NeurIPS 2026 Papers

Recent advances in video generation have achieved impressive visual quality, yet they often fail to produce physically consistent dynamics due to the lack of explicit modeling of underlying physical processes. Existing approaches either rely on simulators with strong assumptions or use coarse semantic guidance, and further struggle to effectively inject physical priors into generation models. In this work, we propose Seeing the Unseen, a unified framework for physics-grounded video generation. Our approach decomposes the problem into two stages: learning physical dynamics and injecting them into video synthesis. First, we introduce a lightweight Particle-based Graph Dynamics Simulator (PGDS) that learns generalizable physical interactions from data and predicts plausible 3D motion trajectories. Second, we propose a Visible–Invisible Motion Field (VIMF) that captures both motion observable in the input frame and motion that emerges over time due to object dynamics. This representation enables more complete and structured motion guidance compared to conventional physical signals. By integrating these trajectories into a diffusion-based generator, our method produces videos that are both visually coherent and physically consistent. Extensive experiments demonstrate improved motion accuracy, interaction consistency, and reduced physical artifacts compared to strong baselines.

3D multimodal language models are becoming a foundation for embodied agents, indoor robotics, and human–AI interaction, but their answers and explanations often remain weakly tied to the specific objects and spatial relations observed in a 3D scene. This paper aims to make 3D reasoning more faithful by reducing language-prior rationalization and forcing reasoning chains to depend on verifiable scene evidence. We propose Anti-Rationalization Chain-of-Thought (AR-CoT), a plug-in training and decoding framework that represents each reasoning step with an explicit evidence pointer and scores candidate answer-chain pairs by their scene-evidence gain. AR-CoT contrasts scene-conditioned rationales with a frozen text-only prior, verifies local object and relation claims, and uses decoy-twin scene pairs to encourage reasoning chains to change when the relevant spatial evidence changes. Experiments on standard 3D QA and grounding benchmarks, as well as MSQA, Beacon3D, and shortcut-sensitive stress tests, show that AR-CoT consistently improves multiple 3D MLLM backbones while strengthening chain grounding, decoy-twin contrast, and scene-swap sensitivity. These results suggest that anti-rationalization offers a practical and verifiable route toward more accurate, interpretable, and scene-faithful 3D multimodal reasoning.

Scene text encodes high-density semantic information, raising privacy risks for automated vision systems. Existing privacy-preserving adversarial methods mainly target Scene Text Recognition (STR) by inducing character-level misrecognition, yet text regions remain detectable, enabling manual inspection or downstream recovery. We argue that stronger privacy requires suppressing Scene Text Detection (STD) during localization, hiding text as background to bypass subsequent OCR pipelines. To this end, we propose **AR-Attacker** (**A**ttention-guided **R**einforcement learning text **Attacker**), a black-box attack framework that generates sparse, visually imperceptible perturbations to effectively suppress STD outputs. We formulate the attack as a Markov Decision Process (MDP) and design an attention-guided action space, which leverages a frozen surrogate model to focus perturbations on salient text regions. Furthermore, AR-Attacker employs a discrete-continuous hybrid policy optimized with Proximal Policy Optimization (PPO), which jointly selects perturbation locations and magnitudes. Empirical results show that AR-Attacker surpasses state-of-the-art baselines by 30% in text removal rate while simultaneously reducing query counts by 40%. Remarkably, the framework maintains high visual fidelity ($\textit{PSNR} > 45$ dB), advancing the "visible to humans, invisible to machines" privacy paradigm through a robust RL-based approach.

Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoints remains largely unexplored. We study this problem through multi-robot cooperative dynamic spatial reasoning, where a model must answer spatial, temporal, visibility, and coordination questions by integrating synchronized egocentric videos from a team of moving robots. To support this setting, we introduce CoopSR, the first benchmark for this task, together with EgoTeam, a multi-robot egocentric QA dataset. EgoTeam contains 114,227 QA pairs spanning 19 question types, four difficulty tiers, and three team sizes in Habitat and iGibson, along with a real-world test set of around 2,326 QAs collected using two quadruped robots. We further propose SP-CoR (Spectral and Physics-Informed Cooperative Reasoner), an MLLM framework for fine-grained cooperative spatial reasoning. SP-CoR combines dynamics-aware multi-robot frame sampling, spectral- and physics-guided view fusion, and physics-aligned prompt distillation, enabling the model to benefit from privileged robot-pose supervision during training while requiring only egocentric videos at test time. Across 22 MLLM baselines, SP-CoR consistently improves cooperative reasoning, outperforming the strongest fine-tuned baseline by +3.87% on Habitat and +7.12% on iGibson. It also shows stronger generalization to unseen team sizes and real-world robot tests. We will release the benchmark and code.

While multimodal large reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions remain underexplored. In this paper, we investigate the underlying causes of hallucinations in MLRMs and accordingly propose a reasoning-centric training framework for mitigation. Specifically, we find that introducing reasoning mechanisms exacerbates models' reliance on language priors and overlooks visual inputs, leading to CoTs with reduced visual cues but redundant text tokens. Guided by the Information Bottleneck (IB) principle, we propose selectively filtering redundant thinking tokens to obtain a more compact, signal-efficient CoT that preserves task-relevant information while suppressing noise. We also observe that the quality of the reasoning trace largely determines whether hallucination emerges in final answers. To leverage this, we introduce a reasoning-enhanced preference optimization scheme that constructs training pairs using high-quality AI feedback. We further propose generating high-quality negative samples for contrastive optimization via a multimodal hallucination-inducing mechanism that exposes model hallucination behaviors through carefully crafted visual and textual inducers. By modeling CoT chains as intermediate representations between inputs and final answers, we establish an IB-based theoretical justification for our method. Extensive experiments reveal consistent hallucination reduction across diverse MLRMs and benchmarks.

Recent progress in speech-driven 3D facial animation has improved vertex level reconstruction quality, but speech-consistent visible articulation remains difficult. This is because speech production follows structured and constrained lip jaw coordination and the mapping from acoustics to motion is inherently one to many. Motivated by the structured patterns of visible articulation, we propose a novel articulation-aware framework that models visible speech through directional lip motions and composes them into geometry consistent facial deformation. To represent visible articulation with three canonical directional motions, spreading, opening, and protrusion, we propose a Speech Articulatory Memory (SAM) that captures the correspondence between speech and directional articulatory motions under phonetic context through key-value memory structure based retrieval and decoding. Then, a Topology-aware Articulatory Composition (TAC) integrates the predicted directional motions under mesh topology to produce coherent 3D facial motion. Experiments on VOCASET and TFHP show that our method achieves the-state-of-the-art performance on standard reconstruction metrics and improves visible articulatory distance and velocity fidelity for key lip factors, while a user study confirms clear preference in lip sync and realism.

Selecting a next motion in a populated scene is not just a matter of avoiding what is currently in the way: an action can be locally feasible yet drift onto the road instead of the crosswalk, cut into a stream of crossing pedestrians, or bottleneck a narrow passage. These failure modes are invisible from the current state alone, and acting on them requires reasoning about what each candidate action will cause. World models offer exactly this, namely action-conditioned predictions of the future, but rolling them out at every decision step is a cost deployable navigation systems cannot pay, and the field has largely traded foresight for speed. We argue this is a false dichotomy. The natural place for a world model in human-aware navigation is at training time, as a preference oracle that distills foresight into a fast policy, rather than at inference time, as an online planner. We pair a discrete visual action prior with two task-aligned world models, one for nearby social dynamics and one for future scene semantics, that score candidate actions by their predicted consequences and refine the policy through group-relative preference distillation. At deployment, both world models are removed and the policy acts in a single forward pass. Across five held-out scenes, this yields navigation that is simultaneously safer, more socially and group-coherent, and more goal-directed than strong reactive and learned baselines, with naive observers rating the resulting motion as more human-like. Taken together, our findings point to a different approach for bringing world-model foresight into deployable agents: not accelerating rollouts, but amortizing them into the policy so that the cost of looking ahead is confined to training.

Cross-view localization classically asks: where does this ground image lie on the satellite tile? Existing methods are typically limited to 3-DoF estimates---an $(x,y)$ position and a yaw angle---because nadir satellite imagery provides no direct cues for roll, pitch, or altitude, forcing a reliance on planar-motion and zero-tilt assumptions. These assumptions break on real terrain with slopes, ramps, and tilted camera mounts. To overcome this, we introduce a single UAV image as an intermediate viewpoint: it reveals the 3D structure invisible from nadir, supplies the cues for roll, pitch, and altitude that the satellite alone cannot provide, and needs only spatial overlap with the ground camera---no known relative pose is required. Building on this insight, we propose **Cross3R**, a flexible feed-forward model that ingests a satellite tile together with a UAV image, a ground image, or both, and, in a single forward pass, recovers a cross-view 3D point cloud, the 6-DoF poses of every input camera, and the on-tile $(x,y)$ position and yaw of each perspective camera. For training and evaluation, we also construct **CrossGeo**, a 278K-image tri-view dataset spanning 85 scenes across every continent except Antarctica. On CrossGeo, Cross3R consistently outperforms feed-forward 3D baselines in point-cloud reconstruction, 6-DoF camera-pose estimation, and cross-view localization. On KITTI, it outperforms dedicated cross-view methods trained on KITTI on most metrics, despite having no KITTI training itself.

Diffusion-based video generation has achieved impressive visual fidelity, yet enforcing temporally consistent motion under explicit control signals remains challenging. Recent noise-warping approaches construct temporally correlated noise by transporting the initial latent noise via diffeomorphic deformation fields derived from optical flow, but this spatial resampling inherently destroys the i.i.d. Gaussian structure of the noise, requiring post-hoc correction steps at the cost of non-trivial computational overhead. We propose \textbf{Seed-Your-Motion}, by conditioning the a priori latent noise on optical flow via per-location orthogonal transformations in latent channel space, parameterized as products of the Householder Transformation. This channel-space formulation has an advantage of preserving the spatial Gaussianity exactly by construction, requiring neither Jacobian corrections nor post-hoc distribution restoration, while at the same time inducing structured cross-frame correlations that ensures geometric consistency across time. With no learnable parameters and a single forward pass, our method is agnostic to model architecture and can be plugged seamlessly into any video diffusion fine-tuning pipeline. Extensive experiments on motion-transfer and camera-controlled video generation benchmarks demonstrate that our method matches or outperform the state-of-the-art noise-warping baseline, while achieving a 2.7× speedup in processing time. The results suggest that the channel-space Householder transformations provide a principled and efficient alternative to noise-warping based motion-controllable video diffusions.

Reasoning segmentation requires localizing objects from complex, implicit textual queries. Existing methods either rely on the MLLM to reason implicitly within hidden representations, or produce explicit but purely textual chain-of-thought that terminates in a coarse bounding box. In both cases, the reasoning process is not grounded in visual evidence at each step, leaving intermediate errors unverifiable, which can propagate to the final prediction. We propose Reasoning with Visual Anchors (ReVA), a framework where each chain-of-thought step is explicitly grounded to a specific image region. ReVA introduces anchor tokens into intermediate reasoning steps, each directly aligned with region-level features in the image encoder's latent space. As the model reasons step by step, each anchor attends to its corresponding image region, grounding inference in concrete visual evidence. To supervise the full reasoning chain, we further require each anchor to correctly transition to the next along the spatial relation described in the text. This progressively guides the model toward the target and produces the correct segmentation mask. To support training, we construct a large-scale Chain-of-Anchor dataset of over 245K quality-filtered samples from the RefCOCO series, each annotated with a spatially grounded chain-of-thought containing explicit anchor regions. The dataset is constructed by leveraging a strong MLLM to generate reasoning traces, followed by a three-stage verification pipeline ensuring spatial accuracy and reasoning quality. Experiments on reasoning and referring segmentation benchmarks demonstrate that ReVA achieves state-of-the-art performance (e.g., +5.4 gIoU and +6.7 cIoU on the ReasonSeg test set), with ablations showing that reasoning in visual evidence is key to the improvement.

We propose using Vision-Language Models (VLMs) for macro placement in chip floorplanning, a complex optimization task that has recently shown promising advancements through machine learning methods. Because human designers rely heavily on spatial reasoning to arrange components on the chip canvas, we hypothesize that VLMs with strong visual reasoning abilities can effectively complement existing placement algorithms. We introduce VeoPlace (Visual Evolutionary Optimization Placement), a novel framework that uses a VLM—without any fine-tuning—to guide the actions of a base placer by constraining them to subregions of the chip canvas. The VLM proposals are iteratively optimized through an evolutionary search strategy with respect to resulting placement quality. Using global half-perimeter wirelength (gHPWL) after standard-cell placement and legalization as the evaluation metric, VeoPlace boosts ChiPFormer performance on 9 of 10 benchmarks with peak reductions exceeding 32%. We further demonstrate that VeoPlace generalizes to analytical placers, improving DREAMPlace on all 8 evaluated Superblue benchmarks with gains up to 4.3%. Our approach opens new possibilities for electronic design automation tools that leverage foundation models to solve complex physical design problems.

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees for AI agents. We present a formal model to reason about the security and expressiveness of agent planners. Using this model, we characterize the class of properties enforceable by dynamic taint-tracking and construct a taxonomy of tasks to evaluate security and utility trade-offs of planner designs. Informed by this exploration, we present Fides, a planner that tracks confidentiality and integrity labels, deterministically enforces security policies, and introduces novel primitives for selectively hiding and revealing information. Its evaluation on AgentDojo and WASP demonstrates that this approach enables us to complete a broad range of tasks with security guarantees.

Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene. Existing defenses usually protect one boundary, either the planner/runtime or the action sink, and therefore do not by themselves secure both surfaces. We present SecureClaw, a dual-boundary architecture that places authorization at the effect sink and plaintext confinement at the read boundary. Sensitive reads pass through a trusted gateway that replaces raw values with opaque handles and, in the evaluated deployment, bounded summaries as an explicit declassification interface. Writes that change external state follow a PREVIEW$\rightarrow$COMMIT protocol in which only a trusted executor may commit the exact canonical request authorized by policy. The runtime can still plan over summaries and symbolic references, but cannot directly dereference secrets or perform side effects. Across AgentDojo, AgentLeak, and Agent Security Bench (ASB), SecureClaw is the only defense we evaluate in a common harness that simultaneously retains usable task utility and achieves 0\% attack success rate (ASR) on ASB, 0.64\% ASR on AgentDojo, and 3.23\% overall leak on AgentLeak's attacked parity lane, which measures final-output and internal-relay leakage.

The rapid emergence of generative image models has led to the development of specialized watermarking techniques, particularly in-generation methods such as seed-based embedding. However, current evaluations in this area remain largely empirical, making them heavily reliant on the specific model architectures used for generation and inversion. This prevents any clear conclusion on the performance of any method, especially regarding security, for which a rigorous definition is lacking. Against this approach, we argue that the effectiveness of a watermarking scheme should be established purely through a thorough theoretical analysis. This is enabled by decoupling the model-dependent part from the actual decision mechanism of the watermarking system. Using this decoupling, we introduce a formal evaluation framework based on security, robustness, and fidelity. This allows precise comparisons between watermarking systems through a characteristic surface representing the trade-off between these three quantities, independent of any generative model. Based on this framework, we propose SSB, a novel watermarking method that generalizes previous seed-based methods by allowing to reach any security-robustness-fidelity regime on its characteristic surface. This work opens the door to the design of modern watermarking systems with theoretical guarantees that do not necessitate any costly empirical evaluations.

Many machine-learning quantities are straightforward to compute once a finite data set is fixed, but their population versions can encode much harder computational problems. We study this gap for population risk, attribution, counterfactual explanation, and calibration certification, asking which of these quantities can be approximated in time polynomial in the requested number of bits. The formal basis is the Kawamura-Cook second-order complexity theory, instantiated here with compact-domain real functions carrying explicit evaluation, continuity, and range information. In this framework, expected risk has exactly the difficulty of real integration. Integrated gradients behave differently by dimension: in one dimension they reduce to evaluating endpoints, while in two dimensions even one coordinate can already encode one-dimensional integration when the relevant derivative is provided. The same lens separates the costs in related explanation and certification methods. Interventional SHAP is integration-hard even with two features, succinct coalitional SHAP is #P-hard, nearest-threshold counterfactual search is NP-hard, and continuous calibration certificates combine integration with maximization. These results give a taxonomy of when population-level explanation and certification admit polynomial-time bit approximations, and what additional structure is needed for tractability.

Machine learning relies on gradient-based training procedures whose empirical efficiency is usually analyzed through finite-dimensional arithmetic counts rather than formal complexity over continuous real-valued data. This paper studies neural-network training primitives as represented-real operators in the second-order complexity framework of Kawamura and Cook. Here, second-order polynomial time means computing a real-valued operator to accuracy $2^{-n}$ in time polynomial in the requested precision, architecture size, primitive evaluation costs, and supplied analytic certificates. We prove that dense backpropagation, convolutional backpropagation, soft attention, fixed finite SGD/Adam-style updates, and related smooth local primitives are second-order polynomial-time computable over the relevant represented real spaces. More precisely, dense one-sample backpropagation has tight arithmetic complexity $\Theta(s)$ for $s$ weights and polynomial bit complexity; convolutional backpropagation is polynomial in the number of active convolution incidences; dense soft-attention backpropagation has arithmetic cost $\Theta(\ell d^2+\ell^2d)$; and fixed finite smooth optimizer updates remain second-order polynomial-time computable under explicit smoothness and lower-bound certificates. Higher complexity enters through three distinct mechanisms: discontinuous selection, global optimization, and continuous-time flow solving. Hard routing, top-$k$ sparsification, argmax decisions, ReLU kink conventions, exact line search, and idealized gradient flow therefore change the second-order complexity status of the training operator. Overall, this work provides a rigorous mathematical language for precision, conditioning, and certificate dependence, which are often implicit in floating-point analyses, thus enabling a unifying complexity account for dense networks, CNNs, attention, Transformers, and standard optimizers.

Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for structured and symbolic generation. However, standard training targets a likelihood-based objective that primarily matches the data distribution and provides no native mechanism for enforcing hard constraints or optimizing non-differentiable properties at inference time. This work addresses this limitation and introduces Search-Augmented Masked Diffusion (SearchDiff), a training-free neurosymbolic inference framework that integrates informed search directly into the reverse denoising process. At each denoising step, the model predictions define a proposal set that is optimized under a user-specified property satisfaction, yielding a modified reverse transition that steers sampling toward probable and feasible solutions. Experiments in biological design and symbolic reasoning illustrate that SearchDiff substantially improves constraint satisfaction and property adherence, while consistently outperforming discrete diffusion and autoregressive baselines.

Generative models are increasingly central to many de novo discovery pipelines, in which designs are generated at scale and filtered through virtual screens to determine a set of candidates to experimentally validate. While Bayesian optimization (BO) is a natural fit for this setting, as it uses past evaluations to guide future proposals, the computational overhead required for its sequential decision-making becomes a bottleneck when virtual screens are relatively cheap. We make BO practical in this regime by exploiting the unique combination of a linear model constrained to a spherical domain where high-dimensional latents concentrate. We build off recent work justifying the use of linear surrogates, while deriving nearly closed-form solutions to the surrogate modelling and acquisition problems that exploit spherical symmetry. The result is a $100\times$ speedup over state-of-the-art baselines, with matching or improved performance across molecular and image generation benchmarks. Altogether, our method makes BO a practical drop-in for de novo pipelines where it was previously too slow to consider.

Spatiotemporal point processes (STPPs) model event data in continuous time and space, with applications in mobility, epidemiology, and public safety. Recent neural STPPs span expressive intensities, density models, continuous-time latent dynamics, normalizing-flow spatial decoders, and score-based generative mechanisms. Yet comparison remains fragile because implementations differ in preprocessing, coordinate normalization, splits, likelihood conventions, and evaluation protocols. We present \textsc{Seahorse}, a unified framework for reproducible STPP experimentation. \textsc{Seahorse} provides an encode--evolve--decode interface and an executable benchmarking contract that standardizes dataset handling, configuration resolution, training, tuning, checkpointing, raw-coordinate likelihood reporting, and run artifacts across heterogeneous STPP families. It supports classical baselines, neural likelihood models, continuous-time Neural STPP variants, and sample-based generative models under one external protocol. Using HawkesNest as a controlled synthetic stress-test suite, we show how diagnostic benchmarking can probe neural STPP behavior under increasing spatiotemporal entanglement and other structural changes. Together, \textsc{Seahorse} and these controlled evaluations provide reusable infrastructure for comparing, diagnosing, and extending STPP models beyond implementation-specific leaderboards.