NeurIPS 2026 论文列表

Real-world documents distribute evidence across text, tables, figures, captions, and page layouts. Answering complex questions over such documents therefore requires more than retrieving relevant passages: systems must recover the evidence topology that connects heterogeneous evidence units. Existing GraphRAG evaluations focus primarily on text-derived chunks, entities, and relations, while multimodal document RAG benchmarks evaluate cross-modal retrieval and generation without directly testing whether systems recover the intended reasoning structure. We introduce \textsc{TopoGraphRAG-Bench}, a layout-grounded benchmark for multimodal evidence reasoning in GraphRAG. The benchmark contains 2,024 questions over 201 long, visually rich documents, with evidence grounded in text, figures, and tables. Each instance is constructed bottom-up from layout-grounded evidence units and assigned one of three controlled topologies: single-hop retrieval, bridge-chain reasoning, or multi-source synthesis. To ensure that questions preserve their intended structure, we apply counterfactual validation for shortcut resistance, modality necessity, and evidence necessity. We evaluate text-only GraphRAG, page-level visual retrieval, and multimodal GraphRAG systems using retrieval, generation, and topology-aware reasoning metrics. Multimodal GraphRAG systems achieve the strongest overall performance, but still fail when visual-textual evidence alignment or multi-unit composition is incomplete. Text-only GraphRAG struggles when key dependencies are grounded in figures or tables, while page-level visual retrieval lacks the fine-grained structure needed for topology recovery. These results suggest that future GraphRAG systems must model not only textual entities and relations, but also layout structure, modality alignment, and the reasoning roles of evidence units. Code and data are available at \url{https://anonymous.4open.science/r/Benchmark-B1DE}.

Topology reasoning jointly detects 3D lanes and traffic elements from multi-view images and infers their structural connectivity. Current methods model lanes as discrete polylines, lacking smoothness, analytical tangent directions, and global spatial support for attention, while providing sparse topology supervision. We propose TopoCurve, a geometry-driven architecture for 3D topology reasoning grounded in a structured parametric lane representation. Lanes are modeled as endpoint-fixed cubic Bézier curves, enabling continuous geometry with exact endpoints and analytically defined directionality. We exploit this shared curve geometry across the entire pipeline. Endpoint distance and tangent alignment are encoded with multi-scale Fourier features and injected into the topology head. Sampled curve points serve as geometry-aligned references for deformable cross-attention spanning the full lane. Parallel curve-anchored attention branches provide diverse predictions for one-to-many topology supervision. These components form a tightly coupled cascade where representation enables geometric reasoning, guides feature aggregation, and supports denser supervision. TopoCurve achieves 50.6 OLS on the OpenLane-V2 benchmark without any post-processing, establishing a new state-of-the-art among end-to-end camera-only methods, and outperforms all existing approaches on endpoint detection (56.8 vs. 52.6 on DET$_p$).

Vision-Language Models (VLMs) have been increasingly adopted for Image Quality Assessment (IQA). However, current methods typically employ a static one-shot scoring paradigm, despite the fact that humans assess image quality through dynamic visual inspection, e.g., selectively adjusting views to verify details and subtle artifacts. Specifically, relying solely on a single-pass observation introduces two primary limitations: first, perceiving the image only at a global scale restricts the assessment of finer local details; second, the original intensity distribution of the image may overwhelm the visibility, leading to insufficient inspection of image quality. To address these issues, we propose Tool-IQA, shifting the assessment mechanism from passive scoring to a tool-augmented workflow. In particular, we equip VLMs with simple yet effective view tools: a Magnifier to inspect local details, and a Gamma Corrector to uncover visibility and hidden artifacts. The assessment follows a structured pipeline that consists of an initial observation with rubric notes, a tool-augmented in-depth inspection, and a final quantification for calibrated quality score. Furthermore, to ensure efficient and purposeful tool callings, we introduce a batch-aware training strategy to reward tool interactions that can yield positive contributions rather than simply encouraging usage. Experiments on a variety of IQA benchmarks demonstrate that, with effective tool calling and calibrated assessment, our proposed Tool-IQA significantly outperforms existing state-of-the-art models, e.g., it achieves a PLCC of 0.854 on the challenging CLIVE dataset. The code and models will be released.

AI-generated image detection has become increasingly important as generative models produce highly realistic visual content. Existing detectors mainly rely on visual artifacts or visual features extracted from pretrained multimodal models, while largely overlooking the structural differences between real and generated images in the joint image--text space. In this paper, we reveal a systematic Cross-modal Alignment Shift (CAS): generated images tend to exhibit stronger and more concentrated alignment with text than semantically matched real images. We verify this phenomenon through retrieval preference, image--text residual structure, spectral concentration, and matching entropy. Motivated by this finding, we propose a CAS-based detection framework(CASNet) that learns an amplified multimodal model with a text-guided alignment-shift objective. The amplification-induced feature increment is extracted as an explicit cross-modal cue and coupled with amplified visual representations, enabling the detector to exploit both alignment-level structural evidence and visual discriminative cues. Extensive experiments across diffusion models, GANs, autoregressive models, and commercial generators demonstrate consistent improvements over state-of-the-art detectors. In particular, on recent commercial generators, our method improves ACC and AP by 5.48\% and 6.13\%, respectively.

Latent medical image generators usually treat the tokenizer as fixed preprocessing. We test whether this separation is valid in a controlled ChestMNIST study at 64×64, crossing discrete tokenizers, generator families, and sampler settings under a shared latent grid, with continuous-latent reference cells. The results show that tokenizer, generator, and sampler cannot be ranked independently. LFQ is the strongest default discrete tokenizer in the matched VQ/LFQ/FSQ grid, but generator rankings change with quantizer family and categorical rate. On LFQ-1024, retuning D3PM and SEDD moves them from default FID-192 0.44/0.41 to 0.09/0.11 at lower NFE, approaching the strongest continuous references. Reconstruction quality is not a reliable selection criterion: the highest-PSNR tokenizers are not the best generation substrates, even when each tokenizer is paired with its best observed generator. We interpret these results as a rate-distortion-modelability tradeoff, where modelability is conditional on the generator, sampler, and inference budget. The study covers 54 discrete tokenizer-generator cells and 16 continuous reference cells, and its scope is deliberately limited: low resolution, one training seed, unconditional generation, and non-clinical FID-based evaluation.

Multimodal large language models (MLLMs) should generate consistent responses given semantically equivalent inputs across modalities. However, we observe a systematic discrepancy in model predictions under such cross-modal variations. To study this phenomenon, we define the modality gap as the difference in model performance under semantically equivalent textual and multimodal inputs. We introduce TokenSwap, a method that constructs such inputs by replacing textual concepts with semantically aligned images, resulting in sequences where visual tokens are interleaved with text tokens. Based on TokenSwap, we transform existing text-based benchmarks (e.g., MMLU) into image-interleaved counterparts, resulting in TOKENSWAP-BENCH. Across 42 MLLMs, we observe a pervasive modality gap, with performance decreasing by 4.2% to 47.4% when moving from text-only to image-interleaved inputs, averaging 19.6% ± 3.3% across models. Notably, we observe that reasoning models exhibit consistently smaller gaps, achieving an average gap of 10.1% compared to 25.5% for non-reasoning models. In contrast, neither prompting strategies nor scaling training compute alone reliably reduces the modality gap. Finally, we demonstrate that incorporating TokenSwap during training effectively mitigates this gap while preserving strong text-only and vision-language performance.

Recent advances in Vision-Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory performance when applying large language or multimodal models to finding abnormal patterns in sequential data. Public anomaly detection benchmarks typically provide interval annotations but not natural-language rationales, making it difficult to fine-tune VLMs to produce grounded, interpretable decisions. To address this gap, we construct VisAnomBench, an explanation-augmented curated benchmark built from public time-series datasets and augmented with high-quality anomaly explanations selected from multiple large VLMs using fine-grained, task-specific rewards. Building on this benchmark, we present VisAnomReasoner, a parameter-efficient VLM for time-series anomaly detection. Experimental results on VisAnomBench show that VisAnomReasoner achieves more accurate anomaly localization and consistently outperforms all baselines, with improvements of at least 21.23 and 23.87 percentage points in precision and F1, respectively. Additional experiments on the TSB-AD-U benchmark demonstrate strong cross-benchmark generalization, with VisAnomReasoner improving precision and F1 by 9.57 and 13.39 percentage points, respectively. Dataset, code, and model weights will be open-sourced.

We study cost-aware cascading bandits, where a learner selects an ordered subset of options, tests them sequentially until the first success, and pays the costs of all tested options. In this problem, regret comes from both testing inefficient options and placing options in a suboptimal order, but existing analyses do not separate these effects for inefficient options and therefore yield an inverse-square dependence on the gap $c_i-\theta_i$. We develop a regret decomposition based on intermediate policies that reorder the remaining suffix and remove inefficient options one position at a time. This allows us to quantify the incremental regret incurred when each option is tested. As a consequence, we show that the regret of CC-UCB admits a problem-dependent bound of $O(\sum_{i:\theta_i/c_i<1}\log T/(c_i-\theta_i))$ up to additive terms and a problem-independent bound of order $\tilde O(L\sqrt{T})$. We further prove that the minimax regret is bounded from below by $\Omega(\sqrt{LT})$ by reducing standard multi-armed bandits to a special case of the model. Finally, we propose CC-UCBv2, which removes the need to specify a positive lower bound on costs and handles zero-cost options by separating empirically zero-cost options from the others. Numerical experiments show the effect of misspecified cost lower bounds and demonstrate that the proposed modification can reduce regret in representative instances involving zero or misspecified costs.

While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the observed images and text-oriented chain-of-thought. They often struggle to infer unobserved layouts, maintain cross-view consistency, and reason from alternative viewpoints when only limited egocentric observations are available. In this work, we study this problem as thinking with imagination, where a VLM actively acquires imagined visual evidence by interacting with a world simulator during reasoning. We propose Astra, an agentic spatial reasoning framework that empowers VLMs with action-conditioned visual imagination. Specifically, Astra couples Astra-VL, an RL-trained VLM policy, with Astra-WM, a Bagel-based world simulator that generates novel-view observations from context images and natural-language camera motions. To provide reliable imagined evidence, Astra-WM is trained with view consistency tuning to improve pose and content consistency across views. In the RL stage, we propose a world-simulator-in-the-loop two-phase RL curriculum to stabilize tool-use exploration and advance the model's ability to invoke the simulator only when imagined observations improve over direct answering. Experiments demonstrate that both the world simulator and the agentic policy are necessary: Astra-WM improves simulator-augmented Gemini-3-Flash on MMSI-Bench from 45.1 to 49.5, while Astra-VL improves the Qwen3-VL backbone from 29.8 to 38.8 on MMSI-Bench and from 36.8 to 42.7 on MindCube. These results show that imagined observations can provide useful spatial evidence, but effective world-model-augmented reasoning requires learning when, where, and how to imagine.

Recent advancements in world models and unified generative models (UGMs) have achieved unprecedented results in visual perception and synthesis. However, these models primarily rely on surface-level alignment, leaving the capacity for high-level visual reasoning underexplored. True visual generative intelligence demands "Reasoning-to-Generation", an ability to infer latent rules from visual inputs and manifest solutions through precise, logically constrained visual outcomes. We introduce RIG-Bench, a novel comprehensive benchmark that systematically evaluates Reasoning-driven Image Generation (RIG) across four cognitively demanding domains: Concept-based, Transformation-based, Pattern & Structure, and Scenario-based. Featuring 2000 curated samples, RIG-Bench serves as a rigorous stress test for RIG. Our extensive evaluations of state-of-the-art UGMs and image/video generation models reveal a significant reasoning-generation gap, wherein models frequently produce locally plausible but globally illogical outputs. RIG-Bench provides a vital diagnostic framework to guide the development of next-generation, logically grounded world models.

Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. Vision-language models (VLMs), in contrast, provide strong semantic grounding and general knowledge by reasoning over uniformly sampled observation frames, but they are not ideal as standalone dense predictors due to compute-driven sparse sampling, a language-output bottleneck that compresses fine-grained interaction states into text-oriented representations, and a data-regime mismatch when adapting to small action-conditioned datasets. We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance via a dual-temporal pathway: a dense JEPA branch for fine-grained motion and interaction cues, and a uniformly sampled observation VLM thinker branch with a larger temporal stride for knowledge-rich guidance. To transfer the VLM's progressive reasoning signals effectively, we introduce a hierarchical pyramid representation extraction module that aggregates multi-layer VLM representations into guidance features compatible with latent prediction. Across EgoDex, EgoExo4D, BAIR Robot Pushing, and Physion, ThinkJEPA outperforms diverse latent world model and trajectory prediction baselines across egocentric trajectory prediction, long-horizon rollout, robotic latent prediction, and physical-scene forecasting. These results show that broad visual-semantic guidance from a VLM thinker can benefit JEPA-style latent forecasting.

Autonomous driving fundamentally demands dense understanding of visual, semantic, and geometric information, yet existing Vision-Language-Action (VLA) models are typically trained with sparse supervision such as language instructions or trajectory signals. This direct mapping from dense visual observations to sparse representations forces the model to compress or even discard critical scene information essential for safe driving. We argue that this limitation does not stem from insufficient model capacity, but from the lack of explicit mechanisms that encourage the formation of dense world representations in the latent space. In this spirit, we propose a novel paradigm for driving intelligence—Think Densely, Act Sparsely—and instantiate it with an efficient and interpretable framework, LECDrive (Latent Expert Cognitive Chains for Vision-Language-Action autonomous Driving). The core idea is to mimic the hierarchical perception process of humans by embedding a progressive chain of latent expert cognition within the VLA model. Concretely, we inject a compact set of task-specific latent tokens as carriers, enabling the model to internalize dense knowledge from foundational vision models, including visual representations (DINOv3), semantic structures (SAM3), and spatial geometry (DepthAnything3), while maintaining efficient inference. This interdependent cognitive chain follows a curriculum learning principle, where supervision is progressively structured from representation to semantics and geometry. Extensive experiments demonstrate that LECDrive consistently improves the performance of base VLMs across multiple autonomous driving benchmarks, covering key tasks such as object perception, state prediction, and trajectory planning. These findings suggest that constructing dense world models through structured latent expert chains is a promising direction for VLA-based autonomous driving.

The task of visual reasoning relative pose identification (VRRPI) has exposed critical weaknesses in the multi-view 3D spatial reasoning capabilities of modern vision-language models (VLMs). We present a systematic analysis of VLMs behavior in VRRPI, uncovering stable output biases where VLMs disproportionately predict specific motion patterns regardless of visual evidence. To mitigate these inherent biases, we propose self knowledge re-expression with iterative debiasing (SKR-ID), an annotation-free pipeline that adapts VLMs for VRRPI using only randomly extracted unannotated image pairs. SKR-ID transitions VLMs' output mechanism from generic next-token prediction to task-optimized classification heads. The pipeline proceeds in two stages: (1) a cold-start initialization using debiasing object-centric prompts to anchor motion inference in 2D visual evidence; and (2) a recursive logit-ranking mechanism that enforces statistical parity by using the median logit value as a dynamic threshold. Experimental evaluations across frontier VLMs on standard benchmarks demonstrate that SKR-ID significantly mitigates systematic biases and unearths latent 3D reasoning ability. Our method achieves substantial gains, improving open-sourced VLMs' Macro-F1 scores by at least 8.3% and at most 23.0%, proving that VLMs possess significant untapped multi-view 3D reasoning potential.

With the rapid advancement of generative models, AI-generated images (AIGIs) have become increasingly realistic, posing new challenges for reliable detection. In this work, we revisit the root causes of poor generalization in AIGI detectors from the perspective of shortcut learning. We find that detectors often rely on spurious semantic cues or a single prominent artifact, causing the feature space to collapse toward low diversity and severely limiting generalization. To characterize this issue, we propose the Generative Artifact Manifold Clustering (GAMC) hypothesis, which shows that although generative artifacts are multi-dimensional, different generators occupy distinct distributions along these dimensions, making detectors that rely on local artifact cues inherently fragile. To address this, we shift AIGI detection from “single-cue reliance” to “multi-dimensional discrimination” and introduce the Semantic–Artifact Self-Adversarial Feature Learning (SA-AFL) framework. SA-AFL progressively disentangles semantics from artifacts and employs a self-adversarial mechanism to balance learning across artifact dimensions, enabling the model to retain richer and more shared generative features. As a result, SA-AFL reduces shortcut reliance and learns more transferable evidence for cross-generator detection. Comprehensive experiments on images from 23 generative models show that SA-AFL improves ACC by 6.84\% and mAP by 8.25\% over state-of-the-art methods.

What if the best way to search a video with a vision-language model (VLM) is to stop asking the model to search? Recent approaches give the VLM control over temporal navigation, tying search quality to the model's reasoning ability. We propose the opposite: BeliefSearch treats the VLM as a noisy sensor and delegates navigation to an external Bayesian controller. A single belief over video segments anchors the system: the question sets the prior, each VLM observation updates it, and the same belief decides whether to search, which segment to examine next, and when to stop. Because the belief is explicit, we can trace why each choice was made. The same signal also drives training: each turn earns credit for the uncertainty it reduces, and the final reward is gated by how much the search lowered entropy. This blocks a reward-hacking shortcut where the model otherwise learns to skip search and guess from the preview frames. On long-video benchmarks, our method outperforms all prior search-based methods by up to 8.8 points while using $5$ to $13\times$ fewer frames than recent RL search baselines.

Large language models consistently fail at elementary counting tasks despite strong performance on complex reasoning benchmarks. Recent work has characterized counting failures behaviorally or identified circuits through which counting succeeds, but a mechanistic account of where and why counting breaks down remains absent. In this work, we provide such an account by tracing the count signal from embedding to output and identifying the geometric bottleneck that prevents correct readout for single digit counting problems. Using a dual-metric framework combining Signal-to-Noise Ratio (SNR) with linear probing, we show that counting information is computed correctly and persists in a linearly decodable subspace through the final layer. The failure in counting is not representational but geometric i.e the digit-token columns of the unembedding matrix $W_U$ are orthogonal to the count subspace in the residual stream, rendering correctly computed counts unreadable at the output. We term this as the $\textbf{Unembedding Bottleneck}$ and to causally validate it, we apply a $\textbf{Probe-Informed LoRA}$ correction targeting $W_U$, which restores single-digit counting accuracy by up to 80-95% across six models while updating only ${\sim}$0.001% of parameters and preserving general capabilities. Our findings reveal a broader class of failure in LLMs where information is internally present but geometrically inaccessible to the output projection.

Machine learning models—including large language models (LLMs)—are often said to exhibit *monoculture*, where outputs agree strikingly often. However, we present two experiments that substantially disagree with prior findings of monoculture. In particular, we find that monoculture virtually disappears in one dataset when we include item difficulty compared to previous works that do not. Informed by these findings, we theoretically formalize what it means to measure monoculture. We show that monoculture is inherently subjective, relying on two key decisions: 1) the baseline null model for what "independence" should look like; and 2) the population of models and items under consideration. We conclude with concrete guidelines for future evaluators to ensure the robustness of their results.

With the rapid development of Vision-Language Models (VLMs), it is increasingly critical to evaluate their ability in accurate and robust reasoning based solely on visual information. However, existing video understanding benchmarks often overlook the deep cognitive processes inherent in visual reasoning and frequently rely on multiple-choice formats, implicitly encouraging reasoning shortcuts. To address these limitations, we introduce \emph{The Prestige}, a novel video understanding benchmark designed to isolate VLM reasoning under deliberate cognitive misdirection through professional magic performances. The dataset consists of a curated collection of high-quality magic videos paired with a diverse distribution of strictly open-ended questions targeting causal state tracking, paradoxical reasoning, and resistance to adversarial questions. These questions need the models to perform long-horizon, multi-step commonsense reasoning with cognition. Through extensive evaluations of leading open-weight and proprietary VLMs, using a combination of machine and human grading, we find a substantial gap between model and human performance. \emph{The Prestige} establishes a rigorous new frontier for evaluating temporal, causal, and cognitive-flow reasoning in multimodal foundation models.

Sequence prediction methods for dynamical systems with long memory, i.e. marginally stable systems, typically achieve regret that grows polynomially with the hidden dimension of the underlying generative model. Universal Sequence Preconditioning (USP) \cite{marsdenuniversal} is a method that compresses any sequence which comes from a linear dynamical system into a ``preconditioned'' sequence which requires exponentially shorter memory for accurate prediction. However, the preconditioned sequence yields exponentially larger diameters and gradients, hindering USP from unlocking optimal regret bounds. Inspired by the minimum description length principle, we show that the Vovk-Azoury-Warmuth (VAW) algorithm is naturally matched to the USP regime. Indeed, it takes advantage of the memory compression while remaining robust to the exponential explosion of the diameter. We prove that combining USP with VAW achieves astoundingly strong results: for any marginally-stable linear dynamical system, this algorithm achieves polylogarithmic regret $O\left( \log^3 T \right)$ even in the presence of asymmetric hidden transition matrices. Finally, we extend the applicability of USP beyond bounded-spectrum systems by providing new complex-analytic bounds on Chebyshev polynomials, allowing for systems with constant complex arguments.