NeurIPS 2026 Papers

AI progress is increasingly tracked through evaluations, such as AI benchmarks, yet small perturbations in evaluation pipelines can produce unstable scores and model rankings. We recast benchmark reliability as a measurement problem and formalize it as a signal-to-noise ratio derived from a crossed random-effects decomposition. This framework yields a direct mapping between variance components and expected rank stability, linking theoretical reliability to observable leaderboard concordance. Modern AI benchmarks operate in a high-dimensional regime with many items and relatively few evaluated models, where classical item-level reliability measures are ill-posed. We define a lower bound for benchmark item-level reliability classically, and we further introduce a tractable proxy, $\lambda^\bigstar_6$, that preserves the variance structure underlying reliability without modifying the estimand through sparsity or dimensionality reduction. Across diverse benchmarks, we show that selecting items via $\lambda^\bigstar_6$ produces smaller subsets that achieve higher ranking reliability than random subsampling at fixed evaluation budgets. Finally, we analyze reliability under positive distribution shift--as often observed in the current AI ecosystem--by partitioning models into lower- and higher-performing cohorts. We show that reliability is population-dependent and frequently declines as between-model variance shifts among stronger systems. Our results establish a principled framework for diagnosing and improving benchmark reliability and demonstrate that ranking stability is neither intrinsic nor static, but a measurable and optimizable property of the benchmark–population pairing.

Stochastic bilevel optimization (SBO) has become a standard framework for hyperparameter learning, data reweighting, representation learning, and data-mixture optimization in deep learning. Existing exact single-loop SBO methods and memory-efficient surrogate SBO methods either create severe memory pressure for large lower-level neural networks or lack competitive convergence guarantees under standard assumptions. In this paper, we propose BROS, a memory-efficient single-loop SBO method with the same convergence rate order as exact single-loop SBO methods. BROS performs lower and auxiliary updates in randomized subspaces with a Rademacher bi-probe correction that recovers an unbiased Hessian-action estimator. We prove that BROS preserves the $\mathcal O(\varepsilon^{-2})$ sample complexity of MA-SOBA for finding an $\varepsilon$-stationary point under only standard assumptions. Experiments on hyper-data cleaning, data-mixture learning, hyper-representation learning, and ViT sample reweighting show that BROS reduces peak memory by up to 44.9% while closely matching full-space baseline performance.

Backpropagation imposes fundamental constraints on training neural networks. It requires the retention of all forward activations until the corresponding backward pass completes, thereby preventing pipelined execution across layers. This work introduces Backpropagation-Free Local Antithetic Node Perturbation (BLANP), a fully local training framework that eliminates gradient propagation across layer boundaries while requiring no negative samples. Each layer updates its parameters from locally available signals through a zeroth-order antithetic perturbation estimator. To stabilize learning, the estimator is evaluated against a frozen exponential moving average critic, decoupling backbone updates from the concurrently evolving local classifiers. The antithetic perturbation formulation cancels even-order bias terms in the gradient estimate, yielding a first-order accurate update from two forward passes alone. A companion variant, BLANP-Exact, replaces the perturbation estimator with exact yet local gradients under a strict stop-gradient constraint, preserving a memory footprint that does not grow with network depth while recovering gradient fidelity. Experiments on MNIST, Fashion-MNIST, and CIFAR-10 across MLP and convolutional architectures show that BLANP matches backpropagation on simple benchmarks. On the more challenging CIFAR-10, BLANP-Exact surpasses the best prior local learning method by 2.40% with a simpler architecture, and trails an identical backpropagation baseline by only 3.90%. The code is available at https://github.com/anonymous/BLANP.

Attribute-efficient PAC learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning algorithms are faced with prevalent data corruptions or even malicious attacks. It is of central interest to design computationally-efficient algorithms that are robust to malicious corruptions. In this paper, we consider that there exists a constant amount of malicious noise in the data and show that it is possible to learn an underlying $s$-sparse halfspace $w^* \in \mathbb{R}^d$ with $O(s^2\log^5 d)$ samples. Specifically, we follow a recent line of works and assume that the underlying distribution satisfies a certain concentration condition and a margin condition at the same time. As a complementary result, we provide an information-theoretic sample lower bound under such conditions. Strong evidence shows that our sample complexity is nearly optimal. To show the robustness of our algorithm, we provide a new gradient analysis that carefully handles the sparsity admitted constraints in hinge loss minimization program, which could be of independent interest.

We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never observed in the training input. This mechanism induces a novel bottleneck absent from dense models. We derive the asymptotic population loss in both the underparameterized and overparameterized regimes, and show that the loss exhibits a double-descent peak near the interpolation threshold---where the number of parameters is just sufficient to fit the training data---resulting in a loss curve governed by two distinct scaling exponents---one for the overparameterized regime and one for the underparameterized regime---with a gap determined by the degree of sparsity. Additionally, we derive a compute-optimal frontier that favors increasing dataset size over model capacity under fixed compute budgets. We also analyze gradient-descent dynamics and identify a scaling law for the probability that fixed-step gradient descent becomes unstable. We further show that the sparsity-induced effect persists under nonlinear activations. Experiments validating the theory can be found at https://anonymous.4open.science/r/sparse-scaling-neurips2026-3CDB/SparseScaling1.ipynb.

Industrial anomaly detection is evolving from category-specific detectors toward unified models capable of handling multiple categories simultaneously. However, in multi-class setting, greater inter-category diversity not only compels enhanced reconstruction capacity to model normal patterns but also exacerbates the “identical shortcut” problem, wherein anomalies are likewise well reconstructed. Moreover, existing unified frameworks are typically confined to single-modal (RGB) inputs and lack multimodal capability. To address these, we propose an Efficient Cross-modal Feature Reconstruction (ECFR) model for unified multi-class anomaly detection, which harnesses the inherent difficulty of cross-modal reconstruction to alleviate the shortcut issue and amplify anomaly discrimination. The framework is built on two core modules: an Adaptive Feature Interaction and Recalibration (AFIR) module and a Hybrid Attention Convolution (HAC) module. Through feature interaction, fusion, and reconstruction, our model achieves two key outcomes: learning normal patterns of multi-class objects while forcing reconstruction failures for anomalous inputs. Extensive experiments on the MVTec 3D-AD and Eyecandies datasets validate our approach, which achieves state-of-the-art performance in multimodal multi-class anomaly detection while requiring significantly fewer model parameters (44.63 M) and lower computational complexity (15.77 GFLOPs) compared to previous multimodal anomaly detection methods.

Agent applications are evolving into workflows composed of large language model (LLM) calls and tool invocations, termed modules. Existing distributed agent systems typically adopt a disaggregated architecture, deploying different modules on separate devices. While this enables pipeline parallelism, imbalanced module latencies introduce severe pipeline bubbles that limit throughput. A natural alternative is an aggregated architecture that co-deploys all modules across all devices, eliminating bubbles by keeping every device continuously active. However, this introduces request blocking: short requests are forced to progress in lockstep with longer ones in the same batch, and newly arriving requests must wait until the entire ongoing batch completes the full workflow. To address this, we propose AgentWeave, an efficient distributed serving system for agent applications built on the aggregated architecture. Its core mechanism, flow decomposition, decomposes long agent requests into fine-grained execution units while preserving agent semantics, allowing short and newly arriving requests to proceed without being stalled by long-running ones. Complementing this, a flow-adaptive scheduler dynamically balances the throughput gains of decomposition against its scheduling overhead. Experiments across four representative agent applications demonstrate that AgentWeave improves throughput by $1.81\times$, reduces average latency by $2.45\times$, and reduces P90 latency by $2.04\times$ over state-of-the-art baselines.

Diffusion Transformers (DiTs) have achieved strong performance in visual generation, but their dense token processing leads to slow training convergence and high computational cost. Recent token routing methods such as TREAD accelerate training by allowing a random subset of tokens to bypass intermediate layers. It can be expected that carefully tuning the routing ratios over time steps or layers can achieve more significant accelerations. However, the theoretical mechanisms underlying stochastic routing remain underexplored, making the tuning of routing ratios intractable. In this paper, we first theoretically show that stochastic token routing can be interpreted as an implicit route-sensitivity regularizer. Under this view, the routing ratio determines the strength of the induced regularization: larger routing ratios introduce stronger route-induced perturbations and therefore stronger regularization pressure. This further motivates a noise-conditioned routing strategy. In diffusion training, samples at larger timesteps contain heavier noise and often provide less stable gradient signals, suggesting that they may require stronger regularization. We therefore assign larger routing ratios to higher-noise samples, allowing the routing-induced regularization strength to adapt to the noise condition. Based on this insight, we propose \emph{Noise-Aware Routing}, which partitions samples within each mini-batch into low-, middle-, and high-noise regions and assigns progressively larger routing ratios to them. This simple noise-conditioned allocation synergistically bridges computational savings with enhanced model priors. Extensive experiments on class-conditional ImageNet generation show that our method accelerates training convergence and improves generation quality. Noise-Aware Routing achieves up to \textbf{15.6}$\times$ and \textbf{20}$\times$ convergence speedups over DiT baselines—and outperforms TREAD—on ImageNet-256 and ImageNet-512, respectively, measured by the training iterations required to match our 400K-step FID. In the guided setting, our method achieves an FID of \(2.67\) with a substantially shorter training iterations without architectural changes.

Temporal action segmentation (TAS) is commonly trained on large banks of pre-extracted frame features rather than raw RGB video, but storing and replaying those features becomes a practical bottleneck for long-form video, especially in incremental TAS where past-task data must remain available to mitigate catastrophic forgetting. Recent TAS replay and condensation methods reduce this burden, but they rely on dense frame-wise annotations and allocate storage through fixed segment-level structures, limiting their flexibility for long procedural videos whose frame complexity varies substantially over time. We introduce Adaptive Residual-Quantized Variational AutoEncoder (ARQ-VAE), a compact and label-free memory representation for TAS features that learns a discrete residual quantization of frame-level video features and then adaptively truncates the residual chain on a per-frame basis, retaining only the residual prefix that best reconstructs each frame feature. This yields a practical compact feature memory that does not depend on frame-wise labels and can therefore support multiple TAS settings with the same stored representation, while a lightweight fine-tuning stage further improves reconstruction quality for the truncated codes that are actually retained. Across standard TAS benchmarks, ARQ-VAE achieves a substantially improved storage--performance trade-off over prior replay and condensation baselines. On Breakfast, our final representation reduces training-set storage from 28 GB for the original I3D feature bank to 10 MB while retaining strong downstream segmentation performance; with ASFormer, it achieves 71.5 Edit and 51.2 F1@50 in the supervised setting. We further show that the same label-free memory remains effective for incremental and unsupervised TAS, and transfers to an alternative pretrained feature space based on DINOv3. We position ARQ-VAE as a practical memory representation for TAS, and a promising direction for broader dataset condensation applications.

Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO) enables input-space adaptation but faces high query costs and optimization challenges in the unsupervised TTA setting. We introduce BETA (Black-box Efficient Test-time Adaptation), a framework that addresses these limitations by employing a lightweight, local white-box steering model to create a tractable gradient pathway. Through a prediction harmonization technique combined with consistency regularization and prompt learning-oriented filtering, BETA enables stable adaptation with no additional API calls and negligible latency beyond standard inference. BETA achieves a +7.1% accuracy gain on ViT-B/16 (ImageNet-C) and +3.4% on CLIP (ImageNet-S/R), surpassing strong white-box and gray-box methods including TENT and TPT. On a commercial API, BETA achieves comparable performance to ZOO at 250x lower cost while maintaining real-time inference speed, establishing it as a practical and efficient solution for real-world black-box TTA.

Large language models (LLMs) have achieved remarkable success while introducing critical energy bottlenecks that challenge sustainable deployment. Spiking neural networks (SNNs) provide a promising approach for energy-efficient spiking LLMs via ANN-to-SNN (A2S) conversion. Among various spike coding methods, time-to-first-spike (TTFS) coding is particularly appealing as it conveys information with a single spike, further reducing energy consumption. However, existing TTFS-based A2S conversion relies on continuous-time assumptions, requiring prohibitively large latencies (e.g., 4096 time steps) to approximate ANN's continuous values. This dependency leads to unacceptable inference delays in LLMs, posing significant challenges for developing practical temporal-coding spiking LLMs. In this paper, we propose a discrete analysis framework for TTFS-based LLMs, reformulating TTFS-based A2S conversion from continuous lossless conversion into discrete error-aware representation. Building on this analysis, we establish an equivalence between discrete TTFS-based SNNs and static quantized ANNs, allowing TTFS conversion to be handled through quantization techniques. Motivated by this equivalence, we introduce Quantization-Consistent ANN-to-SNN (QC-A2S) conversion, which combines static quantization with discretization-compatible TTFS neurons to achieve latency-efficient and high-performance temporal-coding spiking LLMs. Extensive evaluations on representative LLMs across multiple benchmarks demonstrate competitive performance with substantially reduced inference latency.

Addressing codebook collapse in vector quantization models is crucial for efficient discrete representation learning. Recent solutions increasingly rely on expressive codebook reparameterizations, improving adaptability at the cost of additional optimization and computational overhead. This motivates a simple question: what reparameterization scheme is just enough for efficient codebook learning? In this work, we propose Adaptive-Scale Vector Quantization (ASVQ), a lightweight reparameterization method for learning the codebook in a decoupled way. Experiments across image and audio tokenization tasks demonstrate that ASVQ consistently improves codebook utilization, reconstruction quality, and training stability, while remaining competitive with more complex reparameterization-based methods. These results suggest that ASVQ provides a favorable trade-off between codebook expressiveness and efficiency.

Continual pre-training (CPT) enables injecting domain-specific knowledge into large language models during the learning rate annealing phase. However, this compute-efficient paradigm forces practitioners to navigate a challenging optimization space: simultaneously choosing the injection fraction $\lambda$, the data mixture ratio $r$, and the re-warmup peak learning rate $\eta$. Because existing scaling laws have yet to comprehensively integrate and couple these interacting variables, they cannot reliably forecast the resulting trade-offs and final convergence outcomes across unseen injection configurations. To bridge this gap, we introduce the Annealing-phase Domain Injection Scaling Law (ADIS-Law), a parametric framework that explicitly models late-stage distribution shifts as physical perturbations applied to the base pre-training trajectory. ADIS-Law formalizes two opposing macroscopic behaviors: general-domain performance follows a linear forgetting-recovery process, whereas target-domain adaptation adheres to a power-law adaptation trend. Across data-budget and model-scale extrapolation, ADIS-Law predicts target-domain trajectories with an average Spearman correlation of $0.947$ and forecasts tail losses with relative error below $5\\%$. We further show that ADIS-Law can predict optimal injection strategies at extrapolated scales: it ranks target-scale candidate policies with a mean Spearman correlation of $0.936$. By replacing blind grid search over $(\lambda, r, \eta)$ with a single fitted law, ADIS-Law offers a data-driven approach for strategy selection in annealing-phase domain injection.

Neural subgraph matching (NSGM) models are widely used for graph retrieval, where relevance labels for query–corpus pairs are determined by whether the query graph is a subgraph of the corpus graph. Despite widespread applications, the adversarial robustness of such models remains underexplored. In principle, adversarial attacks should induce minimal shift of the instance distribution and the target labels. However, in NSGM, a single edge insertion or deletion can flip relevance labels. Detecting or controlling label flips requires repeated calls to potentially expensive combinatorial solvers. Responding to this challenge, we propose SEAGRAM, a solver-efficient adversarial attack method. It learns to detect non-critical node pairs whose perturbations will likely preserve relevance labels, thereby avoiding solver calls during test time. We further employ an active learning strategy, which reduces the solver calls also during training. Experiments show that SEAGRAM significantly worsens the performance of existing models.

We propose the Grid Efficient Transport Optimization Linear Programming (GETO-LP) model, a novel formulation of the Fixed-Support Wasserstein barycenter problem for $M$ probability distributions supported on $d$-dimensional grids. While standard LP models require $O(MN^2)$ variables, the GETO-LP model requires only $O(dMN^{1+\frac{1}{d}})$, with $N$ being the total number of points in the grid support. Despite the reduced number of variables, our formulation is \emph{exact}, meaning that its solution fully characterizes both the barycenter $\nu$ and the optimal transport plans between $\nu$ and each of the $M$ input distributions without additional optimization steps. We validate the GETO-LP model via extensive comparisons with classical and entropic regularization solvers, demonstrating its effectiveness on both synthetic data and real-world applications such as color palette manipulation and medical data averaging. Overall, our approach provides an effective formulation for the Wasserstein barycenter problem, offering a memory-efficient alternative that naturally integrates with other existing computational frameworks.

Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and often fails to ensure effective context utilization. We propose $\delta$-Mem, a lightweight memory mechanism that augments a frozen full-attention backbone with a compact online state of associative memory. $\delta$-Mem compresses past information into a fixed-size state matrix updated by delta-rule learning, and uses its readout to generate low-rank corrections to the backbone's attention computation during generation. With only an $8\times8$ online memory state, $\delta$-Mem improves the average score to $1.10\times$ that of the frozen backbone and $1.15\times$ that of the strongest non-$\delta$-Mem memory baseline. It achieves larger gains on memory-heavy benchmarks, reaching $1.31\times$ on MemoryAgentBench and $1.20\times$ on LoCoMo, while largely preserving general capabilities. These results show that effective memory can be realized through a compact online state directly coupled with attention computation, without full fine-tuning, backbone replacement, or explicit context extension.