NeurIPS 2026 论文列表

We present a novel GPU-accelerated global solver for constrained nonlinear programming (NLP) inspired by the efficient linear bound propagation framework in neural network (NN) verification. Existing work on NN verification, a problem that can be cast as feasibility detection for a nonlinear objective, demonstrated orders-of-magnitude speedups with the linear bound propagation-based framework when compared to traditional solvers. Extending this paradigm to global nonlinear programming requires addressing many challenges: a global constrained NLP solver must effectively exploit all, possibly unstructured, nonlinear constraints to improve the objective, whereas NN verification typically handles simple input box constraints over a well-structured NN and does not directly optimize an objective function. We address these challenges by fully exploiting the linear bounds produced by bound propagation: these linear bounds can be viewed as relaxations of nonlinear constraints and used to provide dual objectives, check infeasibility, and guide the search for a primal solution. In addition, we proposed tighter linear relaxations (essential for linear bound propagation) for bilinear functions commonly used in NLP problems, and a projected augmented Lagrangian method tightly coupled to our dual solving procedure to produce primal solutions. Our method solves 399 of 505 bounded and continuous NLP problems in the GAMS and MINLPLib benchmarks under a 180-second limit, outperforming many strong global solvers (including commercial ones) such as SCIP, BARON, and LindoGlobal. Compared to SCIP (the strongest solver on these problems), we solve 104 problems exclusively, including large-scale, highly nonlinear ones that are often out of reach for traditional approaches. Our method demonstrates a distinct, highly complementary regime for GPU-accelerated global optimization of nonlinear programming problems.

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces the likelihood in standard RL with its evidence lower bound (ELBO), estimated from randomly masked sequences. Despite being well-aligned with pre-training, these approaches introduce bias from training-inference mismatch by applying the likelihood surrogate ELBO, which can potentially cause training collapse. In this work, we propose **Guided Denoiser Self-Distillation (GDSD)** to directly distill the denoiser of dLLMs from an advantage-guided self-teacher, derived from the closed-form optimum of reverse-KL regularized RL. GDSD matches the dLLM's denoiser logits to the teacher's via a normalization-free objective, which reduces RL to likelihood-free self-distillation and thus bypasses the TIM biases. Recent ELBO-based methods emerge as instances of applying different distillation divergences, but with diagnosable pathologies that GDSD avoids. On planning, math, and coding benchmarks with LLaDA-8B and Dream-7B, GDSD consistently outperforms prior state-of-the-art ELBO-based methods with a more stable training reward dynamics, achieving test-accuracy improvements of up to $+19.6\\%$. These results suggest that direct denoiser self-distillation, without relying on ELBO likelihood surrogate, can provide a more stable and effective RL procedure for dLLMs.

Physical-domain adversarial attacks present critical security threats to diverse AI systems, notably autonomous driving. Generalization is an inherent requirement and a primary obstacle in physical attacks, manifesting as the ability of adversarial patterns to persist across varying environmental configurations and to transfer to unseen victim models. While prior methods demonstrate generalization across specific models, their performance drops significantly on open-vocabulary foundation models, with some approaches becoming entirely ineffective. This lack of generalization stems from the failure of adversarial camouflage to construct a cohesive pseudo-feature across perspectives, lacking the stable semantic representation characteristic of natural objects. Such a deficiency arises because existing attack paradigms rely on independent view-level optimization and non-targeted objectives, which lead to semantically scattered features and inconsistent optimization directions. To address these limitations, we propose Generalizable Physical Adversarial Camouflage (G-PAC), a framework that transitions from view-specific suppression to coordinated object-level representation learning. G-PAC maintains a momentum-updated global pseudo-feature center as a stable adversarial anchor to guide optimization across diverse configurations. By leveraging the feature space of a self-supervised foundation model as a semantic prior, we introduce a contrastive regularization term to encourage feature aggregation while ensuring adversarial potency. Comprehensive digital and physical evaluations demonstrate the effectiveness of G-PAC. Notably, it outperforms the strongest baseline by an average AP@0.5 margin of 0.10 across seven diverse detector architectures in digital settings, and further extends this margin to 0.12 in real-world physical tests. Furthermore, G-PAC exhibits profound black-box transferability against highly resilient open-vocabulary foundation models, inducing an additional absolute AP@0.5 reduction of 0.30 on GLIP.

In this work, we study nonconvex–strongly convex online bilevel optimization (OBO) using only first-order oracle. Existing OBO algorithms are mainly based on hypergradient descent, which requires access to a Hessian-vector product (HVP) oracle and potentially incurs high computational costs. By reformulating the original OBO problem as a single-level online problem with inequality constraints and constructing a sequence of Lagrangian function, we eliminate the need for HVPs arising from implicit differentiation. Specifically, we propose a fully first-order algorithm for OBO, and provide theoretical guarantees showing that it achieves regret of $O(1 + V_T + H_{2,T})$ with a total of $O(T\log T)$ iterations, where $V_T$ measures the variation in function values and $H_{2,T}$ characterizes the drift variation of the inner-level optimal solution. We also establish a sublinear regret bound under the single-loop structure by introducing additional gradient-variation terms. Furthermore, we develop an improved variant with an adaptive inner-iteration scheme, which removes the dependence on $H_{2,T}$ and achieves regret of $O(\log T + V_T)$. Finally, under the stochastic OBO setting, we establish the regret bound for the fully first-order algorithm, i.e., $O(T^{2/3}(1 + \sigma^2) + V_T + H_{2,T})$. Numerical experiments demonstrate the feasibility of our algorithm and support our theoretical findings.

We study price-adjustment dynamics for computing competitive equilibria (CE) in Fisher markets with chores. Unlike in classical goods markets, prices in chores markets are payments for taking on undesirable tasks, and natural excess-demand dynamics can fail; even the naïve analogue of Walrasian tâtonnement may diverge. Recent work of Chaudhury et al. (2025) overcomes this obstacle via \emph{relative tâtonnement}, which subtracts the average excess-demand signal from the excess demand vector. This recovers convergence, but at the cost of coupling the price updates across all chores. This leaves open whether such global coupling is inherent, or whether convergent tâtonnement can be recovered through a genuinely local update in which each chore reacts only to its own excess demand. We answer this question affirmatively through \emph{multiplicative tâtonnement}, a fully distributed dynamics in which each chore price is updated using only its current price and its own excess-demand signal. Although the update contains no explicit normalization term, Walras' law and the multiplicative form of the update implicitly preserve the relevant aggregate price geometry. We prove that multiplicative tâtonnement converges to a CE in any chores Fisher market with continuous, convex, and 1-homogeneous (CCH) disutilities. For convex CES disutilities, we further prove an approximate-CE convergence rate with the same O(1/\varepsilon^2) dependence as relative tâtonnement, but with improved dependence on problem constants. Experiments on real-world and simulated instances show that multiplicative tâtonnement is substantially faster in practice, often by an order of magnitude.

Machine learning (ML) methods have achieved notable success in enhancing individual components of mixed-integer linear programming (MILP) solvers. However, most existing approaches focus on single-component enhancement, neglecting critical interactions among components and often yielding diminishing returns when multiple approaches are integrated. The emergence of large language models (LLMs) provides a promising paradigm for jointly optimizing multiple solver components within a unified framework. In this paper, we propose Jolly-MILP, an LLM-guided framework to jointly optimize presolving, cut selection, and branching variable selection in exact MILP solvers. Our approach introduces a synergistic Coordinator to align component-level generators and a hierarchical Controller to produce adaptive, multi-stage strategies. Extensive experiments on nine MILP datasets demonstrate that Jolly-MILP consistently outperforms both ML-based approaches and existing LLM-based methods. These results show that explicit joint optimization, rather than isolated component-wise enhancement, is crucial for acquiring further gains in exact MILP solving, offering a new pathway for more advanced solver design.

Supervised fine-tuning (SFT) on long teacher trajectories is the dominant method for instilling investigation and reasoning capabilities into open software-engineering (SWE) agents. Under SFT, every retained response is an imitation target, so the student inherits not only the trajectory's outcome but also any flaw in its intermediate steps, including ungrounded leaps and redundant loops. High-quality training data must therefore be jointly effective (each step is grounded and narrows the agent's epistemic gap to the correct fix) and efficient (each step is information-bearing rather than redundant or looping). Existing recipes filter or relabel teacher rollouts using only a binary terminal verifier, which does not directly target these axes and provides no supervision on instances where the teacher fails. Every real issue ships with a developer-authored reference patch $p^\star$ that implicitly testifies to the file paths, runtime behaviors, and conventions a fix presupposes, but the standard pipeline discards it. We propose P2T (Patches-to-Trajectories), which uses $p^\star$ as privileged information during curation, and frames trajectory construction as a bi-objective program over per-step effectiveness and trajectory length. A reverse phase distills $p^\star$ into a latent process graph $G^\star$ of contextual facts and solution milestones, encoding dense intermediate anchors in constructive ordering. A forward phase curate trajectories from blinded teacher continuations, scoring per-step progress against $G^\star$ under a leakage-blocking groundedness check and committing the shortest segments that retain effectiveness. Using only 1.8k curated SWE-Gym instances, P2T improves both axes simultaneously over outcome-filtered SFT and its tool-error-masking variant: on SWE-bench Verified, it lifts Pass@1 by up to +10.8 points while cutting per-instance inference cost by 15%, with consistent gains on SWE-bench Lite and across two teachers. A size-matched ablation and qualitative analysis further isolate per-trajectory quality from data scale.

Importance weights are essential in domain adaptation under label shift, yet their utility is often undermined by the finite sample uncertainty associated with their estimation. Existing methods typically analyze this uncertainty through Gaussian elimination on interval-valued linear systems, which leads to overly conservative confidence regions and inefficient downstream applications. We propose a paradigm shift from inversion-based inference to a direct matrix constraint framework. We use this framework to define a joint confidence region and extract marginal intervals via linear programming, deriving provably tighter bounds for importance weights while maintaining exact finite-sample validity. Furthermore, we analyze the confidence region's geometry and provide the theoretical results for its diameter bounds. Evaluated across text, image, multimodal benchmarks, including AGNews, MNIST, CIFAR-10, N24News, and a real-world autonomous driving dataset, nuImages, our approach consistently yields shorter confidence intervals and smaller prediction sets than inversion-based methods.

Large language models (LLMs) are driving autonomous agents toward real-world environments, with the Web emerging as one of the most representative interaction scenarios. However, training Web agents with naive exploration remains challenging: successful trajectories are rare, and the sparse terminal rewards make it difficult for agents to obtain useful feedback from failed trajectories. Inspired by skill acquisition theory, we propose Skill-Composed Progressive Exploration (SCOPE), a short-to-long learning framework for long-horizon Web agents that decomposes complex task exploration into a gradual expansion process from local skills to complete task-solving capability. Specifically, SCOPE iteratively explores around local skills: Skill Discovery extracts reusable local skills and failure experiences from historical rollouts; Skill Orchestration composes discovered skills into high-level skill chains; andSkill Expansion leverages failure experiences aligned with the current skill chain to guide the agent toward exploring new subskills. Through this process, SCOPE progressively constructs task-completing skill chains across rollouts and internalizes them into the policy parameters through agentic on-policy distillation. Extensive experiments on WebArena, WebVoyager, and WebShop show that SCOPE consistently improves exploration dynamics and achieves 3.9\%--18.6\% relative gains over the strongest baselines in each setting. Our code is publicly available at https://anonymous.4open.science/r/SCOPE-14D3.

The electrocardiogram (ECG) is a time series that records the electrical activity driving cardiac motion through electromechanical coupling (EMC), where the depolarization captured by ECG triggers each heartbeat. The temporal delay and low spatial resolution of such multichannel dynamic data often cause temporal and spatial misalignments along the physical motion, limiting the application of ECG data to event/segment-based downstream clinic practice. Although many efforts have been made to recover spatiotemporal trajectories conditioned on ECG waveforms, the intrinsic principle of EMC that results in various temporal delays remains underexplored in current generative models. To address this limitation, we propose Time2Track, a mechanics foundation model that generates individualized 4D heart motion from same-day ECG recordings by encoding electrophysiology as delay-aware token embeddings. Specifically, a learnable wavelet decomposition extracts the electromechanical delay, which is then formulated as a physics-based conditioning signal for motion diffusion. Time2Track generates 4D motion with individual-specific kinematics, avoiding the collapse to a population average, i.e., a common failure scenario when diffusing motions whose inter-subject differences are subtle. On $n=40,577$ subjects from the UK Biobank, our Time2Track accurately synthesizes 4D cardiac trajectories from ECG and preserves inter-subject diversity, a regime in which generic motion diffusion baselines collapse to a population average.

Deep narrow neural networks underlie modern architectures from ResNets to Neural ODEs, yet their fundamental computational properties at constant width remain poorly understood. We prove that, for every deterministic Turing machine $M$, there is a single $ReLU$ network $N_M \colon [0,1]^4 \to [0,1]^4$ of width $4$ and depth $\mathrm{poly}(|M|)$, polynomial-time constructible, whose iterates simulate $M$ on every infinite binary tape encoded in a \emph{convex} initial region of $[0,1]^4$, with iteration count proportional to Turing-machine time. This establishes a tight correspondence between depth in width-$4$ networks and time on a Turing machine. The correspondence has three immediate consequences. First, verification of width-$4$ $ReLU$ networks spans the full complexity hierarchy along the single axis of depth: it is $NP$-complete for unary-encoded time bound, $NEXP$-complete for binary-encoded time bound, and $RE$-complete (undecidable) for unbounded time. Second, the hardness extends with two extra neurons of width to every common smooth activation: at width $6$, the robust verification problem (a promise problem with $\delta/2\delta$ gap) is $NP$-complete for $\tanh$, sigmoid, GELU, Swish, ELU, and any polynomial-time-computable continuous non-polynomial activation admitting a polynomial-time computable Lipschitz constant. A corollary is a discretized Neural ODE analogue at dimension 5. The simulation and statements are carried out on convex inputs, covering a regime previously inaccessible because of a continuity obstruction inherent to $\ReLU$ networks.

Progress in legal AI increasingly depends on access to authoritative legal text at scale. Yet one of the most consequential layers of American law remains largely absent from existing machine-readable corpora: local ordinances. Local codes govern zoning, housing, business licensing, public health, noise, animal control, and many other domains of everyday regulation, but they are fragmented across vendor platforms designed for human browsing rather than bulk research access. We introduce LOCUS—the Local Ordinance Corpus for the United States—a comprehensive corpus and county-harmonized access layer for U.S. municipal and county ordinance codes. The raw corpus, available for release to researchers, represents nearly all publicly available municipal and county ordinance codes. The resulting raw corpus contains codes from 9,239 cities and counties. A smaller county-harmonized LOCUS access layer provides coverage for the largest 2,309 of 3,144 U.S. counties, accounting for a majority of the population. We use OCR to handle the myriad of document formats that have kept the law from being a public resource. We release the corpus with coverage metadata to support reproducibility, downstream legal AI research, and the incremental expansion of machine-readable access to local law. We train a collection of ModernBERT-based classifiers and scorers to facilitate analyzing U.S. local law among several dimensions, such as opacity and paternalism, that have not previously been studied at this scale.

Active feature acquisition (AFA) requires an agent to choose a budget-limited set of costly features before making a prediction. Greedy conditional-mutual-information (CMI) and value-of-information policies perform well when useful features are individually informative, but fail under joint-only evidence: a query is valuable only because it enables a future evidence set. To address this, we propose Forward-$\Phi$, a model-based non-myopic acquisition scorer that requires a known structural causal model (SCM) or generative AFA model. Forward-$\Phi$ evaluates a candidate query by its Shapley contribution to budget-feasible future action sets in a cooperative game on the expected forward utility. Two variants share the same game: a raw score that keeps both singleton and interaction value, and a residual score that strips the singleton component to isolate joint-only utility on diagnostic probes. On AFABench CUBE-NM, the raw Monte Carlo (MC) Forward Shapley scorer reaches $0.664 \pm 0.024$ accuracy over five MC seeds, well above all reported baselines including the OL-MFRL ($0.235$) and ODIN-MFRL ($0.160$) reinforcement-learning loops trained under the same split and shared pretraining protocol. Controlled SCM and Bayesian-network (BN) probes confirm the predicted mechanism: Forward-$\Phi$ yields substantial gains when target information is jointly carried, and matches Greedy on greedy-aligned controls. The primary contribution is the belief-conditional Forward Shapley state-action score, a credit-assignment signal derived from Shapley axioms for non-myopic AFA under joint-only evidence.

Data heterogeneity and multiple local update steps in federated learning can increase client drift and make global parameter aggregation less stable. Existing Sharpness Aware Minimization (SAM) based federated learning methods usually try to ease this problem by flattening local neighborhoods around client models. However, they do not explicitly optimize on the geometry region where the global parameters are actually aggregated. As a result, the aggregated global model often cannot fully benefit from local flattening. To address this problem, we propose a federated restricted SAM method called FedRSAM, which improves the stability of federated optimization by flattening the parameter aggregation region. First, we build a cone-shaped geometry region using the global update direction from the previous round and the variance of client parameter aggregation, in order to predict where the aggregated parameters may fall in the next round. Then, we restrict the search of SAM perturbation directions to the cone-manifold and only flatten the loss surface inside this region. Extensive experiments on multiple benchmarks and on both vision and natural language backbones verify the superiority of our method in terms of convergence stability and performance under heterogeneous settings.

Large-scale training of machine learning interatomic potentials (MLIPs) increasingly relies on data parallelism over heterogeneous atomistic data. In this setting, atom count captures an important part of the per-rank workload, but structures with similar atom counts can still induce different graph workloads through variations in graph count, cutoff edges, higher-order geometric features, and graph-collation overhead. This makes conventional atom-count batching and offline load tables both incomplete and inflexible, especially when the model architecture, cutoff radius, or data mixture changes. We present Flux, an online workload-aware scheduler for distributed MLIP training. Flux estimates structure-dependent workload signals from lightweight physical and geometric priors during data loading, calibrates them against runtime and memory costs, and forms balanced, memory-feasible local mini-batches across data-parallel ranks. Without requiring precomputed graph metadata, Flux can be used as a drop-in replacement for the standard distributed sampler, making it flexible and portable across training setups. Across large-scale atomistic datasets and three representative MLIP architectures, eSEN, MatRIS, and AllScAIP, Flux improves training throughput by up to 2.23--4.76$\times$ without degrading convergence.

Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory. In this work, we propose FlowR2A, which resolves this tension by reframing simulation-based rewards from discriminative targets into generative conditions. By learning the reward-conditioned action distribution from dense trajectory-reward pairs with a flow-matching decoder, FlowR2A unifies the dense supervision of scoring-based methods with the proposal generation of anchor-based methods in a single generative model, forcing the model to internalize the correlation between an action and its outcomes in safety, progress, comfort, and rule compliance. To balance hard safety constraints against soft progress objectives, we introduce fine-grained per-timestep reward conditioning and reward noise augmentation. The generative formulation naturally supports controllable test-time sampling via reward guidance and anchored sampling, producing high-quality proposals. FlowR2A achieves state-of-the-art results on the NAVSIM v1 and v2 benchmarks, with multimodal proposals of substantially higher quality than prior methods.

Kernelized attention provides a useful perspective for understanding self-attention as a similarity-based aggregation mechanism, but existing approaches often rely on fixed or stationary kernels, limiting their ability to adapt the similarity structure to complex token interactions. In this paper, we propose flow-based spectral kernel attention (FSKA), a framework for learning expressive nonstationary attention kernels. FSKA formulates kernelized attention through spectral density learning and parameterizes the resulting bivariate spectral density with normalizing flows. This design enables flexible and regularizable kernel learning while remaining compatible with scalable linear-attention computation. We further show that expressive kernel learning enables a simplified attention design with removed query--key projections and fixed orthogonal value projections, resulting in a more parameter-efficient architecture. Controlled experiments on classification, ablation, and scalability profiling show that FSKA achieves competitive or improved performance over existing attention mechanisms, while reducing projection-related trainable parameters by approximately 40\%--47\% compared with most baselines and maintaining favorable linear-attention memory scaling.

Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging because their induced function-space distributions are typically not available in closed form. One practical strategy is to approximate the prior using a finite collection of sampled functions, and then represent posterior functions as learned combinations of these samples. Existing approaches commonly place a Gaussian variational distribution over the combination weights. While tractable, this choice limits the shapes of posterior uncertainty that can be represented, especially when the true posterior is asymmetric, heavy-tailed, or multimodal. We propose Flow-Transformed Implicit Processes (FTIP), a variational inference method that makes this finite-dimensional function-space approximation more expressive. Instead of using a Gaussian distribution over the combination weights, FTIP uses a normalizing flow to define a richer variational distribution. This induces a flexible posterior distribution over functions while preserving tractable optimization. We train the model using a Black-Box $\alpha$ objective, allowing us to compare mass-covering and mode-seeking variational behaviour. Experiments show that FTIP captures asymmetric and multimodal posterior structure in function space that Gaussian coefficient approximations tend to smooth or collapse.

Conditional flow matching produces realistic out-of-distribution samples across modalities from images to proteins, yet the conditioning signals that enable extrapolation remain poorly understood for biological time series. While considerable work has focused on areas of biology such as proteins and molecules, generative models of neural time series have been largely restricted to categorical conditioning, which precludes compositional and zero-shot generalization. In this work, we propose a per-timestep conditioned diffusion transformer for generating realistic fMRI brain dynamics during unseen cognitive tasks, by injecting both compositional language and optional spatial priors in-context. Such zero-shot generation would support in-silico task design and counterfactual evaluation of novel cognitive experiments before costly scanner acquisition. Leveraging this model, we evaluate across hundreds of held-out task conditions and characterize predictive performance in relation to the training manifold. From language alone, the model recovers region-specific recruitment across tasks and held-out spatial activation patterns. Spatial priors, when available, complement the text pathway by anchoring generation in regions of task space where language alone degrades, while retaining the compositional structure needed for counterfactual task specification. To our knowledge this is the first generative model of whole-cortex fMRI dynamics for unseen cognitive tasks, enabling counterfactual neuroscience and data-driven experimental design.