NeurIPS 2026 论文列表

Adaptive learning requires distinguishing environmental volatility from observation stochasticity, two sources of uncertainty that demand opposite adjustments to the learning rate but inflate experienced variance similarly. Disentangling them is computationally difficult with no tractable closed-form solution. Particle-filter methods are the natural tool for this kind of joint inference, but their stochastic likelihoods and non-differentiable objectives force derivative-free fitting protocols and discourage the individual-difference analyses central to cognitive modeling, where small effect sizes leave little room for additional estimator noise. We introduce the Categorical Bayes Filter (CBF), a deterministic alternative that preserves the conditional structure of recent particle-filter accounts but replaces the stochastic outer layer with a categorical distribution on a quantile grid parameterized through differentiable Beta quantile functions. The procedure performs evidence maximization with an exact, deterministic marginal likelihood that is fully differentiable in the grid parameters. In a volatility-stochasticity task with N = 643 participants, fitted CBF dispersion parameters reveal a cross-over phenotyping pattern between volatility-blind and stochasticity-blind subjects that is not recoverable from particle-filter parameters fit to the same data under a state-of-the-art protocol. The deterministic structure also yields a trial-by-trial ambiguity signal that predicts response times not used in fitting. More broadly, the approach opens individual-level analyses in cognitive modeling and computational psychiatry that stochastic methods have effectively foreclosed.

Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose limitation in downstream AI applications. In practice, enforcing this principle remains challenging, as released data can be trivially fed into arbitrary models beyond its declared intent. Existing approaches attempt to mitigate this risk by either perturbing data or retraining models to limit unintended use. These strategies, however, offer no protection against inference by unknown or externally trained models, or fundamentally rely on control over the training or deployment. In this work, we introduce non-transferable examples (NTEs), recoded data that act as a task-level "ciphertext" decodable only by a designated model. Where adversarial examples exploit sensitive input directions, NTEs use the complementary insensitive subspace: a training-free, data-agnostic recoding within a model-specific low-sensitivity subspace preserves the authorized model's outputs while degrading unauthorized ones through subspace misalignment. We establish formal bounds certifying output fidelity for the authorized model and showing unauthorized degradation scales with measurable spectral misalignment between models. Empirically, NTEs preserve authorized-model performance across diverse vision backbones and vision-language models, while unauthorized models collapse even under adaptive reconstruction attacks. These results establish NTEs as a practical means to preserve intended data utility while preventing unauthorized exploitation. Our source code and visual demos are available at: https://github.com/model-specific/non-transferable-examples.

Within the landscape of inference-time scaling methods for foundation models, a _width-based_ approach to scaling—which involves the insertion of \ tokens in the input stream to delay model responses—offers a unique advantage by increasing model expressivity while remaining highly parallelizable at both training and inference. The existing literature on training models to utilize \ tokens relies on the standard cross-entropy objective in which the model output is read out and evaluated only at the final step of a pause sequence. This approach provides no mechanism for the model to regulate its own processing or to signal readiness to respond, treating the additional compute steps as a static barrier rather than a resource to be used adaptively. We propose a supervised loss, _Catch Your Breath_ (_CYB_), framed as a sequential-decision problem, that trains a model to dynamically and autonomously scale the number of compute steps used for each input token. The model indicates the need for additional compute steps by emitting a special \ output, delaying its response via a \. The model can abstain multiple times to obtain longer delays. Our experiments demonstrate that CYB significantly outperforms standard cross-entropy when introduced either in pretraining or fine-tuning, reducing perplexity and enhancing downstream accuracy with no additional computational or memory cost.

Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. Current Multimodal Large Language Models (MLLMs) are trained directly on complex downstream tasks. Does it guarantee their performance on these foundational visual capabilities? To systematically investigate this gap, we introduce VisFactor, a benchmark that digitizes 20 vision-centric subtests from FRCT, a well-established cognitive psychology assessment spanning four domains of human visual cognition. Furthermore, we design algorithms to automatically construct and validate unlimited test cases with controllable difficulty. Using VisFactor, we evaluate 39 frontier MLLMs, including both proprietary (e.g., GPT, Gemini) and open-source (e.g., LLaMA, Qwen) models. The best model achieves a score of only 55.9%. Analysis reveals good internal consistency (Cronbach's alpha = 0.94) and construct validity (compared to existing vision benchmarks). Models consistently fail on tasks such as mental rotation, spatial relation inference, and figure–ground discrimination, regardless of model size or prompting strategy. These findings suggest that performance improvements on existing general benchmarks might represent castles in the air instead of a genuine mastery of human-like visual cognition.

Many real-world problems demand exact constraint satisfaction to be meaningfully solved, yet existing neurosymbolic methods face a stark trade-off: those that guarantee satisfaction fail to scale, while those that scale must resort to approximation. Meanwhile, traditional deep learning approaches offer no satisfaction guarantees at all. In this paper, we propose Casper, a neurosymbolic layer that simultaneously (i) guarantees constraint satisfaction, (ii) scales at inference time, (iii) is fully automated, requiring no problem-specific engineering, and (iv) is fully differentiable, making it composable with any neural predictor both at training and at inference time. Casper casts constraint satisfaction as a closed-form Euclidean projection onto the constraint-feasible region, computable in a single forward pass. Experiments across MNIST arithmetic (up to 1024 digits), Sudoku solving, and Warcraft pathfinding show that Casper is the only method that produces guaranteed-valid outputs at scale: on 30×30 Warcraft grids, exact baselines time out and approximate ones produce valid paths less than 7% of the time, while Casper produces them 100% of the time.

Reinforcement learning (RL) is a promising way to improve the clinical reasoning abilities of large language models (LLMs), but current pipelines often rely on expert-labeled questions or costly synthetic-data generation. Meanwhile, the medical literature offers a wealth of high-quality unlabeled documents, including clinical case reports that trace the full clinical course from initial presentation to final treatment decisions. We study whether document-grounded self-play can convert these reports into effective RL training signals. We identify two challenges that limit existing self-play methods in this setting: knowledge-point fixation, where the proposer repeatedly asks about a narrow set of salient clues in a source report, and difficulty-quality mismatch, where appropriately difficult questions may still be poorly formed or shallow, limiting their value for reasoner training. To address these challenges, we propose CasePlay, a self-play framework with two key components: (a) a Knowledge-Conditioned Proposer, which anchors question generation to case-specific knowledge points so that questions draw on a broader range of evidence from the source report; and (b) a Rubric-Judge Reasoner, which augments answer-accuracy feedback with rubric-based quality feedback on clue integration, reasoning depth, and option quality, guiding the proposer toward reasoning-intensive questions that better support reasoner training. Extensive experiments across seven medically related benchmarks demonstrate that CasePlay outperforms existing self-play baselines and improves the SFT warm-start model by 3.0 points on average, highlighted by a 6.9-point gain on LiveClin. This approach offers an effective path toward continually improving medical reasoning ability through self-play RL. Code is available at \url{https://anonymous.4open.science/r/CasePlay}.

Multimodal Large Language Models (MLLMs) have shown strong performance on medical public benchmarks, but existing evaluations remain limited as clinically grounded assessments because they often rely on isolated inputs lacking study-level structure and simplified, recognition-style tasks that are far from real diagnostic workflows. We introduce \textbf{CardioLens}, a leakage-resistant evaluation testbed using multi-sequence Cardiovascular Magnetic Resonance (CMR), constructed from private hospital archives via a rigorous report-to-QA construction and verification pipeline. CardioLens is built from 473,896 slices and 13,494 verified QA pairs across 4D Cine, LGE, perfusion, and T2-weighted imaging, and evaluates three stages of CMR interpretation: image understanding, report generation, and disease diagnosis. Across 24 state-of-the-art MLLMs, CardioLens reveals a substantial clinical reality gap. Models perform poorly overall, with performance degrading along the real CMR workflow. Confusion analysis further reveals a category-collapse failure mode: models often default to frequent abnormal categories rather than reliably telling distinct clinical findings. To rule out MLLM-compatible input construction as the failure cause, we compare random, clinically-motivated, and data-driven selection protocols under different slice budgets; performance changes only marginally, typically by about 1\%. Explicit reasoning prompts also fail to rescue performance, often driving models toward conservative predictions rather than improving visual evidence use. These results show that current MLLMs remain far from reliable CMR interpretation, where clinical decisions require integrating distributed evidence across sequences, views, and temporal phases. By exposing where and how current MLLMs fall short, CardioLens provides a clinically grounded testbed for developing the next generation of MLLMs toward real-world clinical depolyment.

Characterizing the properties of neuronal cell types is central to understanding brain function. Yet, biophysically realistic neuron models remain difficult to scale to large populations while preserving the richness of cellular dynamics and within-cell-type variability. We present a cell-type-specific neural-operator framework for scalable neuronal population modeling. Rather than training separate surrogate models for individual neurons, the proposed framework learns a shared operator across multiple modeled neurons from the same cell type, conditioned on biologically interpretable electrophysiological features. This enables efficient generation of large ensembles of somatic voltage responses while preserving variability across cells and model configurations. We evaluate the approach using membrane dynamics metrics, action potential waveform metrics, spike timing accuracy, input-output firing relationships, and electrophysiological feature distributions. Our framework reproduces subthreshold membrane dynamics, spike waveforms, and firing-rate responses across major cortical inhibitory neuron types, while accurately preserving spike timing despite the sensitivity of threshold-crossing dynamics. The predicted electrophysiological feature distributions show strong agreement with detailed simulator outputs and human experimental recordings, including high explained variability in properties such as inter-spike intervals, firing frequency, action-potential shape, and post-spike recovery. By enabling fast ensemble simulation of cell-type-specific neuronal responses, the proposed framework provides a scalable tool for studying cellular diversity, probing variability near functional thresholds, and generating synthetic but biophysically grounded neuronal populations.

Query clustering organizes queries into groups that reflect shared latent capability demands, enabling capability-aware LLM evaluation. Existing clustering methods, which primarily rely on semantic taxonomies or embeddings, often fail to capture such latent capability requirements due to a misalignment between surface-level semantics and actual model performance. We propose ECC, an algorithm that calibrates prior semantic embeddings using limited posterior model comparisons to bridge the gap between surface-level semantics and latent capability requirements. ECC characterizes each cluster through a capability profile parameterized by a Bradley-Terry model and uses trainable mixture weights to accommodate queries with mixed capability demands, jointly learning a flexible, capability-aware clustering structure that supports query-specific inference of LLM capabilities. Extensive quantitative and qualitative evaluations demonstrate that ECC significantly improves LLM capability ranking quality, outperforming human-labeled and embedding-based baselines by an average of **17.64** and **18.02** percentage points, respectively, and proves effective in downstream tasks such as query routing.

Knowledge editing has emerged as a promising approach for efficiently updating embedded knowledge in large language models (LLMs). It first computes an ideal target hidden state that steers the LLM toward the new output, and then edits the model parameters so that the original hidden state is mapped to this target. While most existing methods focus on the second stage of parameter editing in preserving other knowledge, we find that the upstream construction of the target hidden state also plays an important role in allocating the model's limited capacity space. We first establish a theoretical connection between interference in the parameter space and interference between target hidden states, showing that the two are positively correlated. Building on this insight, we propose a simple yet effective $\ell_1$ regularization method that prunes away unnecessary ``tentacles'' of each knowledge vector, retaining only the essential components. With fewer extraneous tentacles, each edit affects less other knowledge, enabling better coexistence. Extensive experiments across multiple LLMs and benchmark datasets verify the effectiveness of our method.

Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known to induce forgetting, especially in the ubiquitous use-case of leveraging third-party pre-trained models, which is typically understood as a loss of parametric or factual knowledge. We argue that this accuracy-centric view is insufficient for modern foundation models and instead define forgetting as systematic model drift that degrades behavior and user experience. In this context, we introduce __CapTrack__, a capability-centric framework for analyzing forgetting in LLMs that combines a behavioral taxonomy with an evaluation suite centered on capability-specific metrics. Using CapTrack, we conduct a large-scale empirical study across post-training algorithms, domains, and model families, including models up to 80B parameters. We find that forgetting extends beyond parametric knowledge, with pronounced drift in robustness and default behaviors. Instruction fine-tuning induces the strongest relative drift, while preference optimization is more conservative and can partially recover lost capabilities. Differences across model families persist, and no universal mitigation emerges.

Many prediction problems involve a hidden predictive state: a latent task, environment, rule, or data-generating mechanism that changes the query-optimal act. For a fixed query, recovering the full hidden predictive state is often stronger than necessary. The relevant target is the Bayes-act distinction among hidden predictive states that preserves oracle-gain adaptation. This question is central for in-context learning (ICL): a prompt may reveal part of an unseen task or rule, but an ICL system needs only to recover the prediction-relevant quotient state label for the query. We formalize this target through the canonical predictive quotient (CPQ), a problem-relative Bayes-act quotient of hidden predictive states. The theory characterizes the value of adaptation, the quotient that preserves full oracle gain, the sharp zero/positive-gain boundary, and a Bayes barrier showing why context-only prediction cannot recover a positive oracle gain at the risk level. We give two exact examples. A finite-state example makes the quotient structure, sharp positivity boundary, and a strict-loss mechanism explicit. A linear-Gaussian prior-family witness gives closed forms for a collapsed Gaussian baseline and a state-aware oracle, a restricted zero-gain boundary, and an exact prediction-level disagreement identity for the restricted gain. Together, the results give a decision-theoretic target for ICL: not full latent complexity, but the prediction-relevant quotient state label. We support the theory with exact checks, realized bridge experiments over prediction-relevant quotient state labels, and external validity tests on released pretrained in-context predictors.

Dynamic Sparse Training (DST) is an effective paradigm for sparse to sparse training of neural network connectivity under a fixed parameter budget. Recent advances in network-science for AI introduced epitopological learning methods, such as Cannistraci-Hebb Training (CHT), demonstrating that network automata applied to the mere network topology enables gradient-free predictions of the sparse connectivity evolution that can trigger significant increase in task performance. However, these methods were currently developed for standard MLP-like fully-connected architectures and need significant rethinking to be extended to convolutional neural networks (CNNs) due to element-wise weight sharing and spatially repeated interactions. In this work, we bridge this gap by introducing epitopological learning DST for CNNs through channel-wise network modeling to address the prohibitive complexity of element-wise modeling, which treats each kernel-channel as a single network node. Results show orders-of-magnitude improvements in time complexity of link-regrowth when applied at channel-level with respect to element-level. We also enhance the channel-wise formulation with lightweight contextual modulation to improve expressivity. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet with ResNet and VGG architectures demonstrate that our method achieves performance comparable to dense training using only 30% of the parameters, which significantly reduces computational cost. Furthermore, our approach improves robustness under noisy inputs. These results highlight the effectiveness of topology-aware sparse training and the benefit of decoupling graph construction from sparse update rules in convolutional networks.

Active computer vision promises efficient, biologically plausible perception through sequential, localized glimpses, but lacks scalable general-purpose architectures and pretraining pipelines, leaving Active-Vision Foundation Models (AVFMs) underexplored. We introduce CanViT, the first task- and policy-agnostic AVFM. CanViT uses scene-relative RoPE to bind a retinotopic Vision Transformer backbone and a spatiotopic scene-wide latent workspace, the canvas. Efficient interaction with this high-capacity working memory is supported by Canvas Attention, a novel asymmetric cross-attention mechanism. We decouple thinking (backbone-level) and memory (canvas-level), eliminating canvas-side self-attention and fully-connected layers to achieve fast sequential inference and scalability to high output resolutions. We propose a label-free active vision pretraining scheme, policy-agnostic passive-to-active dense latent distillation: reconstructing scene-wide DINOv3 embeddings from sequences of low-resolution glimpses with randomized locations, zoom levels, and lengths. We pretrain CanViT-B from a random initialization on 13.2 million ImageNet-21k scenes--an order of magnitude more than previous active models--and 1 billion random glimpses, in 166 hours on a single H100. On ADE20K segmentation, a frozen CanViT-B achieves 38.5% mIoU in a single low-resolution glimpse, outperforming the best active model's 27.6% with 20x fewer inference FLOPs as well as its FLOP- or input-matched DINOv3 teacher. Given additional glimpses, CanViT-B reaches 45.9% ADE20K mIoU. On ImageNet-1k classification, CanViT-B also sets a new active-vision state of the art, with 84.5% top-1 accuracy after fine-tuning. CanViT generalizes to longer rollouts, larger scenes, and new policies. Our work narrows the wide gap between passive and active computer vision, demonstrating the potential of task- and policy-agnostic AVFM pretraining.

Relational out-of-distribution errors are easy to describe and hard to evaluate cleanly. An image may be natural, a caption may be fluent, and all mentioned objects may be common, yet the caption may describe the wrong relation in the image. Many evaluations intended to test this behavior can be solved without checking the pairing at all, because negatives differ in caption style, template, length, object frequency, or image statistics. We propose counterfactual pairing cycles, a blocked evaluation primitive that reuses the same two images and the same two captions on both sides of the comparison, changing only which image is paired with which caption. This makes image-only, text-only, and additive component shortcuts cancel exactly in finite samples. The same contrast also gives a training loss for relational outlier exposure and a diagnostic for bilinear vision-language scores. Across synthetic controls, GQA, and COCO, cycles separate coarse image-caption matching from stricter role-binding failures. In a shortcut-contaminated COCO outlier-exposure stress test, a model selected by a perfect shortcut validation AUROC transfers poorly to exact relational cycles, while cycle training improves CycleAcc from \(0.576\) to \(0.911\). The main lesson is simple: to test whether a model understands a pairing, the benchmark should keep the parts fixed, change the pairing, and ask only about coupling.

Legal judgment prediction has made substantial progress in recent years, yet existing work evaluates whether models reach correct conclusions rather than whether they reason correctly. The core of legal decision-making is the mapping of case facts to the elements of an applicable legal provision, a step that prior benchmarks neglect. We introduce the first benchmark for evaluating legal reasoning, built on 375 judgments of the European Court of Human Rights (ECtHR) discussing Art. 11 ECHR on freedom of assembly. We exploit that the court routinely splits the decision in a stage reporting the facts of the case, and an evaluation stage in which it uses these facts selectively for justification. We give the (preprocessed) list of facts to 10 downstream LLMs and evaluate their justifications. The pipeline is validated by three expert legal annotators. Downstream models are reasonably accurate in predicting whether Art. 11 has been violated, and which elements of doctrine are critical, but perform substantially worse at attributing specific facts to doctrinal elements. Essentially they make the right decision, but for the wrong reasons. This weakness is invisible under standard evaluation metrics. Our benchmark, pipeline, and evaluation framework are released. They can easily be adapted to any legal rule that follows the Civil law tradition, i.e. to legal reasoning that requires the mapping of facts to an abstract legal rule.

AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate capabilities, rank systems, select informative examples, and diagnose benchmark quality. However, AI benchmark data often departs from the data regimes encountered in human testing, for which standard IRT estimation tools were originally developed: these benchmarks typically involve fewer evaluated models, far more items, and capability distributions that may be skewed, clustered, or multimodal. We examine how these regime mismatches challenge the reliability of IRT modeling for AI evaluation. Using item parameters and capability distributions derived from six widely used LLM benchmarks, we simulate response matrices under three common IRT models and compare four estimators used in recent benchmark studies: marginal maximum likelihood, Markov chain Monte Carlo, variational inference, and a neural pseudo-Siamese estimator. Across 18,000 simulation runs, we systematically evaluate computational feasibility, scalability, and the reliability of IRT inferences about model rankings, predicted performance, and item characteristics. Results show that classical estimators can become computationally infeasible for large benchmarks, whereas scalable estimators can produce unreliable item-level and ranking inferences with small or non-normally distributed model sets. This study identifies when latent trait models reliably support or risk distorting AI benchmarking claims, and what sample sizes and diagnostics are needed for trustworthy use.

Image Manipulation Localization (IML) is commonly formulated as a fully supervised learning task that estimates the optimal manipulation mask $y$ for a given image $x$. In this work, we first reveal the latent nature of artifacts and thus reinterpret IML as a latent-variable problem, $P(y| x)=\int P(y|z) P(z|x)dz$, where $z$ denotes the artifacts. Following this interpretation, we pinpoint the cause for the current IML models' insufficiency as their implicit artifacts modeling strategy, highlighting the necessity of modeling $z$ in an explicit manner. Without direct labels, feature disentanglement is the most appropriate solution for this explicit modeling. Accordingly, we propose a two-stage learning paradigm with the Pairwise Artifacts Learning (PAL) and Standard Localization (SL) phases to estimate $P(z|x)$ and $P (y|z)$ via edit relations. To support our edit-relation-based learning, we further curate EditGroup-45K, a source-anchored dataset organized into edit groups for pair construction. Extensive experiments show that our PAL paradigm yields consistent improvements across diverse IML architectures, and empirical analyses further verify that PAL does capture artifacts explicitly through feature disentanglement. Code and dataset will be publicly available.

Since Vision-Language Models (VLMs) are the core of the perceptual and reasoning capability in Vision-Language-Action models, which are deployed in environments shared with humans, evaluating VLMs' safety reasoning from video is critical for preventing human harm. Current video-based benchmarks, however, evaluate only whether a model can recognize dangers that are already visible, and overlook two capabilities that VLMs require: reasoning under hierarchical principles in which human safety takes precedence over obedience to user instructions, and anticipating harm rather than identifying it after it has occurred. We introduce VESPER, a video benchmark that targets both capabilities by scenarios in which a robot is executing a user-assigned task when a person unexpectedly moves into harm's way, requiring the model to predict the potential harm and decide whether to continue or stop. The benchmark comprises 458 videos covering matched safe and dangerous variants, built through a human-in-the-loop pipeline from diverse taxonomies. We evaluate 21 VLMs, and the results indicate that the current VLMs fail to properly decide the actions under such a scenario.