NeurIPS 2026 论文列表

Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels. This limits researchers' ability to determine which problems are suitable for these models, isolate the factors that drive their performance or lead to failures, or uncover which algorithms perform well. In this paper, we develop synthetic benchmarks for concept-bottleneck models, focusing on their two main use cases: decision support, in which models assist humans in making better decisions, and automation, in which models handle routine tasks without supervision. Our benchmarks can generate labeled datasets while controlling for properties that affect performance, including data modality, concept choice, annotation quality, and completeness. We demonstrate how the benchmarks can be used to evaluate representative classes of concept bottleneck models. Our demonstrations show how the benchmarks can diagnose failure modes and guide follow-up testing.

Many decision making procedures that make use of probabilistic predictors assume that training on new data acts as Bayesian conditioning. When this assumption breaks, the downstream procedure can perform poorly. E.g. we show that in active learning, incoherent updates cause the procedure to prefer to acquire suboptimal points. To quantify how far a model's predictive updates depart from conditioning, we introduce the _incoherence ratio_. We empirically find that amortised predictors such as TabPFN can be more coherent than standard parametric approximations to Bayesian inference. In synthetic active learning experiments, more coherent models acquire better data, an effect not attributable to better predictive performance. In many tasks, decisions depend on a predictor only through its induced action. We therefore introduce action coherence, a decision-theoretic relaxation that measures only the incoherence affecting that action. These diagnostics make coherence testable and quantifiable, enabling incoherence to be diagnosed and addressed.

AI systems must often maintain bounded memory of unbounded interaction histories. However, optimizing the memory representation, and its updates, for downstream task utility is difficult for standard reinforcement learning (RL) due to severe credit assignment bottlenecks induced by sparse, delayed rewards. We introduce MaxIM (Maximally Informative Incremental Memory), a framework that formulates incremental summarization as a capacity-constrained, information-theoretic reward-shaping problem. Grounded in value suboptimality bounds, we prove that minimizing sequential information loss requires maximizing the predictive log-likelihood of future, task-relevant targets (predictive sufficiency). We introduce a recursive consistency condition to ensure summaries are grounded by maximizing mutual information with the observed history. We mitigate credit assignment issues with a parameterized critic that computes step-wise variational lower bounds for dense reward shaping. Empirical evaluation on long-horizon benchmarks shows that MaxIM outperforms state-of-the-art baselines on comprehensive autorater metrics and downstream task utility, without expensive human preference labels.

Natural gradient descent is a theoretical pillar of second-order optimization for neural networks. Existing implementations either rely on structural approximations of the curvature matrix or incur substantial computational and memory overhead. Direct application remains difficult at deep-network scale. We build an optimizer based on an unbiased stochastic estimator of the Fisher information matrix. It employs a truncated exponential moving average metric with damping, which we call the Stochastic Truncated Metric (STM), and is otherwise closely aligned with the original natural gradient. This gives a matrix-free parameter update with strictly $O(Kd)$ time and memory per step, where $K$ is a small constant. It is applicable across network architectures without layer-wise assumptions. We bound the error induced by the finite-memory truncation. We show that STM is stable and efficient on vision and language benchmarks.

Single-step retrosynthesis prediction serves as the core operational unit for automated synthesis planning and remains a fundamental computational challenge in pharmaceutical design. While a critical prior in organic chemistry is that chemical reactions typically preserve the majority of the molecular scaffold, current template-free deep learning models struggle to effectively exploit this characteristic. Existing methods attempt to exploit this by minimizing sequence-level edit distance through carefully chosen graph traversal orders. However, this structural correspondence is only indirectly induced and remains highly sensitive to imperfect traversal heuristics, which limits its effectiveness for complex transformations. To address this limitation, we introduce the Matching-while-Decoding paradigm, replacing implicit sequence alignment with direct structural supervision. We operationalize this paradigm within a graph-to-sequence architecture that explicitly maps generated reactant tokens back to the input product graph during decoding. Furthermore, our hierarchical autoregressive formulation utilizes a custom causal attention mask to enable highly efficient, single-pass parallel training. Extensive experiments across the USPTO-50K, USPTO-MIT, and USPTO-FULL benchmarks reveal a critical accuracy and robustness trade-off in existing methodologies, where models either over-rely on augmentation or fail to leverage it. Our approach uniquely resolves this bottleneck by delivering highly competitive canonical accuracy while scaling exceptionally well with test-time augmentation, establishing new state-of-the-art records on USPTO-MIT and augmented USPTO-FULL. By providing this balanced stability across diverse inference protocols, our approach emerges as a highly promising foundation for dependable single-step retrosynthesis prediction.

Pixel-space diffusion models have recently seen a revival in image generation, yet their training remains less efficient than that of their latent-space counterparts. Existing methods reduce this cost by equipping diffusion models with external representations from clean images. In contrast, representation consistency training, a new generative pretraining paradigm, stands out as it eliminates the need of any off-the-shelf semantic encoders. It proposes pre-training the diffusion model to simultaneously capture meaningful visual semantics from clean images while aligning them with data points across various noise levels. Nevertheless, its training depends on contrastive learning with hand-crafted augmentations. This introduces strong semantic prior into the pretraining, limiting model performance when transferred to downstream target distributions that substantially deviate from the pretraining manifold. To address this, we propose Masked Pixel-space Generative Pretraining (MPG), an augmentation-free framework based on masked image modeling. MPG trains the encoder to recover masked image area and aligns those predictions with samples of different noise levels. To measure the performance of pretrained model, we further introduce NC-CKNNA, a metric that quantifies the semantic structure consistency across different noise levels. Under the same architectures and fine-tuning settings, MPG consistently produces better generation performance across seven downstream datasets, while retaining competitive generation quality on ImageNet-256. These results suggest masked generative pretraining as a practical alternative for training pixel diffusion models.

Existing unified 4D reconstruction and point tracking approaches typically rely on heuristic interpolations or just predict at integer timestamps, lacking kinematic coherence and failing to model dynamics at any arbitrary timestamp. In this paper, we propose Uni4R, a framework that unifies these tasks by learning continuous velocity fields through the synergy of Optimal Transport (OT) and Ordinary Differential Equation (ODE). Importantly, this continuous velocity field acts as a kinematic prior that mutually benefits both 4D reconstruction and point tracking. Specifically, we propose the Flow Matching Guided Decoder (FMGD). A global velocity branch first extracts anchor features that capture the global dynamic state of the sequence. Then, FMGD leverages Flow Matching (FM) theory to formulate a probability path defined by OT on the anchor feature manifold, instantiating it as FM-guided velocity features for velocity prediction. This establishes a robust kinematic inductive bias. Meanwhile, a point reconstruction branch provides geometric features. The local velocity prediction module then joint above features and time embeddings, to decode velocities at arbitrary timestamps. To overcome the absence of high-quality ground-truth velocities in fractional frames, we propose an integral-consistency training strategy. This strategy uses an ODE solver to integrate velocities to recover target pointmaps, enabling the model to be supervised end-to-end directly from integer timestamps. Experimental results demonstrate that Uni4R achieves SOTA performance in both 4D reconstruction and point tracking, and achieves SOTA in our new kinematics-aware benchmark at continuous time.

We study the problem of multiclass classification within the framework of *marginal-nonuniform* learning, where the constants in the learning rate may depend on the unknown marginal distribution generating the unlabeled data, but not on the target concept. This notion naturally lies between classical PAC learning, where the constants are independent of both the marginal distribution and the target concept, and more recent universal learning, where the constants may depend on both. We give a complete characterization of the optimal marginal-nonuniform learning rates, establishing a fundamental trichotomy: exponential, linear, and arbitrarily slow rates. This characterization is witnessed by a new combinatorial dimension, termed the *uncentered DS-eluder dimension*. Technically, a key ingredient in the upper-bound proofs is a set of new *distributional exhaustion* lemmas that exploit the sequential nature of this dimension and may be of independent interest.

GANs are appealing because they generate sharp images in a single forward pass. Recent works have stabilized GAN training, but FID may still plateau on diverse datasets like ImageNet-256 because the discriminator's activation magnitudes increase through training. We trace this pathology to the discriminator's incentive to sharpen its decision boundary by rescaling activations rather than by finding better features. Then, building on R3GAN, we treat magnitude preservation as a first-class architectural target across the network: $\ell_2$ weight normalization with centering, magnitude-preserving LReLU and residuals, forced post-update normalization, and feed-forward classifier heads. Across a roadmap of configurations, we perform diagnostic ablations to clarify what does and does not work and why. The resulting models reach FIDs of 2.20 @ 17 M parameters, 1.63 @ 60 M, and 1.52 @ 130 M on class-conditional ImageNet-256. At 1 NFE, this is substantially more efficient than competing diffusion and autoregressive methods, and than prior GAN baselines too (e.g., 10$\times$ more efficient than StyleGAN-XL for similar FID). In sum, our work presents a new SOTA in FID/parameter efficiency derived from simple adversarial training with well-behaved magnitude preserving layers.

MSConsensus: A Hundred-Million-Scale, Batch-Effect–Suppressed Dataset and Benchmark for Proteomics Machine Learning Machine learning for proteomics is bottlenecked by three coupled and under-explored challenges: (i) noisy mass-spectrometry (MS) data dominated by instrument- and protocol-specific batch effects, (ii) slow data loading from legacy XML- and text-based file formats, and (iii) a fragmented evaluation landscape that prevents meaningful cross-study comparison. Each silently constrains what proteomics models learn, how efficiently they train, and how reliably they are compared. We address all three with MSConsensus, a multi-task dataset and benchmark built natively for proteomics ML. MSConsensus contains 110,209,043 consensus spectra distilled from 1.01 PB of public PRIDE data spanning 1,500 repositories and all major Orbitrap and timsTOF platforms, with per-peak ion annotations and stratified ML splits across instruments, species, and post-translational modifications. Unlike single-representative spectral libraries (MassIVE-KB v2, NIST, ProteomeTools), MSConsensus uses a new Weighted-Score Binning (WSBIN) algorithm that emits multiple consensus spectra per (peptide, charge) cluster, preserving intra-cluster variance required by contrastive and representation-learning objectives while suppressing context-specific artifacts. Across five held-out PRIDE repositories and four search engines (Comet, MetaMorpheus, MSFragger, Sage), WSBIN improves signal-to-noise ratio by an average of +3.86 dB (range +0.57 to +10.47 dB) without sacrificing protein, peptide, or PSM identification counts. To eliminate the I/O bottleneck during model training, we pair MSConsensus with MSCompress and a new msz binary container. msz compresses to 45% of mzML size losslessly and supports 25,378 random-access spectra/sec — 3.2× HDF5 — through a drop-in PyTorch / JAX dataloader. A unified public leaderboard standardizes evaluation across three core tasks—spectrum embedding, intensity prediction, and de novo peptide identification—and we report results for ten widely used systems (Casanovo, InstaNovo, Prosit, MS²PIP, GLEAMS, Spec2Vec, Comet, MetaMorpheus, MSFragger, Sage). Replacing raw training data with MSConsensus stabilizes Prosit's spectral angle on a never-before-seen 2025 instrument (PXD053296) from 0.6964 to 0.8137 and improves Spec2Vec top-1 retrieval from 39.2% to 46.7% (+19.0% relative). By jointly addressing scale, batch-effect suppression, I/O efficiency, and standardized evaluation, MSConsensus provides foundational infrastructure for training, evaluating, and comparing future proteomics models. The dataset is released on Harvard Dataverse (doi:10.7910/DVN/NUCT4N) under CC BY 4.0; MSCompress, MSDatasets, preprocessing pipelines, and baseline scripts are released on GitHub under Apache 2.0, with Docker containers for reproducibility.

Accurately identifying metabolites (small molecules) from mass spectrometry data remains a core challenge in metabolomics, with broad applications in drug discovery, environmental analysis, and clinical research. We address the Molecule Retrieval task, which consists in recovering the chemical structure of a metabolite from its MS/MS spectrum given a set of candidate molecules. While the recent release of benchmark datasets such as MassSpecGym and Spectraverse has considerably accelerated the development of novel machine learning approaches, the complexity of data preprocessing pipelines and the lack of unified implementations make methods and results difficult to reproduce and compare. We make three contributions. First, we propose a unified framework encompassing recent approaches based on representation alignment and contrastive learning. Second, we introduce MSAlign, inspired by multimodal alignment in vision-language models, which learns a shared representation space by aligning two frozen foundation models (DreaMS for mass spectra and ChemBERTa for molecules) through lightweight MLP projections trained with a candidate-based contrastive objective. MSAlign is simple to implement, fast to train and consistently outperforms existing approaches across all benchmarks. Third, we investigate a long-standing evaluation problem: data splitting strategies in molecule retrieval implicitly trade off data leakage against domain shift. We formalize this tension by introducing a quantitative measure of distribution shift, and use it to evaluate splitting strategies in existing benchmarks. All datasets, splits, candidate sets, and a unified implementation of MSAlign and baselines are publicly released to support reproducible research.

Multimodal dynamic graphs are pervasive in real-world applications, where nodes and edges are accompanied by multimodal signals, including text and images. Despite their practical importance, benchmarks and methods that explicitly study multimodal learning in dynamic graphs remain scarce, hindering the full understanding and effective utilization of multimodal information for downstream tasks. To address this gap, we introduce MM-DyGraph, to the best of our knowledge, the first benchmark for multimodal dynamic graph learning, consisting of diverse real-world datasets with fine-grained temporal graph evolution and rich multimodal attributes. MM-DyGraph provides three evaluation tasks to comprehensively assess model performance in dynamic settings. We benchmark five state-of-the-art dynamic graph methods and reveal that naive feature concatenation yields target-level inconsistencies: multimodal inputs benefit certain prediction targets while harming others. This observation indicates that the modality informativeness depends on the specific prediction target over time. Building on these observations, we propose a Target-aware Spatial-Temporal Multimodal Fusion (TST-MF) framework, which jointly conditions multimodal fusion on the prediction target and spatial-temporal relations, enabling context-adaptive cross-modal interplay for target-specific representations. Extensive experiments over diverse datasets and tasks show that TST-MF delivers robust and competitive performance, achieving clear gains in multimodal settings.

Agentic multimodal large language models (MLLMs) have recently pushed the frontier of visual reasoning by calling tools such as zooming and tagging. Despite the recent strong success of agentic MLLMs, this work uncovers a critical safety failure in the tool-use paradigm: agentic tool-using MLLMs become less capable of refusing harmful requests. Our experiments confirm that, across three popular safety benchmarks, all the top open- and closed-weight MLLMs we test exhibit significantly lower safety in tool-using settings than in non-tool settings, with a relative refusal failure rate increase of up to 68.7%. Based on analysis of 100,000+ responses, including extended experiments, we also propose two possible reasons for this safety degradation.

The ability to observe the world is fundamental to reasoning and making informed decisions on how to interact with the environment. However, optical perception can often be disrupted due to common occurrences like occlusions, which can pose challenges to existing vision systems. We present MITO, the first millimeter-wave (mmWave) dataset of diverse, everyday objects, collected using a UR5 robotic arm with two mmWave radars operating at different frequencies and an RGB-D camera. Unlike visible light, mmWave signals can penetrate common occlusions (e.g., cardboard boxes, fabric, plastic). MITO captures over 24 million mmWave frames and uses them to generate 550 high-resolution mmWave images in line-of-sight and non-light-of-sight (NLOS), as well as RGB-D images, segmentation masks, and raw mmWave signals, taken from 76 different objects. We develop an open-source simulation tool that can be used to generate synthetic mmWave images for any 3D triangle mesh. Finally, we establish benchmarks for NLOS segmentation and classification to demonstrate the utility of our dataset and simulator for enabling broader NLOS perception.

Current datasets for text-to-video generation are largely limited to short clips depicting a single event or coarse-grained captions. As a result, they provide limited supervision for modeling long-take temporal dependencies, often leading to temporally inconsistent generations when describing multiple events. In this paper, we introduce MEV, a multi-event video dataset designed for long-take video generation. MEV provides high-quality real-world videos where subjects can perform a sequence of distinct, non-overlapping events, featuring precise temporal boundaries and fine-grained procedural annotations. This event-centric discretization reduces confounding factors and enables models to support temporally localized conditioning and build long-take videos from atomic event units. Furthermore, we introduce a comprehensive annotation pipeline that segments videos into temporally grounded events, and generates structured captions at both the global level and the event level. In addition, under an event-centric evaluation protocol, we conduct multi-event generation experiments by fine-tuning on MEV with temporally grounded event conditioning, leading to improved long-take event transitions and more coherent content. We believe this work removes a key barrier to training video foundation models for multi-event scenarios and provides practical insights into learning from temporally-structured video-text data.

LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate only single-entity updates, MEME defines six tasks spanning the full space defined by the multi-entity and evolving axes, including three not scored by prior work: Cascade and Absence (dependency reasoning) and Deletion (post-removal state). Evaluating six memory systems spanning three memory paradigms on 100 controlled episodes, we find that all systems collapse on dependency reasoning under the default configuration (Cascade: 3\%, Absence: 1\% in average accuracy) despite adequate static retrieval performance. Prompt optimization, deeper retrieval, reduced filler noise, and most stronger LLMs fail to close this gap. Only a file-based agent paired with Claude Opus 4.7 partially closes the gap, but at $\sim$70$\times$ the baseline cost, indicating closure currently depends on configurations that are not practical at scale. Code is available at https://anonymous.4open.science/r/MEME-0612 and the dataset at https://huggingface.co/datasets/meme-benchmark/MEME.

Our aim is to develop a unified model for sign language understanding that performs both sign language translation (SLT) and sign–subtitle alignment (SSA). Together, these two tasks enable the conversion of continuous signing videos into spoken language text and also the temporal alignment of signing with subtitles -- both beneficial for practical communication, large-scale corpus construction, and educational applications. To achieve this, our approach is built upon three design choices: (i) a lightweight visual backbone that captures manual and non-manual cues from human keypoints and lip-region images while preserving signer privacy and enabling end-to-end training; (ii) a Sliding Perceiver mapping network that aggregates consecutive visual features into word-level embeddings to bridge the vision–text gap; and (iii) scaling training to large datasets -- BOBSL covering British Sign Language (BSL) and YouTube-SL-25 covering American Sign Language (ASL) -- to promote generalisation across languages and signers. With this multi-task, multilingual pretraining and strong model design, we achieve state-of-the-art results on BOBSL, How2Sign, Phoenix14T, and FLEURS-ASL SLT benchmarks, and also for SSA on BOBSL and WMT-SLT-SRF. Beyond these standard, signer-interpreted datasets, we show successful SLT on the natural signing data from the BSL-Corpus.

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of transformer architectures for MDMs remains underexplored. In this paper, we show that selectively looping the early-middle transformer layers significantly improves both training efficiency and model performance in MDMs. We call this approach \textbf{LoopMDM} (Looped Masked Diffusion Model), which brings two key benefits: looping layers at training-time yields a depth-scaling effect without adding parameters, while varying the number of loops at inference-time enables flexible compute scaling. Despite the simplicity, the results are striking: across multiple pre-training corpora, LoopMDM matches the performance of same-size MDMs with up to $3.3\times$ fewer training FLOPs, while its final performance outperforms them on various reasoning benchmarks, including up to $+8.5$ points on GSM8K. It even surpasses deeper non-looped MDMs trained with comparable per-step compute, indicating that selective looping is more effective than naive depth scaling. Furthermore, LoopMDM can scale inference-time compute by increasing the number of loops. Adaptively adjusting the number of loops throughout the sampling process further yields additional gains in compute efficiency while maintaining performance. Lastly, with attention analysis, we provide evidence that looping is effective in MDMs by promoting interactions among masked positions. Our code and weights will be publicly released.

The ability to simulate the world in a spatially consistent manner is a crucial requirement for effective world models. Such a model enables high-quality visual generation, and also ensures the reliability of world models for downstream tasks such as simulation and planning. It must not only retain long-horizon observational information, but also enables the construction of explicit or implicit internal spatial representations. However, existing datasets do not explicitly enforce spatial consistency constraints, limiting both the ability to systematically evaluate this capability and to learn it through data-driven approaches. Furthermore, most existing benchmarks primarily emphasize visual coherence or generation quality, neglecting the requirement of long-range spatial consistency. To bridge this gap, we propose loopnav, a dataset and corresponding benchmark centered on loop-based navigation for evaluating spatial consistency. The dataset comprises 250 hours (20 million frames) of loop-based navigation videos with actions, collected from diverse locations in the open-world environment of Minecraft. We further introduce a Scene Graph Consistency Score to quantify spatial consistency while remaining invariant to pixel-level variations. Dataset, benchmark, and code are open-sourced to support future research.