NeurIPS 2026 论文列表

Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18\%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Visualization videos are provided in the supplementary material.

Zero-shot 3D anomaly detection aims to identify anomalies without access to training data from target categories. However, existing methods mainly rely on projecting 3D observations into multi-view representations that primarily capture geometric cues rather than realistic visual semantics and process them with vision encoders pretrained on RGB data, leading to a significant domain gap between the encoder and the projected representations. To address this issue, we propose Align3D-AD, a unified two-stage framework that leverages the RGB modality from auxiliary categories as cross-modal guidance for zero-shot 3D anomaly detection. First, we introduce a cross-modal feature alignment paradigm that maps rendering features into the RGB semantic space. Unlike prior works that implicitly rely on pretrained encoders, our method enables direct semantic transfer from RGB observations. A semantic consistency reweighting strategy is further introduced to refine feature alignment by reweighting local regions according to holistic semantic consistency. Second, we propose a modality-aware prompt learning framework with dual-prompt contrastive alignment. By assigning independent prompts to RGB-aligned and rendering features, our method captures complementary semantics across modalities, while the contrastive alignment further enhances prompt representations to improve discriminability. Extensive experiments on MVTec3D-AD, Eyecandies, and Real3D-AD demonstrate that Align3D-AD consistently outperforms existing zero-shot methods under both one-vs-rest and cross-dataset settings, highlighting its generalization capability and robustness. Code and the dataset will be made available once our paper is accepted.

Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones cannot dynamically incorporate retrieved context on their own. We show this assumption is unnecessary. We introduce $\textbf{Align-RAG}$, a training-free method that applies a closed-form per-pair amplitude rescaling and integer-lag phase shift to retrieved past--future windows before they enter a frozen backbone's context. With no learned parameters, Align-RAG outperforms the state-of-the-art trained retrieval adapter on a frozen Chronos-Bolt on all seven datasets of the standard benchmark (avg $-3.75\%$ MSE), showing that the gains previously attributed to learned fusion are recoverable without any training. Align-RAG further improves zero-shot MSE on four additional frozen TSFMs with various architectures by $2.5\%$ to $13.7\%$ per backbone with no per-backbone tuning. To probe why alignment helps, we compare the frozen backbone's prediction shift under aligned demonstrations to the closed-form ridge prediction shift on the same pairs. We find that aligned demonstrations induce prediction shifts that track a closed-form ridge predictor on the same pairs, with a future-shuffle control ruling out a futures-averaging account. Together, these results indicate that frozen TSFMs already support dynamic in-context use of retrievals, and that closed-form alignment should be the default baseline for retrieval-augmented forecasting before any fusion module is trained. Code available at: \url{https://anonymous.4open.science/r/phase-rag-4D92}

Spatial resolved inference (SRI) is a critical technique in biomedical research, which aims to measure RNA sequence abundances by associating them with whole-tissue images at a fine-grained molecular scale. However, the extremely low throughput and distributional discrepancies involved pose significant challenges to cellular morphologies captured in hematoxylin and eosin (H&E) connection benchmarking, and existing SRI frameworks suffer from coverage gaps. In this paper, we propose MollFlow, a novel generative Mollified Flow matching model for spatial resolution inference, which is designed to learn the probabilistic dependency between the distributions of whole-slide images and expression profiles. We innovatively reframe the anchors of flow matching as a sequential informative prior derived from whole-slide images rather than isotropic Gaussian noise. During inference, MollFlow progressively refines the prior trajectory, ultimately converging to biologically plausible inferences. For the challenging coupling, which requires enabling intermediate states to explore pathologically aligned subspaces, we carry out a boundary mollified strategy to stabilize the velocity field, rather than being constrained by rigid trajectories. Endowed by this, our unique modulation generation perspective allows the model to retain coupling alignment for manifold incommensurability and prevent coverage gaps. Empirically, we find that MollFlow is capable of accurately inferring gene expression while exhibiting excellent performance in a variety of application scenarios.

Federated fine-tuning of large language models (LLMs) under heterogeneous client capacities is increasingly important, and low-rank adaptation (LoRA) with heterogeneous ranks makes it practical. Existing server-side aggregators compose local matrix updates $\Delta W_i$ from client-specific LoRA factors $(A_i,B_i)$ before aggregating them. Although these matrix updates lie in the same weight space $\mathbb{R}^{m\times n}$ and can be averaged directly, the LoRA factors that generate them may expressed client-specific local basis. In the typical compose--aggregate--factorize--dispatch loop, this basis inconsistency can make the rank-$r_i$ reference prefix dispatched to lower-rank clients unstable after server-side refactorization. In this work, we propose FedAbA, a basis-consistent federated LoRA aggregation framework for heterogeneous ranks. FedAbA first extracts each client's local basis, aligns it to the corresponding prefix of the global reference basis, and constructs a basis-consistent reconstruction of each local matrix update before aggregation. It then aggregates these reconstructions with weights that combine client data size and consistency score, followed by exact coefficient-space SVD refactorization and gauge fixing before rank-prefix dispatch. Our theoretical analysis clarifies the role of basis consistency and supports the proposed consistency-aware aggregation mechanism. Extensive experiments show that FedAbA outperforms representative federated LoRA baselines, with the largest gains under the strongest rank heterogeneity.

Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to provide a powerful inductive bias, improving both convergence and sample quality. In this work, we extend this idea to inverse problems, where pretrained generative models are employed as priors. We propose applying representation alignment (Repa) between diffusion or flow-based models and a DINOv2 visual encoder, to guide the reconstruction process at inference time. Although ground-truth signals are unavailable in inverse problems, we empirically show that aligning model representations of approximate target features can substantially enhance reconstruction quality and perceptual realism. We provide theoretical results showing (a) that Repa regularization can be viewed as a variational approach for minimizing a divergence measure in the DINOv2 space, and (b) how under certain regularity assumptions Repa updates steer the latent diffusion states toward those of the clean image. We integrate Repa into multiple state-of-the-art inverse problem solvers, and provide extensive experiments on super-resolution, box inpainting, Gaussian deblurring, and motion deblurring confirming that our method consistently improves reconstruction quality, while also reducing the number of discretization steps required to reach the same performance level as the underlying solver.

We consider linear equations with min and max operators~(LEMMs) that contain many subproblems ranging from optimization, learning, to games. Recently, Chatterjee et al. [2025] gave a systematic study of the complexity of different subclasses. Three key subclasses--(I) halting branching process, (II) absolutely halting LEMMs, and (III) halting LEMMs--are proved to be in UP $\cap$ coUP while generalizing stochastic games (SSGs). In this work, we study the classic algorithms of Policy Iteration (PI) and Value Iteration (VI) for these general subclasses. First, we simplify the problem hierarchy by showing the equivalence between halting branching process and SSGs. Then, we show that while PI diverges for absolutely halting LEMMs due to the loss of monotonicity, VI remains convergent, a result we establish via diagonal rescaling. Finally, we show that neither PI nor VI converges for general halting LEMMs and, to this end, propose variants of simple policy iteration that ensure convergence across all subclasses.

When an algorithm makes a decision affecting multiple people, we implicitly have a social choice problem: how should differing opinions about the right course of action be reconciled into a single outcome? We show that if we make welfare consequences of alignment a first-order consideration, this problem can be reformulated as linear optimization on a convex *impact space*, making it amenable to toolkits from welfare economics and mechanism design. This reformulation provides a clearer understanding of how different protocols shape an algorithm's externalities. Our linear optimization framework uncovers a straightforward solution to strategyproof alignment mechanism—random dictatorship that can be represented as a single parameter, which regulates externalities from manipulation. In addition, our framework allows us to express a family of constrained welfare mechanisms that address participation externalities—how an individual's participation can affect others in the population—and maximize social welfare subject to guarantees on individual outcomes. We illustrate these results empirically using real human preferences over kidney donation assignment, charitable food distribution, LLM responses, and trolley problems.

Contextual queueing bandits provide a framework for learning to schedule heterogeneous jobs under unknown context-dependent service rates. Under stochastic contexts, existing algorithms achieve $\widetilde{\cal O}(T^{-1/4})$ queue length regret, defined as the expected difference between the learner's and oracle's queue lengths at horizon $T$. In this paper, we improve this rate to $\widetilde{\cal O}(T^{-1/2})$. The key observation is that random exploration is needed only up to a carefully chosen cutoff round, rather than throughout the entire horizon. We propose CQB-$\eta$-2, a three-phase algorithm: (i) pure random exploration to construct an initial estimator, (ii) $\eta$-random exploration combined with a UCB rule to continue learning while maintaining negative drift, and (iii) pure UCB after the exploration cutoff. Our proof decomposes the queue length regret at the cutoff round. Before the cutoff, negative drift suppresses queue length differences caused by suboptimal choices. After the cutoff, the first two phases provide sufficient random exploration samples, ensuring that UCB decisions incur small departure-rate gaps. Combining these two bounds yields queue length regret of order $\widetilde{\cal O}(T^{-1/2})$. We further prove a minimax lower bound of order $\Omega(T^{-1/2})$. The proof constructs two hard instances that are statistically indistinguishable up to the final service decision, and uses a queue-specific coupling argument to convert the resulting testing error into queue length regret. Together, our upper and lower bounds characterize the minimax dependence on the horizon $T$ up to logarithmic factors.

We propose a machine-learning framework based on the principle that learning can be achieved through algebraic decomposition rather than numerical optimization. A learning task is encoded as axioms of an algebra, and learning proceeds by computing a subdirect decomposition of the algebra into subdirectly irreducible components. We show that suitable subsets of these components form models that generalize to unseen data because they approximate the underlying rule in the training data. The method has no dataset-specific hyperparameters to tune and shows no evidence of classical overfitting in our experiments, so we run it without a validation dataset. We compare against multilayer perceptrons as generic parametric baselines without task-specific inductive biases. Across 24 classification datasets, the algebraic method is applied only once to each training set without hyperparameter tuning, whereas the multi-layer perceptrons are selected from many configurations using validation data or cross-validation. Nevertheless, the resulting test accuracies are statistically indistinguishable. Moreover, adding a statistical readout on top of the algebraic representation, using untuned logistic regression, improves over the best multilayer perceptrons selected by validation or cross-validation. More broadly, because task axioms may encode examples, formal knowledge, or both, this approach provides a common algebraic framework and the same algorithm for data-driven problems such as classification, formally specified problems such as computing Hamiltonian cycles from specifications, and mixed settings combining data with formal constraints.

Accurate real-time forecasting of atmospheric pollutants is essential for reducing exposure risks and improving public health. Traditional numerical forecasting systems suffer from incomplete parameterizations, uncertain inputs, and high computational cost. Existing deep learning approaches improve efficiency, but often entangle meteorological and pollutant variables within unified forecasting frameworks, limiting flexibility and pollutant-specific representation learning. To address these challenges, we propose AirMPA, a decoupled autoregressive framework for meteorology-to-pollution forecasting. AirMPA predicts 13 atmospheric pollutants at 0.4$^\circ$ spatial resolution and 12-h temporal resolution using meteorological fields, emission priors, and historical pollutant concentrations. The model is built on an improved Swin-Transformer architecture with zonal release attention and dual-branch fusion, enabling more effective modeling of global transport continuity and heterogeneous pollutant dynamics. During training, AirMPA uses ERA5 reanalysis as meteorological forcing, while during inference it directly ingests forecast fields from external meteorological models, enabling stable autoregressive prediction up to 5 days ahead. Experiments show that AirMPA consistently outperforms Aurora and surpasses CAMS in approximately 90\% of pollutant--lead-time evaluation cases over the 5-day forecast horizon, while outperforming CAMS on all variables beyond 48 h. These results demonstrate the potential of decoupled meteorology-to-pollution forecasting for global air quality prediction.

Multimodal large language models offer a promising foundation for industrial anomaly detection (IAD), yet they remain unreliable for fine-grained diagnosis, where subtle defects require tight alignment between localized visual evidence and domain-specific semantics. Existing single-pass frameworks produce predictions without revisiting or validating intermediate evidence, which leads to spatio-semantic misalignment and error accumulation. More importantly, they lack mechanisms to actively control how additional evidence is acquired and integrated during reasoning, limiting their ability to resolve ambiguous cases. To address these limitations, we propose AirIAD, an agentic iterative reasoning framework that unifies progressive refinement with active information acquisition. AirIAD equips the model with two tools, Perceptive Zoomer and Knowledge Retriever, which enable it to iteratively gather complementary visual and semantic evidence. Through this process, the model performs explicit cross-verification between what is observed and what is known, refining intermediate hypotheses until convergence on a reliable diagnosis. This capability is enabled by a two-stage training pipeline. A supervised fine-tuning stage introduces a Spatio-Semantic Cross-Verification Chain-of-Thought, which structures coordinated perception and knowledge grounding. This is followed by a Spatio-Semantic Group-in-Group Policy Optimization stage, which provides dense step-wise supervision to encourage consistent self-refinement and robust spatio-semantic alignment. Extensive experiments on the MMAD benchmark show that AirIAD, built on Qwen3-VL-Instruct-4B, achieves state-of-the-art performance in anomaly detection and fine-grained diagnosis.

Modern agricultural data is sourced from diverse platforms and spans multiple spatial scales, ranging from ground-level close-up photography to Unmanned Aerial Vehicle (UAV) aerial observation and satellite remote sensing imagery. Accordingly, agricultural multimodal reasoning demands robust cross-scale spatial understanding. However, due to the lack of multi-view agricultural benchmark datasets, existing multimodal large language models (MLLMs) exhibit severe ground-level bias, which leads to scale confusion then semantic collapse in agricultural perception tasks, such as misinterpreting farmland imagery as walls or floors. To address this, we introduce \textbf{AgroOmni}, a large-scale multi-view training corpus with 288K Visual Question Answering pairs covering 56 specialized task categories across 14 task types, designed to capture diverse scales in modern precision agriculture. Built on this dataset, we propose AgroNVILA, which achieves a new state-of-the-art of 62.32\% on the AgroMind benchmark ($+15.03\%$ over GPT-5.2), effectively mitigating the multi-view cross-scale gap for holistic agricultural understanding. Diagnostic evaluations on AgMMU further reveal an inherent heterogeneity between macro-priors and micro-diagnostics through constrained zero-shot performance. Meanwhile, even minimal fine-tuning leads to a dramatic performance gain of AgroNVILA on AgMMU, strongly demonstrating its generalization capability empowered by AgroOmni. Full training scripts are publicly available at \url{https://anonymous.4open.science/r/AgroOmni-6510}.

Learning high-quality multimodal entity representations is essential for advancing reasoning tasks such as multimodal knowledge graph completion (MMKGC). However, rigid alignment in existing fusion strategies can bias representations toward a dominant anchor modality, weakening fine-grained complementary cues and propagating noisy signals into relational reasoning. To address these limitations, we propose MANoR, a Multimodal Autonomous Negotiation framework for calibrated Representation learning. MANoR treats modalities as autonomous semantic agents that negotiate before fusion. Specifically, MANoR preserves modality-specific semantics through centroid-guided subspace contraction, which reduces unstable centroid-relative dispersion while retaining entity-level residual semantics. On this stabilized basis, negotiated attention enables selective cross-modal interaction without collapsing modality boundaries. As modalities can still differ in reliability after interaction, uncertainty calibrated fusion estimates dimension-level aleatoric uncertainty and modality-level reliability to compute relation-aware fusion weights. In this way, MANoR couples modality autonomy, selective interaction, and calibrated integration within a unified representation learning framework. Experiments on MKG-W, MKG-Y, TIVA, and KVC16K show that MANoR consistently outperforms strong MMKGC baselines, achieving a relative Hits@1 gain of up to 17.72% on KVC16K.

We study online learning in the adversarial injection model [GHMS23], where each instance is either drawn i.i.d. from an unknown distribution or is an arbitrary adversarial injection. The learner never knows which rounds are adversarial, but may abstain without penalty on adversarial injections. The learner's goal is to make few total misclassifications and few abstentions on i.i.d. instances. This model lies between classical statistical learning, governed by the VC dimension, and adversarial online learning, governed by the Littlestone dimension. Unlike prior work, which has largely focused on the realizable setting, we consider an agnostic formulation that allows arbitrary labels. We present an online algorithm that guarantees sublinear excess misclassification error and sublinear abstention error, against oblivious and adaptive adversaries, for function classes that admit bounded bracketing number witnessed by brackets of bounded VC dimension. Our algorithm is distribution-independent and does *not* require prior knowledge of the distribution. As corollaries, we obtain new learning guarantees for halfspaces (linear classifiers) and richer classes such as feed-forward neural networks with threshold activations.

Message-passing neural networks (MPNNs) learn node representations by iteratively aggregating information from neighbors, but stacking too many layers causes all representations to converge, a phenomenon known as oversmoothing. We propose a geometric perspective on this phenomenon. At each depth $k$, the propagation operator assigns to every node $v$ a walk distribution $p_v^{(k)}$, a probability distribution over all nodes describing how $v$ distributes its attention across the graph. These walk distributions form a point cloud on the probability simplex, and oversmoothing is the contraction of this cloud to a single point. To measure this contraction, we exploit the intrinsic geometry of the simplex: the Fisher--Rao metric, the unique Riemannian metric invariant under sufficient statistics, whose chordal distance under the square-root embedding $p \mapsto \sqrt{p}$ is the Hellinger distance. The resulting diagnostic, the \emph{aggregation dispersion} $\mathcal{D}_k$, is the variance of the embedded point cloud on the unit sphere. We prove that: (i) $\mathcal{D}_k = 0$ if and only if the $k$-th step propagation matrix has rank one, providing a necessary and sufficient condition for representational collapse; (ii) $\mathcal{D}_k$ is monotonically non-increasing with depth, so each layer irreversibly spends a finite diversity budget; (iii) the spectral gap of the propagation matrix controls the rate of this decay; and (iv) for contractive MPNNs, the aggregation dispersion upper-bounds the representation dispersion up to architecture-dependent constants, connecting the geometry of the simplex to the geometry of the feature space. In experiments across 14 model configurations and 11 datasets, $\mathcal{D}_k$ achieves the highest average Pearson correlation with accuracy degradation among all training-free diagnostics ($|r| = 0.721$), outperforming the post-training effective rank ($|r| = 0.688$).

Recent AI systems achieve strong results on many benchmarks, yet these gains have not translated into economically meaningful deployment across professional domains. We argue that this gap is largely an evaluation problem: existing benchmarks rarely measure sustained performance on real, economically valuable workflows. We introduce Agents’ Last Exam (ALE), a benchmark for evaluating generalist computer-use AI agents on long-horizon professional tasks with verifiable outcomes. ALE is developed in collaboration with 250+ industry experts and organized around a taxonomy grounded in O*NET / SOC 2018. The benchmark spans 55 subdomains across 13 industry clusters and currently contains 1,490 task instances sourced from authentic professional workflows. Tasks require integrated GUI interaction, shell execution, software operation, and long-horizon planning inside real computing environments. To support scalable evaluation, ALE uses deterministic deliverable-based scoring and structured rubric verification rather than open-ended human judgment whenever possible. Experimental results show that current frontier agents remain far from saturation: across mainstream harness and backbone configurations, the average full-pass rate on the hardest tier is only 2.6%. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for measuring the gap between benchmark success and GDP-relevant impact.

Static bug analyzers play a crucial role in ensuring software quality. However, existing analyzers for bug detection in large-scale codebases often suffer from high false positive rates. This limitation largely stems from their inadequate capabilities in performing precise path feasibility validation for complex code contexts. While recent work has explored Large Language Models (LLMs) to eliminate false positives in static bug detection, the limited reasoning capabilities of LLMs over long and complex contexts hinder their effectiveness when applied to large-scale software projects. To address this challenge, we propose PathAgent, an agent-driven framework for fine-grained path feasibility analysis. PathAgent decomposes complex inter-procedural analysis into localized symbolic range reasoning sub-tasks, and employs an on-demand contextual exploration strategy to adaptively retrieve only the necessary code context. These designs enable precise path feasibility reasoning and effectively reduce false positives reported by static bug analyzers. Evaluation on large-scale real-world projects shows that PathAgent eliminates 79% of false positives, outperforming all baselines by 23% to 44%, while maintaining strong bug detection capability with a recall of 0.94.

AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark enables fair comparison across these approaches. We present **Agentick**, a benchmark for sequential decision-making agents designed to evaluate RL, LLM, VLM, hybrid, and human agents on common ground and to power research on the fundamental challenges of sequential decision-making. Agentick provides 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities, all exposed through a single Gymnasium-compatible interface. The benchmark ships with a Coding API, oracle reference policies for all tasks, pre-built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation spanning 27 configurations and over 90,000 episodes reveals that no single approach dominates: GPT-5 mini leads overall at 0.309 oracle-normalized score while PPO dominates planning and multi-agent tasks; the reasoning harness multiplies LLM performance by 3--10x; and ASCII observations consistently outperform natural language. These findings highlight the substantial room for improvement that remains across all agent paradigms. Agentick's capability-decomposed, multi-modal design provides the empirical infrastructure needed to drive progress toward general autonomous agents, both as an evaluation framework and as a training ground for RL post-training of foundation models in truly sequential environments.