NeurIPS 2026 论文列表

Video detectors are usually evaluated on observational splits, where target events co-occur with environmental and capture factors. A high AUC under this setup can reflect either the event itself or its surrounding conditions, and standard reporting cannot tell them apart. This work addresses the entanglement with CARVE, a counterfactual video editing protocol. For each source clip, CARVE generates a matched quartet $(V^0, V^E, V^A, V^{AE})$ that holds camera pose, layout, and surrounding traffic fixed while independently intervening on environment and event. A two-phase generator first produces a layout-conditioned reference image, then performs reference-guided video editing; a three-layer reference / objective / VLM-panel protocol filters the output. Each quartet supports thresholded and continuous diagnostics for false-positive purity, event faithfulness, environment-induced drift, and held-out factor compositions. Thresholded scores are paired with continuous ones so that a conservative detector cannot suppress scores everywhere and look robust. The same audit drives training: CGAA-IC samples weak factors weighted by measured brittleness and adds quartet-level purity, consistency, and faithfulness losses; the inference graph is unchanged. On CCTV accident detection, the audit shows that clean AUC does not predict robustness rankings: a VideoMAE detector with $91.4\%$ AUC on TAD scores only $72.3\%$ CPS on the night slice of CARVE-Q. CGAA-IC raises purity from $84.2\%$ to $89.9\%$ and cross-dataset average AUC from $80.3\%$ to $84.5\%$.

Memory facilitates question answering over long videos by extracting and retrieving facts to fit within the limited context windows of multimodal LLMs (MLLMs). Existing solutions typically extract independent memory entries from fixed-length video clips and thus cannot capture high-level semantics that need to be summarized over extended time periods, such as character traits and relations. Moreover, they rely solely on similarity-based retrieval and may fail to retrieve the fine-grained details required for question answering. To tackle these problems, we propose CAM, featuring continuous extraction for high-level semantics and \textit{adaptive querying} for fine-grained details. In particular, CAM stores the entities and relations extracted from video clips in a knowledge graph. To capture the high-level semantics of each entity or relation, CAM summarizes the local subgraph of the target entity or relation once the subgraph reaches a predefined size. To retrieve the fine-grained details required for question answering, CAM supports multiple search methods, such as knowledge graph traversal, video re-watching, and audio listening, and utilizes a planner-executor-verifier pipeline to adaptively compose these search methods according to question intent. Evaluations on three benchmarks show that CAM outperforms SOTA baselines and improves their accuracy by up to 23 percentage points.

Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multiple interconnected rooms and diverse object categories. We introduce CAIRN, a topology-aware 3D-LLM for multi-room 3D scene understanding. CAIRN aligns transformer attention with scene hierarchy, giving the model explicit awareness of object-level relations and room-level connectivity. It enriches object tokens with room-local relational context via a graph neural network, introduces learned room tokens for room-level abstraction, and applies a hierarchical attention mask with geometric bias to route information according to scene topology. CAIRN is developed on CAIRN-MR, a benchmark we introduce on HM3D for multi-room 3D scene understanding, covering grounding, captioning, and four question-answering tasks that progressively evaluate from intra-room perception to cross-room reasoning. Experiments show that CAIRN outperforms prior 3D-LLMs by a large margin across all CAIRN-MR tasks while remaining competitive on five single-room benchmarks.

Video anomaly detection (VAD) is critical for identifying safety risks in surveillance and autonomous systems. Recent large-model-based VAD methods generate textual rationales and directly output anomaly scores. However, mapping rich semantic descriptions and analysis directly to absolute scalar scores can be poorly grounded and inconsistent, leading to scores that are not well aligned with anomaly severity. With the observation that for humans, it is usually easier to compare things than to rate things directly, we explore whether it also holds for large models in VAD by proposing \textbf{CA-Judge} (\textbf{C}omparative \textbf{A}nomaly \textbf{Judge}), a training-free framework that replaces direct scoring with comparative order inference. CA-Judge treats model-perceived anomaly severity as a latent coordinate, constructs this coordinate from self-comparisons among generated normal/anomalous reference events, and models how anomaly likelihood varies along this coordinate using the generated normal/anomalous reference identities. At test time, CA-Judge avoids exhaustive comparison by maintaining a posterior belief over query severity and selecting a few query--reference comparisons by their expected information about the anomaly status. The resulting comparison trace is aggregated under a Bradley--Terry likelihood and read out through the learned severity--anomaly association to produce the anomaly probability. Without fine-tuning or training data, CA-Judge substantially improves over direct-scoring baselines and surpasses prior training-free state-of-the-art methods on UCF-Crime and XD-Violence.

Multimodal large language models (MLLMs) are transforming recommender systems into content-aware decision systems. In these systems, multimodal compression and cross-modal fusion are often viewed as robustness-enhancing mechanisms against content manipulation, as compression can filter noisy signals and cross-modal consensus can suppress inconsistent anomalies. We challenge this assumption by showing that the same process can expose a compression-to-consensus (C2C) bias in ranking decisions. Signals that remain salient after compression and receive consistent support across modalities can gain disproportionate influence in candidate comparison, offering an exploitable direction for content manipulation. In this paper, we introduce C3H, a novel inference-time attack that exploits this vulnerability. Rather than relying on noisy perturbations or training-time poisoning, C3H promotes a target item by tailoring its multimodal content to align with the decision criteria implicitly expressed by the recommender. Extensive experiments demonstrate that C3H substantially increases target-item exposure while maintaining overall recommendation utility.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities, yet they frequently struggle with fine-grained visual perception, often suffering from hallucinations when faced with visually similar but semantically distinct instances. A major underlying cause is the conventional single-sample Supervised Fine-Tuning (SFT) paradigm, which isolates training instances and limits the model's ability to explicitly learn subtle discriminative boundaries. To address this, we propose **C2FT**, a novel **Confuse-then-Contrast Fine-Tuning** framework that enhances fine-grained perception by shifting from independent supervision to joint supervision. Specifically, C2FT assesses the MLLM's internal uncertainty to dynamically mine model-specific semantic confusions, subsequently constructing challenging multi-image groups comprising hard positive and hard negative samples. By interleaving these samples into a unified prompt, our approach forces the MLLM's internal attention mechanisms to cross-reference images and explicitly capture localized visual discrepancies. Extensive experiments on both Fine-Grained Visual Classification (FGVC) and visual question answering (VQA) benchmarks demonstrate the effectiveness of C2FT. For instance, on the Qwen3-VL-4B model, our approach achieves an average improvements of 3.87\% and 4.35\% points over standard SFT and GRPO baselines, respectively.

As generative video models become increasingly realistic, detecting AI-generated videos requires systems that offer both accuracy and interpretability. However, applying Multimodal Large Language Models (MLLMs) to video forensics is currently limited by outdated datasets, simplistic evaluation protocols, and a reliance on black-box classification. To address these issues, we introduce a comprehensive dataset, benchmark, and baseline model for video forgery detection. First, we present \textbf{GenBuster-200K}, a fair dataset of over 200,000 high-quality videos sourced from state-of-the-art generators, featuring diverse real-world scenarios. Second, we propose \textbf{GenBuster-Bench}, a diagnostic benchmark spanning three progressive tracks (In-Domain, Out-of-Domain, and In-the-Wild) to evaluate models across \textit{domain shifts} and \textit{generational shifts}. It also introduces an MLLM-as-a-Judge protocol to assess the quality of the generated forensic explanations. Finally, we develop \textbf{BusterX}, an MLLM baseline with RL training. Instead of direct binary classification, BusterX formulates detection as a visual reasoning task, where the generated reasoning chain serves as detector itself. Experimental results demonstrate that BusterX outperforms several leading MLLMs (e.g., Qwen3.5, Claude-Sonnet-4.6) in both detection accuracy and rationale quality.

Hybrid large language models (LLMs) integrating state space models (SSMs) and full attention face a critical caching bottleneck due to mismatched caching granularities. While full attention allows flexible, token-level cache reuse, SSMs are always restricted to coarse-grained block- or request-level reuse. Consequently, an SSM layer's cache miss can easily invalidates successful fine-grained hits in adjacent attention layers, disrupting the entire reuse pipeline. To resolve this, chunk-level position-independent cache (PIC) reuse is highly desirable to align the caching granularity across all layers. However, enabling PIC reuse for history-dependent SSMs remains fundamentally challenging. To bridge this gap, we propose HyPIC, the first unified framework achieving PIC reuse for hybrid architectures. We introduce residual state propagation and online decay correction, which efficiently adapt offline SSM chunk caches to new contexts by explicitly recomputing minimal boundary tokens. Furthermore, we design a fast parallel recomputation pipeline exploiting the linear superposition property of SSMs to eliminate sequential bottlenecks. Experiments on diverse hybrid models and datasets demonstrate that HyPIC achieves a 2$\times$ speedup in time-to-first-token (TTFT) while maintaining highly competitive accuracy.

Structured road understanding of lane geometry, topology, and traffic element relationships is foundational to safe autonomous driving. While vision-language models (VLMs) offer promising semantic flexibility, they lack the geometric and relational grounding required for precise road reasoning. Conversely, traditional modular systems, e.g., HD maps and topological road graphs, provide structural precision but remain semantically rigid. To bridge this gap, we introduce the Combined Road Substrate (CRS), a graph-grounded framework that makes geometric road structure and open-vocabulary semantics jointly executable in a single representation. CRS enables the automatic generation of compositionally complex and linguistically varied question-answer pairs via recursive graph queries, augmented with a ``grounding for free'' mechanism that ensures logical traceability to specific map elements, and procedurally extracted chain-of-thought supervision traces. We demonstrate that state-of-the-art VLMs - including large, closed-source models - struggle significantly with structured road reasoning, yet training a small 2- or 4-billion-parameter model with as few as 20 to 80 CRS-enriched scenes yields stable gains in compositional reasoning tasks of varying depth. Analysis of model behavior via verifiable reasoning traces reveals a systematic shift in failure modes: whereas baseline models fail at relational scene understanding, CRS-trained models reduce failures to attribute recognition, suggesting that the primary bottleneck in road understanding is not model scale, but the absence of structured supervision.

Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For current multimodal LLMs: even with million-token context windows, frame budgets cover only tens of minutes of densely sampled video, and most evidence is discarded before inference begins. Memory-augmented and agentic approaches help with scale, but their retrieval remains fragmented across modalities and lacks long-range narrative summaries that span days or weeks. We propose MAGIC-Video, a training-free framework built around a multimodal memory graph with interleaved narrative chain: the graph unifies episodic, semantic, and visual content through six typed edges and supports cross-modal retrieval, while the chain distils long-horizon entity biographies and recurring activity events. At inference time, an agentic loop interleaves graph retrieval with narrative fact injection, covering both the modality and time dimensions of ultra-long video in a single retrieval pipeline. On EgoLifeQA, Ego-R1 and MM-Lifelong, MAGIC-Video consistently outperforms strong general-purpose, long-video, and agentic baselines, with gains of 10.1, 7.4, and 5.9 points over the prior best agentic system on each benchmark.

Robust visual recognition under degraded imaging conditions is critical for real-world vision systems.Task-oriented image restoration addresses this problem by enhancing degraded inputs before recognition, but it must preserve natural visual appearance without disrupting the evidence used by downstream recognizers.Existing optimization strategies struggle to satisfy these requirements simultaneously.Restoration driven mainly by visual quality may weaken task-critical cues or introduce texture shifts that are visually plausible but poorly matched to the recognizer.Directly tuning restoration networks with recognition loss is also insufficient, as the restoration model may exploit recognizer-specific shortcut cues and produce visually unnatural artifacts while improving task scores.We propose Causal Mediated Unrolling (CaMeU), an optimization-based framework for task-oriented image restoration with frozen recognition models.Starting from a joint optimization objective, the proposed framework derives a Half-Quadratic Splitting formulation that separates restoration into alternating task-driven and prior-guided updates.The task-driven update introduces an explicit mediator for front-door guided optimization, reducing shortcut bias induced by the recognizer.The prior-guided update performs manifold projection, pulling the intermediate result back toward the natural-image manifold to preserve visual quality.Through this mediated alternating process, the restored image is progressively optimized for both recognition performance and visual quality.Experiments on VOC Haze, VOC Dark, and degraded CUB-200-2011 show that CaMeU consistently improves downstream recognition while reducing visual artifacts.

Vision-language models such as CLIP enable zero-shot classification from arbitrary class names, but under test-time corruptions, their visual encoder projects distorted features onto incorrect textual anchors with high confidence—a phenomenon we term \textbf{modality bias}. Standard entropy minimization reinforces these overconfident errors, triggering a destructive confirmation-bias loop that collapses the predicted label distribution. We propose \textbf{CDIM} (Cross-Modal Information Maximization), an online test-time adaptation method that breaks this loop at three levels. At the \textit{representation level}, a frozen self-supervised DINO backbone is combined with CLIP via a cross-covariance logit ensemble; by projecting text prototypes into DINO's geometric space—rather than the reverse—the classifier operates free of text bias. At the \textit{optimization level}, a gated information-maximization objective (GT-IM) pairs per-sample sharpening with batch-level diversity, while an adaptive gate excludes unreliable samples from the gradient. At the \textit{prediction level}, an online logit adjustment corrects the residual class-distribution skew. Ultimately, \textbf{CDIM} validates its broad effectiveness by delivering robust, competitive performance across demanding setups, including continual TTA, mixed-domain shifts, and diverse domain generalization benchmarks.

The world appears spatially three-dimensional, however, existing large-scale multimodal models are often built mostly around 1D, 2D and 2.5D modalities. To move toward a more complete and actionable understanding of physical reality, models that natively model and generate across 1D, 2D, and 3D modalities are desirable. We present OmniDiMM, an any-to-any foundation model trained on a diverse set of 3D including meshes, Gaussian splats, voxels, and NeRFs; 2D such as images, and 1D like text. We develop tokenizers for a diverse set of 3D modalities, such as NeRF weights triplanes, UDFs, and 3DGSs, that convert them into discrete tokens, which enables multimodal masked modeling for joint training. Out of the box, OmniDiMM can directly perform standard tasks such as novel-view image synthesis and 3D generation from images, where it matches or outperforms existing specialized methods. As an any-to-any model, it can also convert between different 3D representations, such as NeRF weights and UDF, and generate various 3D modalities from 2D inputs, including DINOv2 features and surface normals. Joint training across 3D modalities also leads to strong transfer performance on downstream tasks such as grasping, classification, and object pose prediction. We scale training to a 1B-parameter model using 1T tokens across 1M objects. The pretrained models, training code, and multimodal dataset will be open-sourced.

Distributionally robust optimization (DRO) provides a principled framework for learning under distribution shift, but its practical use is hindered by the difficulty of evaluating worst-case risks for nonconvex loss functions. We study a penalized DRO formulation in which the adversary may choose any distribution but incurs a Wasserstein penalty for deviating from the empirical distribution. We show that the adversary’s problem can be reformulated as an optimization problem over transport maps that push empirical samples to adversarial ones, and we prove that optimal maps are cyclically monotone. We also show that standard adversarial training---based on per-sample local optimization---violates cyclical monotonicity and wastes transport costs unless the adversary is severely restricted. We propose two remedies. First, we introduce multi-start particle ascent, which alternates parallel gradient ascent with reassignment to enforce cyclical monotonicity across samples. Second, we parameterize adversarial maps as gradients of input-convex neural networks, which guarantees cyclical monotonicity by construction. Experiments on robust regression, image classification, and robust control show that our methods consistently outperform standard adversarial training and state-of-the-art baselines, achieving improved robustness and better generalization under distribution shift.

Whole-brain 4D fMRI generation is valuable for modeling functional brain dynamics, yet existing fMRI foundation models mainly target representation learning and downstream prediction rather than conditional predictive generation. We introduce BrainWorld, a structural-prior-conditioned generative model for whole-brain 4D fMRI dynamics. BrainWorld uses sMRI as subject-level anatomical context to guide future fMRI generation, integrating structural information into the denoising process rather than treating it as a parallel modality. Evaluated on 22 datasets spanning diverse cohorts and brain states, BrainWorld generates stable 4D fMRI trajectories up to 400 frames, improves downstream performance through generated-example augmentation, and learns transferable multimodal representations that outperform baselines. Together, these results establish BrainWorld as a condition-aware generative framework for long-horizon brain dynamics modeling and multimodal representation learning.

Naturalistic fMRI offers a time-resolved window into cortical dynamics during continuous multimodal experience, where future brain states are jointly governed by endogenous neural context and exogenous sensory drive. Forecasting such dynamics, however, remains challenging because fast-changing stimulus streams must be reconciled with the sluggish hemodynamic BOLD response, while cortical activity is organized across functionally heterogeneous brain networks. To address these challenges, we introduce BrainVista, a multimodal autoregressive framework for observed-stimulus conditional brain-state forecasting. BrainVista predicts future fMRI states from the history of brain activity and stimulus tokens temporally aligned to each prediction query, enabling autoregressive prediction without access to future ground-truth fMRI states. This design supports causal, temporally consistent modeling of naturalistic brain dynamics under realistic sensory stimulation. Specifically, we design Network-wise Tokenizers for functionally structured brain representations, a Spatial Mixer Head for cross-network interaction refinement, and Stimulus-to-Brain masking to preserve temporally causal stimulus–brain conditioning while preventing future brain-state leakage and stimulus look-ahead. We evaluate BrainVista on Algonauts 2025, CineBrain, and HAD, three large-scale naturalistic fMRI benchmarks, under long-horizon conditional autoregressive forecasting. BrainVista consistently outperforms baselines, improving pattern correlation by 10.8\% and 9.4\% relative to the strongest baseline on Algonauts 2025 and CineBrain, respectively.

Connectomics requires dense segmentation of large-scale electron microscopy (EM) volumes using models trained on small labeled blocks. In practice, a connectomics lab facing a new raw volume has two options: annotate a small block and train on it, or skip annotation and train on the union of available public labeled datasets. We introduce BrainEM, a benchmark that formalizes these options as two standard tracks: the Same-Source Track (Annotate-and-Train) and the Cross-Source Track (Reuse-and-Train). BrainEM brings together 16 EM datasets, including one in-house mouse dataset that we contribute, spanning multiple species, imaging modalities, and resolutions. We further add large-scale test volumes that bring the evaluation closer to realistic practice, and four diverse test targets in the Cross-Source Track. The data, post-processing, and evaluation metrics are fixed across all methods, and the framework is fully model-data decoupled so that new methods can be added with minimal effort. We conduct a systematic evaluation of six representative baselines covering the main technical directions in EM neuron segmentation, making BrainEM the first systematic evaluation at large scale and across diverse cross-source targets. The results differ from prior small-scale evaluations: rankings on the Same-Source Track no longer match those reported on small CREMI splits, and methods diverge sharply on the Cross-Source Track. Both tracks still leave clear room for improvement. We release BrainEM as a public platform to support unified comparison and faster method development in connectomics. All datasets and code are available at https://github.com/kwinderic/BrainEM

Brain foundation models have achieved remarkable advances across a wide range of neuroscience tasks. However, most existing models are limited to a single functional modality, restricting their ability to exploit complementary spatiotemporal dynamics and the collective data scale across different neuroimaging techniques. This limitation largely arises from severe semantic heterogeneity and resolution discrepancies among modalities. To address these challenges, we propose Brain-OF, an omnifunctional brain foundation model jointly pretrained on fMRI, EEG and MEG, capable of handling both unimodal and multimodal inputs within a unified framework. To reconcile heterogeneous spatiotemporal resolutions, we introduce the Any-Resolution Neural Signal Sampler, which projects diverse brain signals into a shared semantic space. To further manage semantic shifts, the Brain-OF backbone integrates DINT attention with a Sparse Mixture of Experts, where shared experts capture modality-invariant representations and routed experts specialize in modality-specific semantics. Furthermore, to explicitly internalize the characteristics of neural activity through self-supervised learning, we propose Masked Temporal-Frequency Modeling, a dual-domain pretraining objective that jointly reconstructs brain signals in both the time and frequency domains. Brain-OF is pretrained on a large-scale corpus comprising around 40 datasets and demonstrates superior performance across diverse downstream tasks, highlighting the benefits of joint multimodal integration and dual-domain pretraining. Our code will be made publicly available upon acceptance.

Object-level spatial-temporal understanding is essential for video question answering, yet existing multimodal large language models (MLLMs) encode frames holistically and lack explicit mechanisms for fine-grained object grounding. Recent work addresses this by serializing bounding box coordinates as text tokens, but this text-coordinate paradigm suffers from a fundamental *modality mismatch*: object information is inherently visual, yet encoding it as text incurs a high token cost that forces aggressive temporal downsampling. We propose *BoxTuning*, an object-aware visual prompting framework for multimodal model fine-tuning that moves spatial-temporal object states from text-coordinate serialization into the visual stream while retaining only object identity in a compact text legend. Colored bounding boxes and trajectory trails encode geometry and motion on video frames, while the color-to-object legend provides the minimal textual identity bridge. This reduces the token cost significantly, achieving 87-93\% text token reduction in practice. It also preserves full temporal resolution, where the trajectory trails further encode inter-frame motion direction and speed within each keyframe, recovering fine-grained dynamics that text-coordinate methods are forced to discard. Experimental results on five video QA benchmarks (CLEVRER, Perception Test, STAR, NExT-QA, IntentQA) show that BoxTuning surpasses text-coordinate baselines on spatially oriented tasks and avoids their degradation on reasoning-centric tasks, establishing object-aware visual prompting as a natural and efficient way to convey object information to MLLMs.