NeurIPS 2026 Papers

Although many OOD detection methods have been proposed, no clear winner can be identified as winners are benchmark-specific. One problem with evaluating OOD detectors is the imprecise definition of the "out" distribution, as many commonly used OOD datasets designed to test for 'semantic shift' contain a substantial proportion of 'covariate shift' samples. Moreover, recent work finds that, on carefully crafted benchmarks focused on semantic shift, modern OOD detectors yield little improvement over the baseline MSP. We analyzed a vast number of post-hoc OOD detectors on these benchmarks. We found that they consistently misclassify a common, substantial subset of samples across modern CNN and ViT architectures. We showed that failures across all OOD detectors on this benchmark are primarily due to learned feature representations: we observe that feature extractors map many semantically distant OOD samples closer to ImageNet classes than some in-distribution samples. This misalignment raises safety concerns about DNNs operating in open-set recognition scenarios. We publish a new benchmark, along with a reproducible construction protocol, that focuses on shared hard examples drawn from semantically distinct datasets, including NINCO and ImageNet-OoD. Our new benchmark can reveal fundamental security gaps in current DNNs, as they fail to reliably distinguish semantically distant OOD samples from in-distribution samples.

Evaluating large language models across many benchmarks is expensive, yet many benchmarks are highly correlated. We formalize the selection of a small, informative subset as submodular maximization under a multivariate Gaussian model. Entropy (log-determinant covariance) and mutual information between selected and remaining benchmarks arise as natural objectives. Both are submodular; entropy selection coincides with pivoted Cholesky and has spectral residual bounds, while mutual information is non-monotone in general but empirically monotone for small subsets, so we optimize it greedily. Experiments on three matrices from ten public leaderboards show that mutual information selection outperforms entropy for imputation at small subsets.

When labeling is expensive or datasets exceed computing capacity, selecting an informative subset of data is a practical necessity. Identifying such subdata is a classical NP-hard problem due to its inherent discreteness. While many subdata selection methods have been proposed for parametric models, two fundamental challenges remain: first, how can we accurately assess the statistical efficiency of selected subdata relative to the theoretical optimum? Second, given $N$ data points and a subdata size $n$, which $n$ points should be selected to achieve high statistical efficiency? We address both challenges within a unified framework. We develop a new information-based subdata selection methodology grounded in optimal approximate design theory, yielding subdata that approaches the theoretical optimum. Our algorithm is general, accommodates arbitrary $N$ and $n$, supports multiple optimality criteria, and is accompanied by a convergence proof. Crucially, our framework provides, for the first time, tight lower and upper bounds on the statistical efficiency of subdata selected by any method, enabling accurate and rigorous benchmarking across the literature. This benchmarking capability reveals the true performance landscape of existing methods and shows that many of them have been operating substantially below their theoretical potential. The subdata produced by our methodology is highly efficient and outperforms all existing methods.

Neural network verifiers aim to provide formal guarantees on model behavior, but existing verification benchmarks are fundamentally limited by their lack of ground-truth labels. As a result, verifier evaluation relies on indirect heuristics, which prevents exact scoring and systematic studies of verifier failure modes. We address this gap by introducing a reusable framework for generating verification instances whose ground-truth robustness labels are known a priori through analytic construction. Our framework led to the discovery of multiple numeric tolerance concerns and implementation bugs in popular verifiers, highlighting the need for ground-truth labels. Additionally, to systematically study verifier failure modes, we introduce the verification Difficulty Profile, a collection of estimable quantities capturing distinct sources of instance hardness. Using our framework and these profiles, we evaluate five state-of-the-art verifiers and show that different instances stress distinct aspects of the verification pipeline. We show that these results can aid the future development of verifiers as they provide actionable targets for improving numerical reliability, relaxation quality, and search behavior. Our code is publicly available: https://github.com/NeurIPSAnon12345/VeriStressGT.git.

When algorithmic predictors inform resource allocation in high-stakes domains such as healthcare, these predictors must account for strategic manipulation of input features. The typical solution is to redesign the predictor itself to explicitly account for strategic interactions. In practice, however, decision makers are often constrained to adjusting coarser levers within existing prediction pipelines. For example, healthcare organizations often select which features to exclude based on perceived manipulability, while using standard regularization procedures to shrink the coefficients of retained features. In this work, we initiate a formal study of strategic classification through *feature selection* and its interaction with *ridge regularization*. Our main finding is that excluding features based on manipulability alone is generally suboptimal. We provide a fine-grained characterization of the performance of a feature subset under optimal regularization, yielding new insights for policy design. Motivated by this characterization, we develop a practical algorithm for jointly choosing the feature set and the level of ridge regularization. Through a real-world case study on a healthcare payments benchmark, we illustrate how our algorithm can guide the design of coarse policy levers in practice. Our results provide a principled, practical framework for mitigating the effects of strategic behavior in algorithmic decision-making systems.

Public benchmarks play a significant role in steering LLM development, as market incentives drive model developers to optimize for leaderboard performance. However, fundamental information limitations mean that evaluators are only able to cover a subset of socially relevant capabilities with their evaluation tasks. On the other hand, model developers often have additional private benchmarks that are unavailable to evaluators. The resulting information asymmetry opens the door to strategic task specialization that can lead to suboptimal social welfare. We propose randomized evaluation mechanisms (effectively private benchmarks) as a way to incentivize model developers to train to cover a broader set of socially relevant tasks, including those unknown to the evaluator. We formalize this as a dynamic game with information asymmetry between an evaluator and a model developer. We prove that randomized evaluation aligns incentives to the developer’s prior belief over possible evaluated tasks, and is socially optimal when that belief matches society, but information leakage degrades this over rounds. However, if the evaluator can continually update their known task set, alignment can be asymptotically recovered. We illustrate a variance–leakage–correction tradeoff in semisynthetic experiment with a latent factor structure over MMLU-Pro.

Determinant point processes (DPPs) have recently emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, coresets and other parsimonious representations of large-scale datasets. While basic theoretical foundations and promising empirical performance have been demonstrated, there are two main challenges for current proposals for DPP-based coresets or minibatches. The first is the need for families of DPPs with certain key variance reduction properties, usually constructed in a continuous setting, of which there are few known examples. The second is the need for an ad-hoc construction of a discrete DPP defined on a given dataset, that inherits such variance reduction. In this work, we contribute to the programme of establishing DPPs as a subsampling toolbox for ML by advancing on these two fronts. First, we propose new DPPs on the Euclidean space based on wavelets, with provably better accuracy guarantees than the best known rates. Second, we introduce a general method to convert such continuous DPPs, which are more amenable to proving analytical statements, into discrete kernels, which are pertinent for subsampling tasks such as minibatch and coreset constructions. This conversion mechanism simultaneously preserves the desired variance decay and reveals a low-rank decomposition of the discrete kernel, which makes sampling the corresponding DPP computationally inexpensive. En route, we enlarge the class of ML tasks amenable to improvements via DPP-based minibatches and coresets to include highly non-smooth objective functions, with arbitrarily low regularity, and rate guarantees that adapt explicitly to this regularity.

Agent simulation aims to model the future behavior of interacting agents, but existing benchmarks have largely focused on structured domains such as autonomous driving. Adversarial and partially observable settings remain less explored, despite their importance for modeling strategic multi-agent behavior. To address this gap, we introduce StarCraft Motion, a large-scale dataset for agent simulation built from human StarCraft~II replays. Our processing pipeline converts raw replays into standardized simulation scenarios by extracting continuous unit trajectories, deriving command-based unit-level intent labels, and aligning game states with player-specific fog-of-war observations. This enables direct study of behavior, intent, and opponent responses under competitive partial observability. As an initial study, we evaluate autoregressive simulation methods on StarCraft Motion and introduce HMART, a hierarchical baseline that extends SMART with learnable player-level query aggregation for efficient global-context modeling in large-agent-count scenarios. Experiments show that global context improves observer-unit simulation and intent prediction, while closed-loop fine-tuning further improves rollout quality. However, accurately capturing intent initiation and transitions remains difficult. We also find that opponent modeling from partial observations is substantially more challenging, and that additional global information can be misleading when it does not match the opponent's perspective. These results highlight StarCraft Motion as a useful dataset for studying scalable agent simulation in adversarial, partially observable environments.

Federated Learning (FL) is a promising paradigm for distributed machine learning. However, FL often suffers from degraded generalization performance due to the inconsistency between local and global optimization objectives and client-side overfitting. In this paper, we provide a global-update stability analysis framework as an analytical tool to study generalization error and derive the stability bounds of mainstream FL optimization algorithms under non-convex settings. Our analyses reveal how the number of global update steps, data heterogeneity, and update rules influence their stability. We observe that momentum-based FL acceleration methods do not improve stability. To address this issue, we propose FedSEMA, a new FL algorithm that couples global momentum with a gradient-difference corrected Nesterov Accelerated Gradient (NAG) scheme and a hybrid proximal term to enhance stability. This design ensures updates follow a globally consistent descent direction while retaining the benefits of acceleration. Theoretical analysis shows that FedSEMA achieves an improved stability upper bound on non-i.i.d. datasets in the non-convex settings. Extensive experiments on real-world datasets demonstrate that FedSEMA significantly outperforms multiple baseline methods under standard FL settings, achieving faster convergence and state-of-the-art performance.

Online platforms connect users with relevant products and services using ads. A key challenge is that a user's search query often leaves their true intent ambiguous. Typically, platforms passively predict relevance based on available signals and in some cases offer query refinements. The shift from traditional search to conversational AI provides a new approach. When a user's query is ambiguous, a Large Language Model (LLM) can proactively offer several clarifying follow-up prompts. In this paper we consider the following: what if some of these follow-up prompts can be ``sponsored,'' i.e., selected for their advertising potential. How should these ``suggestion slots'' be allocated? And, how does this new mechanism interact with the traditional ad auction that might follow? This paper introduces a formal model for designing and analyzing these interactive platforms. We use this model to investigate a critical engineering choice: whether it is better to jointly optimize the user interaction and the final ad auction, or to decouple them into separate mechanisms for the suggestion slots and another for the subsequent ad slot. We show that the VCG mechanism can be adopted to jointly optimize the sponsored suggestion and the ads that follow; while this mechanism is more complex, it achieves outcomes that are efficient and truthful. On the other hand, we prove that the simple-to-implement modular approach suffers from strategic inefficiency: its Price of Anarchy is unbounded, for various natural choices for the two mechanisms. While we show that this inefficiency can be mitigated through revenue redistribution, we argue that the resulting mechanism sacrifices the practical simplicity that motivated the modular design in the first place.

We introduce Split-RL, a reinforcement learning (RL) algorithm based on decision trees. It uses guidance labels to explicitly partition the state-space and isolate localized conflicting signals. RL policies are often trained by mixing contradictory feedback that is localized in space and time. For example, a robot may prioritize speed in open areas versus precision in tight gaps. These regions are often easily detectable from sensor data or a human operator. Standard neural networks (NNs) lack the structural mechanism to isolate these signals. While Gradient Boosting Trees (GBT) provides the inductive bias to explicitly partition the state-space, standard tree-fitting procedures fit only aggregated gradients, merging contradictory updates before they reach the leaves. Split-RL leverages this bias to integrate guidance labels into tree construction, routing these updates into disjoint regions of the state-space to prevent signal interference during training. Such labels can arise from simple heuristics, sensor-derived events, or existing rule-based systems, allowing Split-RL to incorporate rule-derived structure while retaining a learned policy. We theoretically show how early gradient aggregation loses objective-specific information and characterize when the Split-RL score isolates conflicting updates. Finally, we evaluate Split-RL on constrained tasks and offline imitation learning from mixed-quality datasets. Across constrained domains with spatial, rare-event, and temporal conflicts, Split-RL consistently outperforms existing methods by achieving low-cost, feasible solutions while maintaining competitive rewards. In offline settings, Split-RL localizes the tradeoff between imitation and policy improvement, outperforming other methods and achieving near-expert performance across varying dataset sizes.

Novel view synthesis methods such as 3D Gaussian Splatting degrade under sparse-view settings, suffering from an inability to extrapolate beyond observed regions. To enable high fidelity reconstruction and rendering from sparse views, inpainting of sparsely observed areas and completion of occluded regions is required. Unlike existing approaches that perform these tasks using 2D inpainting diffusion models or geometric-only 3D completion models, we propose a fully 3D scene completion framework, called InvisiSplat, that performs geometry and appearance completion directly in 3D. Our method consists of a Gaussian Splat VAE which learns a sparse point cloud latent space that predicts Gaussian Splat parameters from the latents, as well as a two-step flow model that learns to generate samples conditioned on the point cloud latents, different from other approaches that use tokens without 3D coordinates. Our flow model utilizes alternating local 3D attention and global attention, which balances the needs for precise local geometry and large-scale spatial context. Across several datasets, we demonstrate that our method produces 33% - 82% higher fidelity 3D geometry over prior work while attaining competitive performance on appearance metrics when compared to existing approaches.

E(3)-equivariant networks are promising for 3D atomistic system modeling, yet their scalability is limited by the $O(L^6)$ complexity of the Clebsch-Gordan Tensor Product (CGTP). The recently proposed Gaunt Tensor Product (GTP) reduces the complexity but is unable to capture the antisymmetric paths, resulting in incomplete expressivity. In this work, we present SpinGT, an approach to overcome the GTP incompleteness by generalizing from scalar functions to Spin-Weighted Spherical Harmonics (SWSH). By relying on the algebraic properties of SWSH, SpinGTP recovers the missing antisymmetric interactions while maintaining the asymptotic efficiency of GTP. It also allows for a more expressive equivariant basis that naturally accounts for the parity-odd components of tensor products. We evaluate SpinGTP across diverse benchmarks, including Tetris, 3BPA, SPICE-MACE-OFF, and OC20. Our results show that SpinGTP achieves accuracies comparable to full CGTP. Notably, by explicitly capturing antisymmetric paths, SpinGTP exhibits superior performance in tasks involving chiral materials and non-centrosymmetric geometries. This work provides a scalable, complete, and mathematically rigorous path toward high-order equivariance in large-scale 3D atomistic system simulations.

Spiking Neural Networks (SNNs) promise energy-efficient inference, but adapting large pre-trained SNNs to new tasks is expensive because BPTT memory and runtime scale with the number of simulation steps $T$. We observe that weights in pre-trained SNNs are strongly concentrated near zero, and under thresholded dynamics many such synapses are functionally silent. Based on this, we propose \textbf{Spike-SFT}, a two-stage adaptation framework. Stage 1 (\textbf{Selective Parameter Enhancement}, SPE) fine-tunes only a small-magnitude subset via masked updates with low-rank regularization, progressive re-selection, and sparse-gradient storage, reducing memory while maintaining competitive accuracy. Stage 2 (\textbf{PickIt}) fuses multiple SPE-adapted models by alignment and interference-aware delta merging with spike-statistics calibration, yielding a single merged model with zero inference-time overhead. Across several SNN backbones and benchmarks, Spike-SFT offers a favorable accuracy--cost trade-off, improving fine-tuning efficiency (time/memory) while retaining strong accuracy, and enabling zero-overhead weight-space fusion via PickIt.

Spiking Neural Networks (SNNs) offer a promising energy-efficient alternative to Artificial Neural Networks (ANNs) through event-driven, multiplication-free computation. However, when applied to downstream tasks such as Neural Radiance Fields (NeRF), SNNs suffer from significant information loss, resulting in a noticeable performance gap. In this paper, we present \textit{Spik-NeRF v2} to advance SNN-based neural rendering. We propose the $\pm$I-LIF spiking neuron, which extends I-LIF to support signed integer values during training, thereby mitigating information loss. During inference, it is converted to ternary spikes $\{-1, 0, 1\}$, preserving event-driven properties with addition-only operations. Furthermore, we introduce a re-parameterization technique that transforms a trained I-LIF-based Spik-NeRF with $t$ timesteps into an equivalent $\pm$I-LIF-based model with $t/2$ timesteps. This enables faster inference while preserving rendering quality, overcoming the suboptimal performance of directly trained $\pm$I-LIF models with reduced timesteps. Extensive experiments on synthetic and realistic datasets demonstrate that Spik-NeRF v2 surpasses existing SNN-based NeRF methods and achieves rendering quality comparable to ANN-based approaches.

Post-hoc image explanations usually reveal *where* a model looks through spatial heatmaps, or *which channels* matter through global channel scores. This separation is limiting for multi-spectral data, where channel relevance is often spatially localized and physically meaningful. We introduce **Spectral-Spatial Interpretation (SSI)**, a full-grid attribution method over position-channel players (g, c). For each spatial position, SSI fixes the observed surrounding context, defines a conditional game over the channels at that position, and applies the Shapley value to this local game. The result is a full spectral-spatial attribution matrix rather than a single heatmap or a global channel ranking. SSI has a clear local semantics: it satisfies Shapley fairness within each position, and its channel aggregation exactly recovers the position-level contextual contrast obtained by replacing that entire position with the baseline. We also distinguish SSI from context-averaged Owen-style hierarchical accounting, which respects the same position-channel grouping but averages over external spatial coalitions. On HLS Burn Scar, SSI outperforms an MC-Owen estimator across retained attribution metrics while using only about 6% of its evaluation budget. Across CUB-200, EuroSAT, and HLS Burn Scar under both per-channel mean and zero baselines, SSI achieves the best joint deletion and insertion AUC over dense, flat, and rank-1 baselines, yields the strongest spectral hit rates and channel deletion, and leads spatial localization on both annotated datasets.

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.

In recent years, open-source efforts like Senorita-2M have propelled video editing toward natural language instruction. However, current publicly available datasets predominantly focus on local editing or style transfer, which largely preserve the original scene structure and are easier to scale. In contrast, *Background Replacement*, a task central to creative applications such as film production and advertising, requires synthesizing entirely new, temporally consistent scenes while maintaining accurate foreground-background interactions, making large-scale data generation significantly more challenging. Consequently, this complex task remains largely underexplored due to a scarcity of high-quality training data. This gap is evident in poorly performing state-of-the-art models, *e.g.,* Kiwi-Edit, because the primary open-source dataset that contains this task, *i.e.,* OpenVE-3M, frequently produces static, unnatural backgrounds. In this paper, we trace this quality degradation to *a lack of precise background guidance* during data synthesis. Accordingly, we design a scalable pipeline that generates foreground and background guidance in a decoupled manner with strict quality filtering. Building on this pipeline, we introduce *Sparkle*, a dataset of ~140K video pairs spanning five common background-change themes, alongside *Sparkle-Bench*, the largest evaluation benchmark tailored for background replacement to date. Experiments demonstrate that our dataset and the model trained on it achieve substantially better performance than all existing baselines on both OpenVE-Bench and Sparkle-Bench. Our proposed dataset, benchmark, and model are fully open-sourced at https://showlab.github.io/Sparkle/.

Large language models (LLMs) increasingly answer queries by citing web sources, but existing evaluations emphasize the final answer rather than evidence quality. We introduce SourceBench, a benchmark for measuring the quality of cited web sources across 100 real-world queries spanning informational, factual, argumentative, social, and shopping intents. SourceBench uses an eight-metric framework covering content quality (content relevance, factual accuracy, objectivity) and page-level signals (e.g., freshness, authority/accountability, clarity), and includes a human-labeled dataset with a calibrated LLM-based evaluator that matches expert judgments closely. We evaluate eight LLMs, Google Search, and three AI search tools over 3996 cited sources using SourceBench and conduct further experiments to understand the evaluation results. Overall, our work reveals four key new insights that can guide future research in the direction of GenAI and web search.