NeurIPS 2026 论文列表

Time-resolved stellar spectroscopy is a primary observational window onto mass-loss, disc formation and rotational physics, phenomena that single-epoch surveys cannot capture. Be stars are rapidly rotating B-type stars that episodically grow and lose a circumstellar gas disc, which imprints a variable emission profile on the hydrogen H-alpha Balmer line (6562.8 Angstrom) on timescales from days to decades. Decoding these spectral variations is both a key step in understanding stellar evolution and an open challenge for machine learning on irregularly sampled scientific time series. Yet no benchmark exists for these spectra: professional surveys deliver a single epoch per star, and the amateur-driven BeSS database, although it hosts hundreds of thousands of multi-epoch spectra, has never been curated for machine learning. We close this gap with BESS-Bench: 339,115 optical spectra of 1,468 Be stars over 35 years, all expert-reviewed, from amateurs (81.7%) and professionals (17.7%), with a scored H-alpha benchmark slice of 26,937 spectra and three tasks under a unified evaluation protocol. SpecProbe measures how well frozen embeddings recover six scalar line features (width, peak separation, line-core depth, asymmetry, equivalent width, peak intensity). LineTransfer tests cross-line generalisation (H-beta to H-alpha). EWForecast predicts the next-epoch equivalent width of H-alpha (a disc-mass proxy) from a star's recent spectroscopic history. We release a compact masked auto-encoder baseline (BeMAE) and benchmark it against PCA and two zero-shot time-series foundation models (Chronos-Bolt and TimesFM-2.0). The ranking is sharply task-dependent: BeMAE recovers shape features with an R2 that is 4.24x that of PCA(10) (bootstrap CI95 [4.12, 4.33]), yet a PCA+ridge pipeline lowers EW forecasting MAE by 5.8% over persistence, beating both foundation models, and calling as such for further development of AI models in this context. Dataset, weights, frozen splits and evaluation pipeline are released under CC-BY-4.0, so the scientific community can adopt BESS-Bench as a shared testbed and contribute new representations and models to advance our understanding of stellar variability.

Self-Driving Chemical Laboratories (SDCLs) are moving chemical experimentation toward embodied automation, where machines must perceive laboratory scenes, reason about experimental states, and act under physical, procedural, and safety constraints. Although Multimodal Large Language Models (MLLMs) are increasingly considered as embodied brains for such systems, existing laboratory benchmarks mainly focus on safety, anomaly detection, or general scientific understanding, leaving their execution-oriented embodied capabilities underexplored. To fill this gap, we introduce BEAKER, a Benchmark for evaluating Embodied Actionability, Knowledge, Experimentation, and Reasoning in SDCLs. BEAKER contains 1,000 expert-curated QA samples across 11 image and video task types, covering key judgments required for chemical laboratory execution, including affordance grounding, trajectory planning, equipment and state understanding, apparatus connection, operation process reasoning, and result understanding. All questions and annotations are manually created and reviewed by chemistry and embodied AI experts, without AI-assisted generation or annotation. We evaluate 28 general-purpose, scientific, chemical, and embodied MLLMs on BEAKER. Results show that current models can recognize laboratory objects and states, but still struggle to ground experimental knowledge into operable regions, feasible trajectories, and long-horizon procedural reasoning. BEAKER thus reveals a clear gap between multimodal laboratory perception and action-grounded experimental understanding, providing a diagnostic benchmark for future MLLMs in SDCLs.

Formulating an optimization problem strongly affects the quality of the final solution, yet good formulations usually require substantial expertise. Recent studies have therefore examined how to automatically derive optimization problems from natural-language descriptions, but existing benchmarks focus on settings where objectives and constraints can be written explicitly as mathematical expressions. Many practically important problems, including hyperparameter optimization in machine learning, are naturally treated as black-box optimization (BBO) problems, in which only objective values are observable, and the functional form is unavailable. In BBO, the search space design, a part of the problem formulation, and the selection of the optimization algorithm are crucial for problem-solving. Automating these processes with large language models (LLMs) is a significant challenge. This paper introduces Black-Box Optimization Word Problems (BBOWP), a novel problem setting in which a system must infer both a search space and an optimization algorithm from a natural-language description of a black-box optimization task. To support research on this setting, we establish the BBOWP Benchmark Suite (BBOWP-Bench), a dataset and evaluation framework for BBOWP. Each instance combines a natural-language problem description, an executable evaluation environment, and a human-designed baseline formulation, allowing evaluation of both search-space design and algorithm selection. The benchmark covers 23 instances from four different application domains and supports reproducible assessment through actual black-box optimization runs. Using this benchmark, we provide the first evaluation of LLMs and show that current LLMs are capable of selecting suitable algorithms based on the given evaluation budget. However, they sometimes struggle with search space design, particularly in identifying important variables and balancing their ranges when the problem description is less informative or the search space is highly problem-specific.

Few-shot medical image segmentation has shown great potential in reducing annotation costs for clinical applications. Recently, many few-shot methods have explored the Segment Anything Model (SAM) for training-free medical image segmentation via prompt engineering. However, existing approaches mainly focus on locating positive prompts from support images while overlooking informative background cues, making them prone to over-segmentation in anatomically similar regions. Moreover, simply introducing negative prompts cannot effectively suppress boundary leakage, and may even interfere with SAM’s mask decoding process, resulting in worse performance than using positive prompts alone. To address this limitation, we propose a training-free support-query framework, termed Boundary-Aware Prompt Mining, which introduces boundary-aware negative prompting for SAM-based few-shot medical image segmentation. Specifically, we introduce a Prototype-guided Positive Prompt strategy, which adopts a multi-center prompting mechanism to construct multiple foreground prototypes, enabling comprehensive spatial coverage in query images. Furthermore, we propose a Boundary-band Ambiguity Filtering strategy that identifies a boundary-adjacent background band and progressively removes ambiguous pixels and unreliable clusters highly similar to the foreground, enabling the selection of reliable negative prompts for suppressing false positives near foreground boundaries. The generated positive and negative prompts are jointly fed into SAM to produce refined segmentation results without additional training. Extensive experiments on Abd-MRI and Abd-CT datasets demonstrate that our method consistently outperforms existing approaches, highlighting its effectiveness and robustness under limited annotation settings. Code will be released upon acceptance.

Geometry Problem Solving (GPS) serves as a rigorous touchstone for evaluating the complex reasoning capabilities of Multimodal Large Language Models (MLLMs), particularly when solutions necessitate auxiliary constructions absent in the visual input. However, current approaches face the following challenges: explicit diagramming methods suffer from unstable image generation quality and error cascading, while existing implicit attention mechanisms are restricted to visible elements, failing to perceive the latent auxiliary structures required for deduction. To bridge this gap, we propose AuxCA (Auxiliary-Clues-Aware GRPO), a novel framework that internalizes the capability of auxiliary construction into the model’s reasoning intuition without relying on external tools. Specifically, we introduce Auxiliary Clues Dependency (ACD) to quantify the causal influence of visual cues and integrate it into GRPO via a fine-grained advantage weighting strategy. Complementing this, we incorporate an auxiliary incentive reward to explicitly encourage the model to actively attend to and utilize these geometric elements during reasoning. Extensive experiments demonstrate that our resulting model, AuxCA-8B, significantly outperforms state-of-the-art explicit plotting methods and achieves performance competitive with top-tier proprietary models. Code is available in \url{https://anonymous.4open.science/r/AuxCA-5510}.

Multimodal models have demonstrated strong capabilities in web, desktop, and mobile GUI environments, but their performance in automotive cockpit systems remains largely unexplored. In-vehicle GUIs introduce unique challenges beyond traditional GUI interaction, including vehicle-state reasoning, implicit intent understanding, and safety-critical decision making. To address this gap, we introduce Automotive-ENV, an interactive benchmark for evaluating multimodal models in automotive cockpit environments. Built on Android Automotive OS, Automotive-ENV combines cockpit-screen interaction with vehicle-state signals and deterministic state-based evaluation. The benchmark contains 420 carefully constructed tasks covering routine cockpit operation and safety-critical scenarios. Unlike prior GUI benchmarks that rely on action matching or LLM-based judging, Automotive-ENV evaluates model behavior through reproducible validators over UI states, vehicle signals, and safety-related conditions. We benchmark representative general-purpose multimodal models and GUI-specialized vision-language models on Automotive-ENV. Experimental results show that current models remain far from reliable in automotive environments, with substantial performance degradation in implicit and safety-critical tasks. Further analysis reveals consistent failure modes in safety-aware reasoning, vehicle-control understanding, and implicit hazard recognition. We will release Automotive-ENV, together with tasks, validators, and evaluation tools, to support future research on automotive multimodal systems.

The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted, making the process labor-intensive and often suboptimal. In this work, we propose RuleRefine, a framework for automatic coding rule refinement. RuleRefine maintains a pool of candidate coding rules and iteratively improves them. In each iteration, it employs an LLM-powered mutator module to generate variants from existing candidates, and then uses a judge module to evaluate these variants and update the pool with the best-performing ones. Extensive evaluations across two coding-agent frameworks, four backbone LLMs, and three benchmarks demonstrate that RuleRefine outperforms both manual engineering and existing prompt optimization baselines in terms of functional correctness of the generated code, code length, and/or generation cost (e.g., tokens used).

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise labels, collapsing nuanced preferences into opaque parametric proxies and exposing vulnerabilities to reward hacking. While recent Rubrics-as-Reward (RaR) methods attempt to recover this structure through explicit criteria, generating rubrics that are simultaneously reliable, scalable, and data-efficient remains an open problem. We introduce Auto-Rubric as Reward (ARR), a framework that reframes reward modeling from implicit weight optimization to explicit, criteria-based decomposition. Before any pairwise comparison, ARR externalizes a VLM’s internalized preference knowledge as prompt-specific rubrics, translating holistic intent into independently verifiable quality dimensions. This conversion of implicit preference structure into inspectable, interpretable constraints substantially suppresses evaluation biases including positional bias, enabling both zero-shot deployment and few-shot conditioning on minimal supervision. To extend these gains into generative training, we propose Rubric Policy Optimization (RPO), which distills ARR’s structured multi-dimensional evaluation into a robust binary reward, replacing opaque scalar regression with rubric-conditioned preference decisions that stabilize policy gradients. On text-to-image generation and image editing benchmarks, ARR-RPO outperforms pairwise reward models and VLM judges, demonstrating that explicitly externalizing implicit preference knowledge into structured rubrics achieves more reliable, data-efficient multimodal alignment, revealing that the bottleneck is the absence of a factorized interface, not a deficit of knowledge.

Generative video models have achieved remarkable visual fidelity and temporal coherence, yet intentional camera control remains elusive. Existing frameworks treat camera motion as a byproduct of pixel synthesis, producing trajectories that are stochastic, spatially inconsistent, and indifferent to the human subject driving the scene. In this work, we present Auteur, a method for language-driven, human-centric camera framing in generative video. Our core insight is that professional filmmakers conceive shots not as world-space trajectories but as framings defined relative to the actor, encoding shot size, angle, and composition as functions of human pose and motion. We formalize this intuition as a human-centric camera parameterization and introduce a Domain-Specific Language (DSL) that is convertible to standard 6-DoF camera parameters. A fine-tuned multimodal large language model then acts as a virtual director, mapping natural language descriptions and coarse human motion to sparse DSL keyframes that are deterministically inter-polated into continuous camera trajectories, which are then provided as input to video generators. We train and evaluate Auteur on a new dataset of 30K aligned text, human motion, and DSL-annotated camera trajectories drawn from procedural synthesis and real-world movie footage from the CondensedMovies dataset. Auteur enables cinematographic framing of human-centered scenes, a capability largely absent in prior generative models. To assess this behavior, we propose new framing-focused metrics, and our experiments show that Auteur consistently outperforms existing methods.

As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We introduce Auditing Sabotage Bench, a benchmark for evaluating the ability of auditors to detect and fix sabotage in ML research codebases. Our benchmark consists of 9 ML research codebases with sabotaged variants that produce qualitatively different experimental results. Each sabotage modifies implementation details, such as hyperparameters, training data, or evaluation code, while preserving the high-level methodology described in the paper. We evaluated frontier LLMs and LLM-assisted human auditors on our benchmark and found that both struggled to reliably detect and fix sabotage: the best performance was an AUROC of 0.77 and a top-1 fix rate of 42%, achieved by Gemini 3.1 Pro. We also tested LLMs as red teamers and found that LLM-generated sabotages were weaker than human-generated ones but still sometimes evaded same-capability LLM auditors. We release the benchmark to support research on monitoring and auditing techniques for AI-conducted research.

Public validation sets in machine-learning challenges frequently become de facto test sets in downstream work, making train–validation source overlap a first-order concern for claim validity. We audit the released public split of the *Capsule Vision 2024 Challenge* (CV2024) using perceptual hashing (pHash+dHash, PDQ at 99.4%), pixel NCC, and DINOv2/ResNet feature checks. The released CV2024 public split contains 1,381 / 11,581 KVASIR validation rows (11.9%; 540 pixel-confirmed at NCC ≥ 0.99, i.e. 4.66%) with pHash-exact training matches — directly violating the organizers' "NOT have duplicates" preprocessing description. All 1,381 trace to shared Kvasir-Capsule video prefixes, consistent with frame-level (not video-level) random splitting. The full CV2024-KVASIR slice falls in the disclosed Kvasir-Capsule near-duplicate set (60.7% bit-identical; non-KVASIR controls ≤ 0.31%). Training on the Kvasir-origin-removed le6 split drops public-validation balanced accuracy by Δ = −0.213 (95% CI [−0.220, −0.206], n=10 paired seeds), quantifying the public score's dependence on the KVASIR channel; the magnitude is mechanically expected given the 71.8% KVASIR validation composition rather than a leakage-specific causal effect. le6 is not a hidden-test proxy (team-level Spearman against AIIMS: ρ=0.355 vs. 0.566 for the original score). We release le6, le6_plus_internal, hash/NCC annotations, audit code, and a Croissant 1.1 descriptor as a within-public-pool sensitivity probe; no image bytes are redistributed. Detector portability: ISIC 2019 cross-source rate is 0.008% (2/25,331, both re-attributed as within-source metadata-gap pairs ⇒ genuine cross-source 0/25,331; Cassidy et al. 2022's recall-tuned multi-hash pipeline flags 14,310); HyperKvasir and Kvasir-SEG cross-benches against CV2024 return 0 pairs (procedure-disjoint negative controls). At the matched NCC ≥ 0.99 endpoint, the CV2024 rate of 4.66% (540/11,581) is ≈ 148–583× above the ISIC cross-source rate (Wilson-lower / Wilson-upper to point/point).

Post-hoc scoring functions for out-of-distribution (OOD) detection in transformer models are typically validated on a single architecture and a single modality, leaving cross-architecture behavior largely uncharted. We report a cross-modality empirical study of attention-head-masking-based OOD detection across more than 1,200 AUROC measurements, spanning LayoutLMv3 on document classification, ViT-B/16 on natural images, and RoBERTa-base on text. Each setting is evaluated against seventeen baselines under a uniform protocol with five fixed seeds, including the Attention Head Sensitivity Scoring (AHSS) and AHM-augmented distance methods of Constantinou et al. (2024) and the recent X-Mahalanobis from NeurIPS 2025. Paired statistical tests are run on every head-to-head claim. Within the AHM family, mahAvgAvg_AHM significantly beats X-Mahalanobis on Tobacco-Cross (Wilcoxon $p=0.031$) and on RoBERTa SST-2$\to$20-Newsgroups ($p=0.031$); on standard CIFAR vision benchmarks, X-Mahalanobis remains state-of-the-art. Three architecture-dependent phenomena surface that current evaluation practice tends to miss: Monte Carlo Dropout collapses to chance-level AUROC across all four ViT settings tested; the AHSS displacement score inverts polarity on RoBERTa, yielding a mean AUROC of 0.296 even though it functions on vision and document transformers; and on near-OOD splits where ID and OOD share visual or semantic structure, every method including the strongest baselines degrades by 25 to 42 percentage points relative to standard OOD. We release per-seed measurements, AHM masks, and code to support replication.

Text- and image-conditioned world generators can now produce visually rich 3D environments, but these worlds are usually silent or paired with a soundtrack generated only from text or rendered video. Such audio can describe what should be heard, but it does not explicitly represent where sounds live in the world or how they should change as a listener moves. We propose Audible World Models, a training-free framework that treats sound as part of a generated world state. Given a text prompt, our system builds a panoramic 3D proxy, decomposes it into semantic layers, identifies audible foreground objects and ambient background regions, synthesizes dry audio for each sound label, attaches sources to reconstructed geometry, and renders listener-dependent spatial audio through geometric acoustic propagation. This explicit coupling of semantics, geometry, and propagation produces audio that remains tied to persistent source locations and responds to viewpoint and motion. Across 80 generated scenes, our method substantially improves spatial consistency over text-, video-, and panorama-conditioned baselines while maintaining competitive semantic alignment. VLM-based and human evaluations further show that the resulting soundtracks are preferred for audio--visual consistency, spatial plausibility, and motion-dependent behavior.

Understanding how the brain integrates information across sensory modalities under naturalistic settings remains a central challenge in cognitive computational neuroscience. Despite recent progress in multimodal brain encoding driven by the advancement of deep learning, many existing approaches combine representations from pretrained modality-specific models using static aggregation or linear readouts, and therefore do not explicitly capture how information is selectively integrated across cortical regions. Here, we introduce Multimodal Transformer Brain Encoder (M-TBEn), a neural encoding framework that models multimodal integration as a routing problem. M-TBEn extends prior vision-based brain encoding approaches by introducing a cross-attention mechanism for multimodality, in which learnable parcel-level queries dynamically select and aggregate modality-specific representations from visual, auditory, and linguistic inputs. This design is not only parameter-efficient but also yields parcel-specific multimodal representations that support a flexible linear readout for predicting brain responses at various spatial resolutions. We evaluate M-TBEn on naturalistic video-viewing data, including both in-distribution and out-of-distribution stimulus conditions. The model is able to accurately predict parcel-level and voxel-level fMRI responses and generalizes across stimulus distributions. Furthermore, the learned attention patterns provide a structured descriptive basis for analyzing modality integration across cortical parcels, enabling a connection between parcel-specific routing profiles and established functional brain networks. Together, these results suggest that attention–based routing offers a principled computational framework for modeling multimodal integration in the human brain.

We study attention mechanisms through the lens of a canonical unsupervised problem: principal component analysis (PCA). We show that, when trained on Gaussian data, both softmax and linear attention layers learn parameters that align with the principal eigenvectors of the covariance matrix, thereby establishing a direct and explicit connection with PCA. Our analysis covers both finite and infinite prompt regimes. In the infinite-prompt limit, we prove convergence to globally optimal solutions aligned with the leading spectral direction, while in the finite-prompt setting we show that the same behavior emerges up to sampling effects. We further extend the analysis to an in-context setting with spiked Wishart covariances, where attention successfully recovers the underlying signal direction. These results demonstrate that attention inherently performs PCA-like computations under unsupervised objectives, providing a theoretical foundation for its representation-learning capabilities.

A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a randomly initialized standard student ViT, is sufficient to recover the full benefit of the teacher's pre-trained weights. We revisit this finding on a comprehensive benchmark of 20 teachers from 11 well-known ViT families and reveal that Attention Transfer is not universally effective. While 7 families transfer successfully, 4 consistently fail, falling up to 5.1\% below the from-scratch no-transfer baseline. Further results demonstrate that this failure is family-consistent across model sizes, and persists under extended training durations, different transfer datasets, and out-of-distribution evaluations. Controlled analyses then consistently localize the problem to the attention-routing channel, indicating that the key issue is not whether the student can match the teacher's attention patterns, but whether the matched patterns remain functional for the student. Crucially, we identify architectural mismatch between the pre-trained teacher and the standard student as the primary mechanism. By adding only the teacher's native architectural components to the student in a randomly initialized state, we completely reverse the failure for all 4 families. Notably, these components alone do not improve from-scratch training, confirming that they specifically unlock the usability of the teacher's attention. We further systematically show that this failure is not explained by the inadequate choice of transfer loss or by differences in pre-training recipes. Our findings refine the prevailing understanding of attention in ViT representations: attention is sufficient only when the student architecture matches the teacher.

Recent studies have explored attention dynamics in Large Vision-Language Models (LVLMs). However, most existing approaches aggregate attention across heads, potentially obscuring head-specific visual information and weakening visual grounding, leading to hallucinations. In this work, we revisit hallucination from the perspective of how visual information is distributed and utilized across attention heads. We observe that a small subset of visual tokens accounts for most of the attention within each attention head, with these tokens—defined as head-wise visual cues—being complementary across heads, suggesting that effective grounding requires preserving head-specific support. We further find that the proportion of visual cues within visual attention declines during generation, leading to key visual information loss and hallucination. In addition, hallucinated tokens show weaker utilization of long-range textual context compared to correctly generated tokens. Building on these findings, we propose **V**isual Cu**e**s **R**einforcement via Head-Adaptive **D**e-redundancy and Distance-Aware **A**ttenuation (**VerDA**), a training-free method to mitigate hallucinations. Specifically, we remove redundant visual tokens via head-adaptive de-redundancy, suppress local textual bias through distance-aware attenuation, and reinforce visual cues by redistributing attention. Experiments across multiple LVLMs and benchmarks demonstrate that VerDA consistently outperforms existing methods in mitigating hallucinations, with negligible inference overhead. ***Code is available in the supplementary materials.***

Visual perception depends on top-down goals and bottom-up sensory mechanisms. Vision-language models implement both, allowing us to treat each component as a separable hypothesis about what drives where we look. We compared spatial attention maps from six vision-language models against human fixation heatmaps recorded on 200 images during two tasks (general description and social captioning). The six models spanned a 2$\times$2 factorial of CNN vs.\ ViT encoders crossed with LSTM vs.\ Transformer decoders, plus Molmo 7B-D and Qwen3.5 9B. We found that both decoder and encoder architecture shaped alignment, but decoder choice dominated. LSTM vs.\ Transformer decoders increased alignment by 40--50 percentage points (80--87\% vs.\ 40--59\% of the human noise ceiling). In contrast, CNN vs.\ ViT encoders contributed a secondary 5--20 point advantage depending on decoder family, with CNN-LSTM the most aligned model overall (85--87\%). Despite their alignment advantage, LSTM-decoder attention maps were spatially diffuse and minimally task-differentiated; ViT-Transformer, the weakest in alignment, showed the sharpest spatial concentration and strongest task differentiation. A hemispatial-neglect simulation confirmed that ablating attention impacted LSTM decoders more than Transformer decoders. In an exploratory extension using TRIBE-simulated synthetic neural responses, fixation alignment and neural relevance dissociate: CNN-Transformer attention maps better predicted synthetic brain activity despite lower fixation alignment, with attention maps best predicting early visual cortex. Together, top-down and bottom-up components trade off what they predict in behavioral and synthetic neural data.

Robust visual classification often depends on localizing the main foreground objects in an image while ignoring spatially-separable distractors. Surprisingly, we find that the attention maps of smaller self-supervised ViTs localize foreground objects better than those of larger ones. However, we still need large ViTs, because they extract richer representations from each patch. To get the best of both worlds, good localization _and_ rich representations, we propose $A^2$, a simple method that leverages this inverse scaling finding by decoupling _where to look_ (a small attention model) from _what to extract_ (a large embedding model): we crop around the attention peaks of a small model and embed the crops with a larger model. $A^2$ uses entirely pretrained features and does not require per-dataset attention or backbone training. Across $5$ benchmarks, $A^2$ is competitive with backbone-matched loss-level methods like DFR, and outperforms end-to-end attention training under stronger distribution shifts.