NeurIPS 2026 Papers

Cognitive diagnosis (CD) infers students' mastery of knowledge components (KCs) from their responses, supporting personalized feedback and exercise recommendation. Cognitive diagnosis models (CDMs) are often ranked by response-prediction AUC under inconsistent experimental protocols, while their KC-level mastery profiles are not consistently audited under a shared protocol. We introduce \texttt{pyCD}, a unified benchmark of eleven CDMs on six public datasets that fixes preprocessing, splits, hyperparameter search, and stopping rules; the benchmark reports KC-level diagnostic metrics for learned mastery alongside standard prediction metrics. Two findings show that gains in AUC do not translate into gains in diagnostic quality. First, the AUC leaderboard is sharply compressed and sensitive to protocol choices: modern CDMs often cluster within $0.005$--$0.020$ AUC, with the per-dataset best non-IRT CDM improving over IRT by only $0.017$ AUC on average; removing validation-AUC early stopping can shift AUC by up to $0.13$ on individual cells. Second, the AUC gaps that remain do not reliably transfer into diagnosis: the top-1 AUC model is typically outside the top-3 by KC-level diagnostic agreement (DOA). The same mismatch extends to exercise difficulty: against Junyi's human pairwise difficulty ratings, learned CDM difficulty parameters rank worse than both an empirical accuracy-based baseline and zero-shot LLMs given only exercise titles. CDM evaluations should therefore report diagnostic outputs directly rather than infer them from predictive gains; \texttt{pyCD} provides a unified protocol for doing so. Code, splits, and configurations are available at \url{https://anonymous.4open.science/r/pyCD-NeurIPS2026-60B8}.

As machine learning systems are increasingly deployed in real-world applications, the question of how to represent and quantify uncertainty has moved from a methodological side issue to a central concern. In practice, however, making a model uncertainty-aware is still surprisingly difficult: relevant tools tend to be scattered across libraries, each tied to a particular framework and a particular approach to modeling uncertainty, and the choice of representation, quantification, and evaluation is typically left to the user without much guidance. In this paper, we present probly, a Python package that addresses theses issues in a single, modular framework. probly offers (i) lightweight transformations that turn existing models into uncertainty-aware ones, currently supporting PyTorch, scikit-learn, and Flax, (ii) several representations, including second-order distributions, credal sets and conformal prediction, (iii) the corresponding quantification measures, and (iv) a number of evaluation protocols, which can be combined more or less arbitrarily. Using probly, we conduct a benchmark study on three standard tasks --- selective prediction, out-of-distribution detection, and active learning. In addition, and unlike existing benchmarks, we evaluate suitable methods on first-order data, i.e., datasets for which the target itself is a distribution over outcomes. We further illustrate the flexibility of the package on a number of less standard case studies, including large language models, graph neural networks, and data streams. The package is publicly available at \url{https://anonymous.4open.science/r/probly}.

Reasoning is essential for autonomous driving (AD) in long-tail scenarios, where vehicles must apply commonsense knowledge, understand spatial relations, infer agent interactions, and make safe decisions. However, existing AD datasets and benchmarks mainly target perception, prediction, or planning, and provide limited supervision for reasoning over realistic long-tail driving scenes. We introduce nuReasoning, a large-scale real-world dataset and benchmark for reasoning-centric AD. Following the lineage of nuScenes and nuPlan, nuReasoning advances real-world AD datasets and benchmarks toward structured reasoning in long-tail driving scenarios. It contains 20K 20-second clips collected across multiple cities, with synchronized multi-camera images, LiDAR, HD maps, object annotations, and complementary forms of human-verified reasoning annotations: Spatial Reasoning, Decision Reasoning, and Counterfactual Reasoning. Unlike prior datasets that focus primarily on visual question answering, nuReasoning supports both reasoning evaluation and planning evaluation, enabling a direct study of how reasoning supervision affects driving performance. Experiments show that fine-tuning VLMs on nuReasoning substantially improves driving-specific question answering, while incorporating reasoning supervision into VLA training improves planning performance even when textual reasoning outputs are disabled at inference time. These results establish nuReasoning as a foundation for evaluating and improving robust, interpretable, reasoning-driven AD systems in realistic long-tail settings.

Distributed training is essential for scaling LLM training across thousands of GPUs. However, as distributed training requires complex implementations, they are prone to silent bugs, which do not produce explicit error signals but lead to in correct training outcomes. Common debugging practices based on monitoring training loss or gradient norm curves are slow or unable to detect bugs and also do not help localize bugs. We design and implement nnTrace, the first systematic differential testing system for detecting and localizing silent bugs in distributed training. nnTrace aligns intermediate tensors from distributed training with those from a trusted reference implementation. To properly compare the floating-point values in the corresponding tensors, we propose a novel mathematical analysis that provides a guideline for setting tolerances, enabling nnTrace to distinguish bug-induced errors from numerical errors. Experimental results demonstrate that nnTrace effectively detects 11 existing bugs and 3 new bugs in the widely used Megatron-LM framework. nnTrace is effective in various training recipes, including low-precision recipes involving BF16 and FP8. Notably, Megatron-LM has already adopted the method proposed by nnTrace in its development workflow. Our code is available at https://anonymous.4open.science/r/NECK-3C61/.

Haphazard inputs arise in online learning when feature availability varies across instances and the complete feature space is unknown in advance. However, the landscape of haphazard inputs research has been fragmented due to inconsistent data preprocessing, non-uniform evaluation metrics, limited coverage of streaming regimes and normalization, and model specific experimental code, making direct comparison across existing methods unreliable. We present haphazard, an open source Python library for reproducible benchmarking of haphazard input methods. The library provides an order preserving data pipeline with streaming normalization, unified evaluation, four streaming regimes, and shared interfaces for datasets, models, normalizers, and metrics. The current release supports 22 datasets, 11 model implementations, 5 normalization strategies, and 7 evaluation metrics, enabling systematic benchmarking across datasets and stream settings. By consolidating the experimental pipeline and exposing extensible interfaces for datasets, models, normalizers, metrics, and streaming regimes, haphazard provides a common reference point that can grow with future research on haphazard inputs. The anonymized source code is available at https://anonymous.4open.science/r/haphazard, and the PyPI package and docker container will be released publicly upon acceptance.

In this paper, we present gfnx, a fast and scalable package for training and evaluating Generative Flow Networks (GFlowNets) written in JAX. gfnx provides an extensive set of environments and metrics for benchmarking, accompanied with single-file implementations of core objectives for training GFlowNets. We include synthetic hypergrids, multiple sequence generation environments with various editing regimes and particular reward designs for molecular generation, phylogenetic tree construction, Bayesian structure learning, and sampling from the Ising model energy. Across different tasks, gfnx achieves significant wall-clock speedups compared to Pytorch-based benchmarks (such as torchgfn library) and author implementations. For example, gfnx achieves up to 55 times speedup on CPU-based sequence generation environments, and up to 80 times speedup with the GPU-based Bayesian network structure learning setup. Our package provides a diverse set of benchmarks and aims to standardize empirical evaluation and accelerate research and applications of GFlowNets.

Spreadsheets are among the most widely used tools for computations, and formulas are their core building blocks. Besides agentic spreadsheet tools, proactive formula suggestions enable significant productivity gains and are now available in popular spreadsheet software (Microsoft Excel and Google Sheets). Such suggestions pose interesting challenges: the right context must be collected and represented for a machine learning model, which must then be able to write a correct formula, in a way that is fast and cheap enough to trigger on every $\texttt{=}$ (or subsequent keystrokes for auto-completion) without taking users out of their editing flow. Surprisingly, there is no public benchmark for formula suggestions on real spreadsheets. In this paper, we therefore (1) introduce fxbench as a manually curated benchmark of 503 formula suggestion tasks based on Sheetpedia, (2) break down the formula suggestion problem into four capabilities---gather context, understand context, understand intent, write formula---that a formula suggestion system requires, and (3) evaluate existing and new approaches to understand bottlenecks in these capabilities that pose interesting research directions. Specifically, we annotate each benchmark with the cells that describe intent to determine the theoretical performance limit of a given context selection strategy, we evaluate performance of small and large models on different representations of context---including a dense format with high theoretical coverage at low token counts---and we fine-tune smaller language models to show that we can learn to understand such dense formats. Additionally, we perform quantitative and qualitative analysis on failure modes to understand bottlenecks in the formula writing capability---the best configuration only achieved 58.8\% correct suggestions.

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench, a suite of 5,500 test cases across 10 country-language pairs, comprising a Jailbreak Benchmark of country-grounded adversarial prompts and a Cultural Benchmark where local sensitivities are embedded within innocuous requests. Each item is constructed via a multi-stage pipeline that combines LLM-assisted discovery, automated validation gates, and dual independent native-speaker annotators per country. We report Attack Success Rate (ASR) alongside Neutral-Safe Rate (NSR) to separate principled refusal from non-engagement, and introduce the Cultural Sensitivity Rate (CSR) for recognizing embedded sensitivities. Evaluating 10 frontier and 27 local LLMs reveals two key findings. First, strong jailbreak robustness does not always come with strong cultural awareness, showing why the two should be evaluated separately. Second, local models exhibit a strong ASR–NSR trade-off (r = -0.81), suggesting that low attack success in several local models reflects non-engagement rather than safe refusal. XL-SafetyBench enables more nuanced, cross-cultural safety evaluation in the multilingual era.

Palmprint modality offers a privacy-preserving biometric solution, yet its deployment is hindered by the domain gap between controlled enrollment and unconstrained authentication. Existing datasets are largely restricted to controlled setups and fail to capture the compound variability of real-world environments. In this paper, we introduce X-Palm, a cross-domain dataset comprising 6,006 palm images from 103 individuals (206 hands). To the best of our knowledge, X-Palm is the first palmprint dataset providing novel paired-identity acquisition specifically designed to bridge the gap between reliably controlled multispectral enrollment and unconstrained mobile authentication while encompassing a broad spectrum of in-the-wild variability. Unlike existing datasets that focus on single to a few variations, X-Palm addresses the massive modality and environmental shifts encountered in practical deployments by capturing paired data for identities across two distinct domains: (1) a controlled Multispectral Palmprint setting using our custom-developed scanner, and (2) an unconstrained smartphone palmprint setting that is participant-driven, incorporating simultaneous variations in hardware, hand pose, illumination, background, camera-to-hand distance, perspective, and palm surface conditions (e.g., moisture and occlusions). Our extensive benchmarks of 12 SOTA models reveal that while existing methods achieve high performance on controlled data, they experience severe performance collapse on X-Palm. Conversely, models trained on X-Palm demonstrate consistent robustness across domains, positioning X-Palm as a valuable resource for training a model towards real-world, cross-domain generalization. Data access instructions and the related benchmarking codes are publicly available at: https://github.com/X-Palm/X-Palm-2026

Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively. Despite its importance, existing relevant benchmarks largely evaluate agents on pre-specified or synthesized files with limited real-world dependencies, leaving workspace-level evaluation underexplored. To this end, we introduce Workspace-Bench, a benchmark for evaluating AI agents on Workspace-Learning involving Large-Scale File Dependencies. We construct realistic workspaces with 5 worker profiles, 74 file types, 20,476 files (up to 20GB) and curate 388 tasks, each with its own file dependency graph, evaluated across 7,399 total rubrics that require cross-file retrieval, contextual reasoning, and adaptive decision-making. We further provide Workspace-Bench-Lite, a 100-task subset that preserves the benchmark distribution while reducing evaluation costs by about 70%. We evaluate 4 popular agent harnesses and 7 foundation models. Experimental results show that current agents remain far from reliable workspace learning, where the best reaches only 68.7%, substantially below the human+tool result of 80.7%, and the average performance across agents is only 47.4%. More details please refer to https://workspace-bench.github.io.

Oscillations and synchronization are widely believed to play a fundamental role in representation and computation. However, existing machine learning approaches based on synchronization dynamics have largely been confined to specialized settings such as object discovery, with limited evidence of scalability to standard vision benchmarks or logic reasoning tasks. We propose the \emph{Winfree Oscillatory Neural Network} (\emph{WONN}), a dynamical neural architecture based on generalized Winfree dynamics. \emph{WONN} evolves representations on the torus $(S^1)^d$ through structured oscillatory interactions, combining phase-based inductive biases with flexible and hierarchical interaction mechanisms instantiated as either fixed trigonometric mappings or learnable neural networks. We evaluate \emph{WONN} on image recognition and complex reasoning tasks, including CIFAR, ImageNet, Maze-hard, and Sudoku. Across these domains, \emph{WONN} achieves competitive or superior performance with strong parameter efficiency. \textbf{In particular, \emph{WONN} is, to our knowledge, the first synchronization-based oscillatory architecture to scale competitively to ImageNet-1K.} Furthermore, on Maze-hard, \emph{WONN} achieves \textbf{80.1\% accuracy using only 1\% of the parameters of prior state-of-the-art models}. These results suggest that structured oscillatory dynamics provide a scalable and parameter-efficient alternative to conventional neural architectures.

We introduce WildBox, a dataset and benchmark for monocular 3D detection of wildlife from drone video, comprising 237,505 3D bounding box annotations across seven African savanna species grouped into six benchmark classes. Annotations follow a KITTI/Omni3D-compatible format in a per-segment scale-normalised camera frame, with instance identities maintained across each segment. We evaluate two open-vocabulary monocular 3D architectures, OVMono3D-LIFT and DetAny3D, under zero-shot, ground-truth 2D box prompt, and supervised fine-tuning protocols. Open-vocabulary 2D foundation models provide usable zero-shot wildlife localisation (50.55 AP@50), but zero-shot 3D detection collapses to 0.00 AP across both architectures and every 2D-input condition tested, including ground-truth 2D box prompts—isolating the failure to the 3D stage. Fine-tuning on WildBox recovers performance to 8.68$\pm$0.47 AP-BEV@0.50 and 13.17$\pm$0.69 AP3D macro. Depth contributes 84\% of normalised Hausdorff distance after fine-tuning and over 99\% in zero-shot, identifying monocular aerial depth as the dominant open problem in this regime. A coarse-to-fine curriculum—pretraining on a merged zebra class before fine-tuning on the Grévy's/plains split—improves macro 3D performance with less total compute, with the largest gains on the two zebra subclasses. WildBox is released with video-level splits, evaluation code, and baseline checkpoints to enable progress in 3D wildlife perception from drone video.

A solid understanding of the predictive success of deep neural networks (DNNs) remains elusive. For example, while many data-dependent metrics exist that seek to predict model quality of DNNs, these metrics may be expensive to compute for large datasets and/or may be impossible to compute when training datasets are not released. A practical and effective predictor of model quality involves analyzing DNN weight matrices, as it is known that a heavy-tailed spectral distribution often correlates with strong model quality. As such metrics lack a rigorous statistical derivation, in this work we aim to understand why they perform well, by employing a probabilistic framework to derive the marginal likelihood for the trained weights of a DNN. Across large-scale convolutional DNNs and LLMs, we find that this marginal likelihood predicts model quality. To understand the role heavy-tailed spectra play in predictive performance, we derive the limiting log-marginal likelihood for spectra that follow the heavy-tailed High-Temperature Marchenko-Pastur (HTMP) distribution. We show that this limiting quantity is convex in a *heaviness* parameter, and we derive an optimal *heaviness* that empirically predicts over-fitting for large-scale DNNs during training.

Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler, making automated attribution increasingly important. We introduce Who&When Pro, a large-scale benchmark for automated failure attribution in agentic systems. Using a strictly controlled pipeline that injects a failure only after exactly replaying a successful prefix, we construct 12,326 failed trajectories with golden labels across 3 modalities and 26 benchmarks covering various scenarios. Beyond benchmarking, we conduct extensive experiments and analyses, revealing systematic patterns in how models attribute failures across modalities, protocols, and model families, and providing empirical guidance for future automated failure attribution systems.

Video Large Language Models (Video-LLMs) have made rapid progress on temporal video understanding, yet many fail at a basic perceptual primitive: signed image-plane motion direction. On simple videos of a single object moving left, right, up, or down, most Video-LLMs perform near chance, with above-chance cases largely attributable to prediction biases rather than genuine direction understanding. We call this failure directional motion blindness. We localize the failure by tracing motion direction information through the Video-LLM pipeline. Motion direction remains linearly accessible from the vision encoder, projector, and LLM hidden states, but the readout fails to bind this signal to the correct verbal answer option, revealing a direction binding gap. Although synthetic motion direction instruction tuning reduces this gap on the source domain, motion direction concept vector analysis shows that visual complexity weakens the signal magnitude and limits out-of-domain generalization. We introduce MODIRECT, a dataset family for motion direction instruction tuning and evaluation, and DeltaDirect, a diagnosis-driven, projector-level objective that predicts normalized 2-D motion vectors from adjacent-frame feature deltas. On MODIRECT-SYNBENCH, instruction tuning with DeltaDirect improves motion direction accuracy from 25.9% to 85.4%. On MODIRECT-REALBENCH, DeltaDirect improves real-world motion direction accuracy by 21.9 points over the vanilla baseline without real-world tuning data, while preserving standard video-understanding performance.

A central yet underexplored question in Multimodal Large Language Models (MLLMs) is where to connect — how visual information from a hierarchical vision encoder should be wired into the layer-wise semantics of a large language model. Mainstream MLLMs inject a fixed single-layer visual representation into the LLM and treat all LLM layers as a single consumer, ignoring that different layers demand different visual granularities. Recent multi-layer fusion methods either compress hierarchical features on the encoder side or rely on predefined sparse or hierarchical layer-to-layer connections, and therefore stop short of modeling adaptive cross-layer interactions between the ViT and LLM hierarchies. We address this gap with DGP (Dynamic Gated Pathways), a routing mechanism that establishes all-to-all connections between every ViT layer and every LLM layer, with each LLM layer dynamically gating its preference over visual layers conditioned on its own semantic state. Built on top of LLaVA-1.5-7B and 13B, DGP delivers consistent gains over the LLaVA-1.5-7B baseline (e.g., +4.2 on SQA$^{I}$, +3.3 on MM-Vet, +3.1 on VizWiz and LLaVA$^{W}$) and surpasses prior multi-layer visual fusion methods on most benchmarks. Layer-wise routing analyses further show that different LLM layers do select different visual granularities on demand, supporting both the effectiveness and interpretability of the proposed dynamic gated pathways. We will open-source code/weight/demo soon.

Tabular foundation models are used as off-the-shelf predictors for heterogeneous tabular tasks, but it remains unclear how they will perform on real genotype-to-phenotype tabular datasets, which carry unique challenges. One such challenge is ancestry-dependent non-stationarity in allele effect sizes (the effects of genetic variation on disease risk): the predictive contribution of a given genetic variant may change significantly across the ancestry spectrum. This is especially consequential for patients from ancestry groups that are underrepresented in existing datasets, because models that are unaware of this non-stationarity are more likely to perform poorly for them. The battery of synthetic tasks used to pretrain tabular foundation models does not capture this structure, and we show that it leads to systematic performance degradation. Using controlled hierarchical Gaussian-process stress tests, we demonstrate that both off-the-shelf TabICL and TabPFN are robust when ancestry dispersion in the data is low, but as dispersion grows, the latent ancestry-dependent non-stationarity of effect sizes becomes a first-order problem, and the predictive performance of both models deteriorates. We confirm the same pattern on All of Us (AoU) (a large biobank containing whole-genome sequencing and electronic health record (EHR) data spanning the ancestry spectrum) across an extensive panel of cancer phenotypes evaluated with the two leading tabular foundation models: TabICL and TabPFN. Holding the in-context training-set size, phenotype, and feature set fixed, ancestry-specific in-context tables, which are less dispersed in ancestry space, consistently outperform size-matched meta-ancestry tables, isolating ancestry dispersion as the driver of degradation. To address the failure without changing the base architecture, we construct two synthetic task families that explicitly encode ancestry-dependent effect drift and instruction-tune an off-the-shelf TabICL model on tasks sampled across both families. On held-out AoU evaluations covering cancer and respiratory disease phenotypes, the tuned model yields more stable performance across ancestry-distance bins and is especially strong in the bins farthest from the center of the in-context exemplars in ancestry space, that is, on subjects whose ancestry is most underrepresented among the provided exemplars. The paper contributes an evaluation protocol, a failure analysis, and two synthetic task families targeted at ancestry-dependent non-stationarity in precision-medicine tabular modeling.

This paper studies the convergence of the Optimistic Multiplicative Weights Update algorithm (OMWU) in two-player zero-sum games. Recent works have identified instances on which the last-iterate of OMWU can converge arbitrarily slowly, but understanding when and why this slow convergence occurs has remained open. In this work, we develop a new analysis framework that gives sharp, quantitative explanations for this behavior. Our analysis is based on viewing the algorithm's dual iterates as an *optimistic skew-gradient descent* with respect to an energy function. We prove over the dual iterates that energy is dissipative, and by establishing tight bounds on the magnitude of dissipation, our analysis quantifies the geometric bottlenecks that arise when the corresponding primal iterates are close to the simplex boundary. This further translates into a new linear last-iterate convergence rate in KL divergence on games with a unique and interior Nash equilibrium. Compared to prior work, this new rate contains a much sharper dependence on game-specific constants, and we prove this dependence is optimal. Moreover, these geometric insights further translate into new separations on *uniform* convergence rates for OMWU. On the one hand, we prove *constant lower bounds* on the uniform *best-iterate* convergence rate in KL divergence and Total Variation distance from Nash. On the other hand, we establish for the $2\times 2$ setting a new $\widetilde O(T^{-1/2})$ best-iterate rate in duality gap, improving substantially over prior work. Together, this shows in general that uniform convergence rate guarantees do not transfer across different measures of distance to Nash.

Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multiple large language models (LLMs) to improve reasoning and provide effective supervision to superhuman LLMs. However, increasing empirical evidence suggests that MAD may not outperform or even significantly underperform single-agent approaches (SA), raising doubts about the benefits of MAD. In this work, we investigate this issue by analyzing the incentive structures of popular MAD paradigms: (i) competitive MAD (CopMAD) where agents compete by holding opposing positions; (ii) consensus-seeking MAD (CosMAD) where agents are driven to seek consensus. We show that both paradigms suffer from debate hacking: CopMAD reduces to a cheap-talk game, where agents produce misleading messages to win the game, while CosMAD filters out informative disagreements for premature consensus. Consequently, agents in both CopMAD and CosMAD fail to jointly resolve the ambiguity and seek the truth. To this end, we introduce ColMAD, a collaborative protocol that reframes MAD as a non-zero-sum game to encourage agents to provide informative while truthful messages. Through extensive benchmarking on challenging tasks such as error detection, we show that ColMAD significantly outperforms previous MAD protocols up to 10 percentage points. Under the same budgets, ColMAD effectively brings non-trivial improvements over SA methods, implying that the protocol design is critical to realizing the potential of MAD.