverage guarantee, making it especially attractive for clinical applications. Standard conformal prediction, however, provides such guarantees only at the population level, and its prediction sets can exhibit coverage disparities across clinically important subgroups. A natural remedy is to calibrate within predefined groups. However, this can require access to sensitive subgroup attributes and is prone to a worst-group bottleneck: protecting the most difficult subgroup can inflate prediction sets for all, increasing cognitive burden on decision makers. To this end, we propose Stochastic Grouping Conformal Prediction (SGCP), a conformal framework for subgroup-reliable uncertainty quantification. It learns a stochastic grouping map that allows each sample to draw calibration information from others with similar calibration behavior, yielding a local score law that boosts reliability across subpopulations. We prove that SGCP retains the standard coverage guarantee. Experiments on synthetic and real-world benchmarks show that it consistently reduces subgroup coverage gaps while achieving smaller or comparable prediction set sizes relative to existing baselines.

We study stochastic simple bilevel optimization with smooth, possibly nonconvex upper- and lower-level objectives accessed only through stochastic gradient oracles. A key challenge is that the dual multiplier induced by the lower-level constraint may become unbounded near lower-level stationary points, invalidating bounded-dual analyses and destabilizing stochastic gradient estimates. To address this, we propose \emph{Stochastic Dynamic Barrier Perturbed Gradient} (SDBPG), a single-loop method that adaptively perturbs the dual formulation to regularize this degeneracy. The perturbation stabilizes the multiplier and yields controlled bias and variance even near the lower-level stationarity region. Under a mild rare-visit assumption, SDBPG finds an $(\epsilon_f,\epsilon_g)$-stationary point in $\mathcal{O}(\max\{\epsilon_f^{-2},\epsilon_g^{-2}\})$ iterations, with sample gradient complexities $\mathcal{O}(\epsilon^{-4})$ and $\mathcal{O}(\epsilon^{-6})$ for the upper- and lower-level objectives where $\epsilon=\max(\epsilon_f,\epsilon_g)$. We further develop PR-SDBPG, a penalty-regularized variant that eliminates the rare-visit assumption, and VR-PR-SDBPG, which improves the resulting sample complexities entirely through variance reduction. To our knowledge, these are the first explicit $(\epsilon_f,\epsilon_g)$-stationarity guarantees for stochastic nonconvex-nonconvex simple bilevel optimization.