NeurIPS 2026 Papers

Causal reasoning from observational data becomes significantly challenging when the underlying causal structure is only partially known. In this work, we study the the equivalence class of structural causal models (SCMs) with latent variables sharing the same set of conditional independencies, as represented by a partial ancestral graph (PAG). Specifically, we provide a new characterization of SCM-induced causal diagrams in this equivalence class using differentiable parameters. Building on this characterization, we introduce a new model class called PAG-constrained neural causal models ($\mathcal{P}$-NCMs) which parameterize this equivalence class of SCMs. We prove that $\mathcal{P}$-NCMs are expressive enough to represent counterfactual distributions induced by any SCM in the class, while remaining consistent with the structural constraints shared across all its members. Finally, we demonstrate how the differentiable parameterization of this model class enables causal inference under Markov equivalence by reducing counterfactual partial identification to an optimization problem over $\mathcal{P}$-NCMs. We establish the theoretical soundness of this approach and validate its performance on simulations.

Online Conformal Prediction (OCP) sequentially constructs prediction sets whose average empirical coverage converges to a target level over time, for arbitrary, potentially adversarial datasets. In the multi-level setting of OCP, prediction sets are produced at $d$ coverage levels at once. Prior work showed that online gradient descent with lazy isotonic projections produces sets properly nested across levels, but with a $\sqrt{d}$ dependence in the per-level coverage convergence rate. Here, we both generalize and improve prior work. First, we show that lazy isotonic projections can be safely used for the construction of multi-level online conformal prediction sets from \emph{any} online learning algorithm. Then, through a black-box reduction, we show that the linearized regret of the online algorithm itself automatically gives control over both per-level calibration and distributional consistency of multi-level predictions via Fenchel duality. Finally, by using the Weighted Interval Score, the standard scoring rule for assessing multi-level interval forecasts, we prove that these projections reduce both the size of the sets and their under-coverage. We show two instantiations of our theory, $p$-norm Online Mirror Descent and coordinate-wise Universal-Portfolio, both improving the dependence on the number of levels to $\sqrt{\log d}$ for the multi-OCP problem. Experiments on stock prices, electricity demand, and synthetic streams confirm consistent gains in coverage-width trade-offs over existing baselines.

We investigate data filtering for large model pretraining via new scaling studies that target the high compute, data-scarce regime. In spite of an apparently common belief that filtering data to include only high-quality information is essential, our experiments suggest that with enough compute, the best data filter is no data filter. We find that sufficiently trained large parameter models not only tolerate low-quality and distractor data, but in fact, including nominally 'poor' data improves model performance.

Optimal transport (OT) provides a principled framework for mapping between probability distributions. Despite extensive progress, applying OT to large-scale data remains computationally demanding, and the resulting pointwise transport plans are often difficult to interpret. We introduce Optimal Mixture Transport (OMT), a scalable framework that shifts the transport paradigm from individual samples to mixtures of subpopulations, reformulating the transport problem as a strictly biconvex optimization with a unique global minimizer. We further establish theoretical guarantees on the stability of the OMT map, showing that bounded perturbations of the underlying distributions lead to bounded changes in the transport plan. By formulating subpopulations as exponential-family distributions, OMT decouples computational complexity from the sample size, scaling solely with the number of mixture components. We demonstrate the effectiveness and practicality of OMT on a wide range of synthetic benchmarks and real-world datasets, including image data and large-scale single-cell RNA sequencing measurements.

Long-form omni-modal video understanding requires models to integrate vision, speech, and ambient audio with coherent long-context reasoning. Existing video benchmarks often trade off temporal scale, modality coverage, open-ended interaction, and interpretable scoring. To address this gap, we introduce $\textbf{LongShOTBench}$, a long video evaluation benchmark designed around three coupled goals: holistic omni-modal integration, intent-driven open-ended interaction, and rubric-level diagnosis. It constructs single- and multi-turn questions from practical viewing scenarios, involving systematical tasks for probing visual, speech, ambient-audio, temporal, and cross-modal reasoning. Each item includes a reference answer and a weighted criterion-level rubric, enabling evaluation to identify which perceptual facts, temporal links, modality-grounding requirements, and reasoning steps are satisfied or missed. All samples are manually verified and corrected to improve grounding, clarity, and rubric reliability. We also introduce $\textbf{LongShOTAgent}$, a training-free omni-modal evidence-seeking agent that couples full-video preprocessing with targeted retrieval, query-adaptive segment refinement, and explicit claim verification over visual, speech, and non-speech audio evidence. Its iterative search-refine-verify loop exposes intermediate evidence and lets modality-specific specialists re-analyze relevant moments before answering. We perform comprehensive evaluation of 105 video-capable models spanning open-source omni-modal models, vision-language systems, audio LLMs, agentic pipelines and closed-source APIs. Across this broad evaluation, current MLLMs remain far from saturating LongShOTBench, while our LongShOTAgent emerges as the strongest training-free system, reaching 66.64\% overall. By releasing the benchmark, leaderboard, and agentic method, our work provides the community with a shared, interpretable testbed for evaluating and advancing long-form omni-modal video reasoning.

Hartigan's $k$-means algorithm has theoretical advantages over the standard Lloyd's variant, which has become synonymous with ``$k$-means''. Yet, Hartigan's algorithm is far slower in practice due to its inherently sequential calculations. We devise a Batched Hartigan's method that enables vectorized calculation by exploiting the triangle inequality to expose a set of parallel-safe updates and a smaller set of sequential updates. This makes Hartigan's method competitive with Lloyd's in execution speed for the first time.

Feed-forward 3D reconstruction models have demonstrated strong generalization under large-scale pre-training, yet they struggle in long-tail scenarios such as low-light reconstruction, joint human-scene reconstruction, and test-time adaptation. We observe relational attention structure collapse, manifested as the failure of cross-view correspondences, as a primary cause of these limitations. While adaptation offers a practical way to bridge this gap, existing parameter-efficient fine-tuning (PEFT) approaches mainly perform channel-wise feature adjustment and lack mechanisms to explicitly adapt relational structures, leaving correspondence failures unresolved. In this work, we formulate adaptation of 3D reconstruction models as a problem of correspondence recovery under domain shift and propose 3R-Adapter, a PEFT paradigm for long-tail 3D reconstruction scenarios. Our method consists of three components: Deformable Retrieval for task-adaptive relation candidate retrieval, Relational Rewiring for reconstructing cross-view relational structures, and Consistency Refinement for injecting the rewired relations into stable predictions. Extensive experiments on low-light reconstruction, joint human-scene reconstruction, and test-time adaptation demonstrate that our approach significantly improves robustness over existing PEFT methods while maintaining efficient lightweight adaptation.

AI video generation is evolving rapidly. For video generators to be useful for applications ranging from robotics to film-making, they must consistently produce realistic videos. However, evaluating the realism of generated videos remains a largely manual process -- requiring human annotation or bespoke evaluation datasets which have restricted scope. Here we develop an automated evaluation framework for video realism which captures both semantics and coherent 3D structure and which does not require access to a reference video. Our method, 3DSPA, is a **3D** **S**emantic **P**oint **A**utoencoder utoencoder which is trained to reconstruct held out 3D point trajectories which have been augmented with DINO semantic features. By combining both semantic and geometric representations, 3DSPA enables robust assessments of realism, temporal consistency, and physical plausibility in generated videos. Experiments show that 3DSPA outperforms leading VLMs by more than 10\% in identifying videos which violate physical laws, and more than doubles the correlations between human and auto-eval ratings in judging physical common sense and motion quality across multiple generative video datasets. Our results demonstrate that enriching trajectory-based representations with 3D semantics offers a strong foundation for benchmarking generative video models, and implicitly captures physical rule violations.

Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neural 3D generators inherently lack. Authoring such procedural content, however, demands deep expertise in 3D software APIs, parametric design, and code-level geometric reasoning. In this paper, we propose 3DCodeBench, a systematic benchmark for evaluating vision-language model (VLM) agents for procedural 3D generation in 3D modeling software. Specifically, 3DCodeBench evaluates how effectively 11 advanced VLMs can serve as procedural 3D modelers by transferring text and image references into procedural code for software. Recognizing that automated metrics may not fully capture the perceptual quality of 3D shapes, we build 3DCodeArena, a ranking platform based on human preference between generated pairs. From extensive evaluations and results, we observe that: (1) Failures mostly arise from API usage, while successful renders still suffer from disconnected or floating 3D geometric components. (2) Test-time scaling, such as higher thinking budgets and multi-turn refinement, improves performance overall. Our findings highlight a critical need for high-quality procedural coding data to advance commercial VLMs. Furthermore, effective procedural 3D modeling requires a robust execution environment that provides high-fidelity feedback for iterative refinement. To accelerate research in this domain, we release 3DCodeBench—including the curated data, benchmark, evaluation protocol, and qualitative results—as a foundational tool for developing VLM-based 3D modelers.

In this paper, we address the Cross-View Object Re-Identification (ReID) task, aiming to match identities across drastically different viewpoints. We focus specifically on Single-View Aerial-Ground ReID (SV AG-ReID), where models train on one viewpoint and must generalize to another at inference. To bridge the viewpoint gap of Cross-View ReID, related work employs generative models to synthesize novel views from source images as additional training data. We leverage recent advances in large-scale single-view 3D mesh reconstruction to lift source images into textured meshes and to render them from new viewpoints. However, this pipeline produces unreliable data in two distinct ways, and addressing both is vital for synthetic data to serve as an effective training signal. First, the reconstruction may fail and produce geometrically incorrect meshes, resulting in severe corruption in rendered novel views. Second, even when the geometry is correct, the rendered novel views contain hallucinated textures in regions not visible in the source image, which may degrade training if used naively. We address both shortcomings by exploiting a signal that prior generative methods do not naturally expose. Indeed, the reconstructed mesh carries a per-pixel partition between regions visible from the source view and regions that the reconstruction model had to hallucinate, available as a deterministic byproduct of rendering. We introduce this per-pixel visibility map and exploit it in a two-stage design. Cross-View Consistency Filtering (CVCF) discards geometrically incorrect meshes by ensuring multi-view consistency between source and novel views over visible patches. Visibility-Aware Attention Supervision (VAAS) leverages the visibility map to guide the model's attention toward reliable regions of the rendered view during training. Combined, these two components enable our method, 3D-VITAL, to better leverage the synthetic signal from single-view 3D mesh reconstruction, benefiting from wider viewpoint augmentation. 3D-VITAL sets a new state-of-the-art on three SV AG-ReID benchmarks (AG-ReID, AG-ReID.v2, MOO). Code and data will be released at \url{url}

3D multimodal large language models (3D MLLMs) describe a 3D object as a whole but cannot address, name, or reason about its parts. Prior part-aware attempts add segmentation decoders, heavier 3D encoders, or bounding-box grammars at substantial parameter cost. We take a fundamentally different path: we reorganize the input token stream so that parts become directly addressable through the LLM’s own vocabulary. Our model, 3D-PLOT-LLM, partitions the frozen point encoder’s patches into K locally coherent regions and inserts, before each region’s patch tokens, a learnable per-region marker and a reserved vocabulary token \; a Marker-Space Refinement (MSR) module then conditions each marker on its region’s spatial statistics and adjacency neighbors. The model thus cites parts in its output and follows prompts that refer to parts by token, a capability absent from prior object-level 3D MLLMs. To probe this interface, we construct PartVerse-QA, a vocabulary-level part-QA benchmark adapted from PartVerse mesh annotations (77K training pairs and 588 held-out queries on disjoint object splits), on which 3D-PLOT-LLM reaches caption-to-slots Jaccard 0.459 and Exact-match 13.78% (+64% relative over the strongest non-MSR variant), with a slot-to-caption GPT-4o judge of 44.68. On the 3DCoMPaT-GrIn part-aware grounded description benchmark, 3D-PLOT-LLM outperforms PointLLM, Kestrel, PARIS3D, and SegPoint on every text-output metric, and ShapeLLM on 3 of 4, with up to +3.03 GPT-4o judge over PointLLM. On Objaverse whole-object captioning, adding PartVerse-QA at Stage 2 yields +0.65 SBERT and +1.85 GPT-4o over PointLLM, and tops PointLLM-PiSA on 4 of 5 traditional metrics (SBERT, SimCSE, BLEU-1, METEOR) despite targeting a different (part-grounded) objective. All with under 1M new trainable parameters on a frozen point encoder, an order of magnitude below prior part-aware 3D MLLMs, and no segmentation decoder or bounding-box head.

3D Gaussian Splatting (3DGS) has become a vital tool in novel view synthesis. 3D Gaussian functions with attributes like color, opacity, and scale are stacked together to explicitly model a radiance field. However, discrete 3D Gaussians usually produce poor depth with few geometry details but lots of floaters, which makes modeling smooth radiance fields remain a challenge. To address this issue, we propose to learn a radiance field within a continuous view-dependent color field parameterized by neural networks. With the continuous constraints in color, the bias on low-frequency signals of neural networks highly encourages the geometry to contribute to high-frequency color variations on images, but not solely relying on the color attribute itself. Moreover, we impose a constraint to improve the Lipschitz continuity of the neural color field, making large changes of each Gaussian's color also match with large changes of its position in terms of a ratio. To this end, we additionally introduce novel self-learning strategies to learn neural view-dependent color fields without any external knowledge or priors, aiming for better generalization. Our numerical and visual comparisons on widely used benchmarks justify our idea and show better ability of high fidelity geometry recovery in 3DGS.

We present 3D consistency tokens, a compact set of 3D anchors that ground cross-view correspondence in explicit geometry. While feedforward Gaussian models amortize per-scene optimization into a single forward pass, their rendering quality still falls short of optimization-based pipelines. A primary cause lies in the relatively inaccurate correspondences they recover by comparing each image token to others across views based on appearance and semantic cues, which can be ambiguous in repetitive or semantically uniform regions. The proposed consistency tokens alleviate such ambiguity by routing image tokens that look alike but originate from different parts of the scene to distinct anchors, so that cross-view matches are established through shared 3D locations rather than appearance alone. We construct the consistency tokens from point clouds produced by either Structure-from-Motion or modern geometry foundation models, both of which can be noisy or incomplete. To address this, we adopt a bidirectional cross-attention architecture in which the two token sets co-refine one another, with image tokens gaining geometric grounding from the consistency tokens and the consistency tokens being corrected by the appearance cues of the images. On DL3DV-10K and in cross-dataset evaluations on Mip-NeRF 360 and Tanks \& Temples, our approach surpasses prior feedforward models and attains quality competitive with optimization-based pipelines, while preserving single-pass efficiency.

Despite advances in vision-language-action (VLA) models, they remain limited in highly dynamic game settings such as 3D open worlds and competitive player versus player (PvP) settings, where agents must efficiently extract sparse, actionable signals from dense visual input while integrating multimodal cues to track off-screen high-value targets in real time. To address this, we introduce 3A-VLA (Abstraction-Aligned Action VLA), a framework that grounds action learning in explicit intention and environment abstractions rather than superficial pattern matching. We introduce dual task-agnostic abstractions: the intention abstraction (IA), which condenses verbose instructions and reasoning into explicit semantic primitives, and the environment semantics abstraction (ESA), which structures dense visual streams into a spatial--functional affordance representation to guide grounded actions. We further propose an abstraction alignment reweighting (AAR) module that adaptively reweights the action imitation loss. A continuous intention--environment alignment signal is used to emphasize reliable action supervision when abstractions agree and reduce the influence of ambiguous demonstrations when they diverge, thereby learning a policy that balances fine-grained control and high-level reasoning without the need for manual rules. Extensive experiments show that 3A-VLA yields state-of-the-art results in both open-world (Minecraft) and competitive PvP (Game for Peace) settings. It also demonstrates strong zero-shot generalizability to high-fidelity games across different domains, including Valorant, CS2, GTA V, Elden Ring, and Mount \& Blade. Code and models will be publicly released at https://3a-vla.github.io/.

Many modern learning approaches are still struggling with spatial reasoning tasks, i.e. they lack the ability to utilize geometric information of perceived entities and their spatial relation to each other to solve problems. We introduce a novel Adaptive Neural Cellular Automata (aNCA) architecture which uses deformable convolutions to dynamically adapt the perceptive field and iteratively reason over 2D spatial relations on grid-like data structures (e.g. images). Empirical results on public benchmarks show state of the art comprehensible results with high generalization abilities for solving image based puzzles like Sudoku or finding the shortest path in a maze.

Predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary. Yet, we still lack a clear understanding of how decision makers learn from ML-based decision support (ML-DS). In this paper, we introduce a general computational framework, the 2-Step Agent, to capture this process. As a prediction from an ML model contains information about the training data, a prediction can also be used for inference. Our framework models (i) how a prediction for a new observation affects the beliefs of a rational Bayesian agent, and (ii) how this change in beliefs affects the estimation of causal effect, the downstream decision, and the subsequent outcome. In addition to the framework itself, we make three contributions. First, for the linear Gaussian setting, we derive a tractable solution for the challenging Bayesian inference problem we introduced, i.e. one in which the agent infers from an ML prediction. Second, we experimentally identify conditions under which ML-DS is beneficial. Third, we show that a single misaligned prior belief can be sufficient for ML-DS to lead to worse downstream outcomes compared to no decision support *even when the ML model is well-specified and the agent is perfectly rational*. Hence, even under ideal conditions, ML-DS can do more harm than good.

We study connections between the sample cost of replicability, which requires an algorithm to produce consistent outputs in different runs, and the sample complexity in the high success probability regime for distribution testing algorithms. Specifically, we consider a stronger notion of replicability, which we term as strong replicability, and show that any $\rho$-strongly-replicable testing algorithm can be converted in a blackbox manner to a tester with at most $\exp(-\tilde{\Omega}(\rho^{-2}))$ failure probability under the same sample budget. Our conversion is optimal for many natural testers. As applications of our conversion theorem, we obtain tight sample lower bounds for strongly replicable testers for coin bias and closeness testing.

Helpful-only models—that is, models that are trained to always follow user intent—are valuable for dangerous capability evaluations and other areas of AI R&D where refusals would be an obstacle. Little is known about the generalization properties of helpful-only training: they refuse less than their harmless counterparts, but previous work has not studied other dimensions of their alignment. We find that existing helpful-only models have serious shortcomings. Some show emergent misalignment, others have residual refusal behaviors, and most show poor steerability, sycophancy, and an incoherent character. We show that simple anti-refusal training can cause many of these issues. None of these problems are necessary consequences of helpful-only training, though: we show that synthetic document fine-tuning and adding character-related questions to SFT and RL can mitigate them.

Training-free camera control for pretrained flow-matching video generators is a partial-observation inverse problem: a depth-warped guidance video supplies noisy evidence on a subset of latent sites, which the sampler must reconcile with the pretrained prior. Existing methods struggle to balance the trade-off between trajectory adherence and visual quality and the heuristic guidance-strength tuning lacks robustness. We propose $h$-control, which resolves this dilemma through a structural change to the sampler: each outer hard-replacement guidance step is augmented with an inner-loop block-conditional pseudo-Gibbs refinement on the unobserved complement at the same noise level, with provable convergence to the partial-observation conditional data law. To accelerate convergence on high-dimensional video latents, we exploit their conditional locality, partitioning the unobserved complement into 3D patches, each tracked by a custom mixing indicator that adaptively freezes converged patches. On RealEstate10K and DAVIS, $h$-control attains the best FVD against all seven training-free and training-based competitors, outperforming every training-free baseline on every reported metric.