NeurIPS 2026 Papers

Large Language Diffusion Models (LLDMs) are emerging as an alternative to autoregressive models, offering faster inference through higher parallelism. Similar to autoregressive LLMs, they remain prone to hallucinations, making reliable uncertainty quantification (UQ) crucial for safe deployment. However, existing UQ methods are fundamentally misaligned with this new paradigm: they assume autoregressive factorization or use expensive multiple sampling, negating the efficiency of LLDMs. In this work, we present the first systematic study of UQ for LLDMs and propose lightweight, zero-shot uncertainty signals derived from the iterative denoising process, leveraging intermediate generations, token remasking dynamics, and denoising complexity. We further adapt a state-of-the-art UQ method to LLDMs by combining masked diffusion likelihoods with trajectory-based semantic dissimilarity. We provide theoretical grounding, proving that expected trajectory dissimilarity bounds the masked diffusion training objective. Comprehensive experiments across three tasks, eight datasets, and two models show that our method achieves a great cost-performance trade-off: it approaches the strongest sampling-based baselines while incurring up to one hundred times lower computational overhead. Our work demonstrates that LLDMs can deliver both fast inference and reliable hallucination detection simultaneously.

Accurate image registration is essential in many medical imaging applications, yet most deep registration networks provide little indication of when or where their predictions are unreliable. Existing uncertainty estimation approaches, such as Bayesian methods, ensembles, or MC-dropout, typically require architectural modifications or retraining, precluding their applicability to pretrained registration models. We propose an inference-time, model-agnostic uncertainty estimation framework that applies directly to any pretrained registration network. Our approach is grounded in the transformation equivariance property of image registration, which states that the underlying anatomical mapping should remain consistent under spatial perturbations of the input. Experiments across three pretrained registration models and four anatomical structures show that the resulting uncertainty maps consistently correlate with registration error and highlight unreliably aligned regions. This framework turns pretrained registration networks into risk-aware tools at test time, moving medical image registration closer to safe clinical and large-scale research deployment. The code will be released at ***.

This work presents UGD-FM, a novel unaligned image guided denoising framework based on cross-modal conditional flow matching. Unlike previous approaches that assume spatially aligned inputs or only handle small-baseline rectified pairs, we address a more challenging setting where severe target noise and large-range two-dimensional cross-modal misalignment coexist. Specifically, we formulate guided denoising as a progressive flow matching process, allowing image restoration and aligned guidance aggregation to mutually reinforce each other. To support efficient few-step inference, we introduce a stage-focused and inference-consistent training strategy that focuses on task-critical denoising stages, and mitigates the training-inference mismatch. We further propose adaptive sparse guidance propagation for efficient and reliable large-range matching, regularized by content and geometry level auxiliary losses. Experiments demonstrate that UGD-FM achieves state-of-the-art denoising performance with only one or two inference steps, and is compatible with modern single-image restoration backbones.

Multinomial logistic regression (MLR) is the default last-layer classifier in fully supervised recognition, while prototype classifiers are central to few-shot recognition. Although they are usually presented as different principles, we show that both can be organized by a geometric notion of class boundaries. A Euclidean MLR logit is a signed distance to a class hyperplane, so ordinary MLR is already the hyperplane decision-boundary case of Umbilic Multinomial Logistic Regression (UMLR). Classical submanifold geometry supplies the matching spherical decision boundary: in Euclidean space, the complete connected totally umbilic hypersurfaces are hyperplanes and spheres. The spherical UMLR form keeps a prototype-like center but adds a learnable radius; its signed squared-distance form contains squared prototype scoring as the radius-zero case. Thus UMLR is not a separate replacement for MLR or prototypes, but a boundary-aware family that places hyperplane logits, spherical logits, mixed heads, and prototype scoring in one framework. Experiments on low-shot vision head swaps, prototype comparisons, and mixed hyperplane--sphere heads support this organization and show how the different decision boundaries behave across data regimes. UMLR provides a compact geometric language for studying when class evidence is better modeled by flat boundaries, spherical boundaries, or their mixture.

We present UltraVoxelGS, a 3D ultrasound reconstruction method that achieves both fast reconstruction and physically faithful rendering, bringing live spatial feedback during 2D ultrasound scanning within reach. This is made possible by a feed-forward design that predicts a complete Gaussian scene representation from posed ultrasound images directly, entirely bypassing the per-scene optimization bottleneck that has confined prior methods to offline use. Realizing such feed-forward prediction in this setting is non-trivial: unlike natural images, ultrasound slices share at most one-dimensional intersections and exhibit view-dependent appearance due to acoustic propagation and attenuation, violating the dense overlap and photometric consistency assumed by existing feed-forward Gaussian methods. To achieve fast reconstruction, we introduce a feed-forward voxel-to-Gaussian pass that decouples representation size from input count by lifting posed slices into a fixed-size voxel support and predicting Gaussian parameters directly. For faithful rendering, we propose an ultrasound-aware appearance rendering strategy that factorizes reflection from cumulative attenuation during training and exploits appearance continuity among spatially adjacent slices for efficient Render-time Appearance Adaptation. On both real-world and simulated datasets, UltraVoxelGS achieves the best PSNR/SSIM compared with per-scene optimization baselines, while reducing inference from 10--20 minutes to approximately 10 seconds, over 60× faster, and scaling to sequences exceeding 1,000 frames.

Direct Preference Optimization (DPO) offers a streamlined one-stage alternative to Reinforcement Learning from Human Feedback (RLHF). However, our theoretical analysis reveals a structural distinction between the two: DPO and RLHF optimize alignment on different data distributions with different supervision sources. Specifically, DPO learns from ground-truth human preferences but within the off-policy support of an offline dataset, while RLHF optimizes on the on-policy rollouts but learns from pseudo-labels produced by a reward proxy. This distinction explains how each method may fail: DPO alignment collapses when the policy drifts away from the offline dataset support, and RLHF alignment is biased due to the extrapolation error of the reward proxy on out-of-distribution rollouts. Effective alignment requires avoiding both failure modes, which neither method can do alone. We achieve this via a semi-supervised alignment objective: ground-truth preferences anchor alignment within the dataset support, and pseudo-labels on online rollouts extend it beyond. Applying DPO's reward reparameterization to this objective yields Ultra-DPO, a one-stage algorithm that augments direct human alignment with an online self-alignment mechanism. Across multiple benchmarks, Ultra-DPO consistently outperforms DPO, RLHF, and online preference learning methods.

While recent autoregressive video diffusion models achieve remarkable streaming quality, they remain confined to low resolutions (e.g., $480$P), leaving efficient, scalable, real-time high-resolution video generation a fundamental open challenge. To bridge this gap, we present Ultra Flash, a cascaded streaming framework capable of real-time high-resolution video generation. Ultra Flash achieves ${\sim}30$ FPS at 1K resolution and ${\sim}18$ FPS at 2K resolution on a single B200 GPU through three key contributions: (1) an architecture-preserving T2V-to-TV2V super-resolution training paradigm coupled with an AIGC-oriented data degradation pipeline that effectively preserves the generative capability of the base model, enabling enhanced high-resolution detail when cascaded after mainstream low-resolution generative models; (2) a causal streaming latent upsampler paired with a high-resolution decoder, which enhances spatiotemporal coherence while enabling efficient latent spatial scaling and precise high-resolution decoding with negligible computational overhead; and (3) a cascade high-resolution streaming video generation optimization scheme that first performs hybrid-reward-enhanced sparse causalization and single-step distillation of the super-resolution model, then introduces cascaded streaming self-forcing preference optimization with dynamic cache management, jointly enhancing overall coherence, improving quality, and enabling real-time high-resolution streaming video generation. Extensive experiments demonstrate that Ultra Flash reliably produces ultra-high-resolution streaming video while maintaining state-of-the-art visual quality and superior efficiency.

Diffusion-based models have demonstrated impressive accuracy and generalization in solving partial differential equations (PDEs). However, they still face significant limitations, such as high sampling costs and insufficient physical consistency, stemming from their many-step iterative sampling mechanism and lack of explicit physics constraints. To address these issues, we propose \emph{Phys-Instruct}, a novel physics-guided distillation framework which (1) not only compresses a pre-trained diffusion PDE solver into a few-step generator via matching generator and prior diffusion distributions to enable rapid sampling, (2) but also enhances the physics consistency by explicitly injecting PDE knowledge through a PDE distillation guidance. Phys-Instruct is built upon a solid theoretical foundation, leading to a practical physics-constrained training objective that admits tractable gradients. Across five PDE benchmarks, Phys-Instruct achieves orders-of-magnitude faster inference while reducing PDE Error by more than 8$\times$ compared to state-of-the-art diffusion baselines. Moreover, the resulting unconditional student model functions as a compact prior, enabling efficient and physically consistent inference for various downstream conditional tasks. Our results indicate that Phys-Instruct is a novel, effective, and efficient framework for ultra-fast PDE solving powered by deep generative models.

As long-video understanding becomes increasingly important, augmented reality (AR) devices offer a natural platform for deploying egocentric video intelligence. Yet first-person videos often contain substantial temporal redundancy, creating heavy memory and compute demands for resource-limited AR hardware. We present~\textit{UTOPI}, a plug-and-play pre-compression module tailored to egocentric long-video processing on AR devices. UTOPI first uses user motion cues to estimate cross-frame overlap and remove redundant content through a viewpoint-shift-robust pruning strategy. It then leverages eye-tracking signals to detect user fixation regions, separating attention-relevant foreground from background and preserving important content through a fine-tuned neural adjustment module. Evaluated across multiple benchmarks and model backbones, UTOPI reduces video tokens by up to $95%$ while maintaining task performance.

World Action Models have recently emerged as a promising paradigm for improving action generalization in autonomous driving by leveraging future video prediction as dense supervision for scene dynamics and temporal causality. However, it remains unclear how video modeling should be integrated with action generation to maximally transfer these benefits. Existing cascaded or dual-Diffusion Transformer architectures decouple video imagination from trajectory prediction, limiting knowledge transfer: the action model may still overfit dataset-specific driving priors, while the video model only indirectly regularizes planning. In this paper, we propose UNIVERSE, a unified video-action model built upon a single mask-modulated Diffusion Transformer. By co-training future video latents and ego-trajectory tokens within shared generative parameters, UNIVERSE allows dense video supervision to directly shape trajectory denoising, leading to stronger cross-domain action generalization. To ensure causal validity and efficient deployment, we introduce a Modality-Decoupling Visibility Mask, which shares historical context across modalities while blocking mutual attention between future video and trajectory tokens. This prevents future-modality dependency and enables trajectory-only inference by removing future-video denoising at test time, achieving a $4.3\times$ speedup over joint video--trajectory rollout while maintaining comparable planning accuracy. The same model also supports video-only and joint video--trajectory rollouts. Experiments show that UNIVERSE achieves 91.0 PDMS on NAVSIM and strong zero-shot transfer to nuScenes and Bench2Drive without fine-tuning, while ablations confirm the importance of single-DiT unification, video co-training, and mask-based modality decoupling.

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual understanding tasks. Conversely, directly modeling continuous semantic representations (e.g., CLIP, SigLIP) poses significant challenges in high-dimensional generative modeling, resulting in slow convergence and training instability. To resolve this dilemma, we introduce UniCom, a unified framework that harmonizes multimodal understanding and generation via compressed continuous semantic representations. We empirically demonstrate that channel-wise compression is significantly more effective than spatial token reduction, retaining competitive VAE-free reconstruction fidelity while substantially improving generative convergence. Accordingly, we design an attention-based semantic compressor to distill dense features into a compact unified representation. A Transfusion-style predictor then generates these compressed latents with dense spatial correspondence. At scale, UniCom achieves competitive text-to-image generation and state-of-the-art performance on complex image editing without relying on VAE latents. The gains are especially clear on knowledge-intensive benchmarks.

Multi-Agent Systems (MAS) are a promising paradigm for improving the reasoning capabilities of large language models, yet they remain prone to hallucinations and erroneous outputs. Uncertainty Quantification (UQ) is crucial for assessing system reliability, but existing methods are largely designed for single-agent settings; how to exploit MAS structure for UQ while keeping inference cost-neutral remains underexplored. We propose UMAS, a parameter-free, cost-neutral, system-level UQ framework that estimates the credibility of inter-agent influence from each generation’s intrinsic confidence. UMAS uses these credibility signals to modulate how uncertainty is updated at each node, and then aggregates node-level uncertainty into a system-level estimate. Extensive evaluations on Debate and DyLAN across diverse benchmarks show that UMAS consistently outperforms state-of-the-art baselines by an average of 10.49 AUROC points. Beyond uncertainty estimation, UMAS enables hallucination detection and uncertainty-aware answer selection, improving MAS accuracy by up to 12.6 points on specific tasks while enhancing reliability.

Genomic events span multiple spatial scales, from single-nucleotide substitutions to large structural variants, yet existing foundation models process only reference DNA sequences, leaving methylation, short variants, and structural-variant boundaries as downstream labels or auxiliary inputs. We propose the Unified Genomic Model (UGM), an encoder-only genomic foundation model that learns multi-scale genomic events as native tokens within a unified 43-token vocabulary. UGM introduces three algorithmic components: (i) a unified event tokenizer that maps reference bases, SNPs, CpG methylation, short INDELs, and structural-variant boundaries into a single event-state space; (ii) event-balanced pretraining, which promotes adequate gradient coverage for rare but biologically important events; and (iii) Site-Level Joint Prediction (SJP), a masked-language-modeling objective that recovers the complete genomic state at a masked position as a single token rather than predicting base, methylation, and variant labels independently. We evaluate UGM against specialized and generalist baselines across functional variant classification, regulatory benchmarks (NT and GUE), structural-variant detection, and cross-event attention analysis. UGM achieves competitive performance, particularly on tasks where explicit event-state information is central. It obtains the highest score on all seven functional variant tasks, reaches competitive splicing prediction on NT, and notably outperforms DNA-only baselines on SV breakpoint detection. These results suggest that native multi-scale event pretraining is a promising direction for genomic representation learning.

Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve over time. However, existing CGL methods largely assume clean supervision and overlook a critical challenge: the newly arriving portions of the graph are often noisy, due to annotation errors or adversarial corruption. This mismatch limits their applicability in practice. In this work, we study robust continual graph learning, where models must simultaneously handle catastrophic forgetting and noisy supervision in evolving graph data. We show that label noise introduces a new failure mode—catastrophic remembering, where models persistently reinforce corrupted knowledge across tasks. To address these challenges, we propose a Unified Flow-Oriented framework (UFO). First, UFO models conditional feature distributions via flow-based generative modeling and produces replay representations, mitigating forgetting without storing historical data. Second, UFO estimates instance-level reliability scores to distinguish clean from noisy nodes, reducing the impact of corrupted supervision and alleviating catastrophic remembering. Extensive experiments on four benchmark graph datasets under varying noise ratios demonstrate that UFO consistently outperforms existing methods in both accuracy and forgetting metrics. Code is available at: https://anonymous.4open.science/r/UFO.

Multi-view transformers for feed-forward 3D reconstruction must jointly solve two tasks. They need to extract precise per-view features and reason about cross-view geometric correspondences. Existing architectures apply cross-view attention throughout the network, leaving each layer to handle both objectives together. We revisit this design through a layer-wise probing analysis of feed-forward geometry transformers and observe that trained models tend to divide these two roles across layers. Early layers tend to specialize in per-frame feature extraction, while spatial cognition and cross-view reasoning emerge predominantly in later layers. This suggests that separating the two roles across the network can allocate compute more effectively. Building on this observation, we propose U-MVP, a U-shaped multi-view transformer for feed-forward 3D Gaussian Splatting that reflects this structure in the architecture itself. The encoder applies frame-wise attention to preserve per-view detail, the decoder introduces multi-view attention for cross-view geometric reasoning, and skip connections fuse the two streams so that appearance and geometry are recombined at decoding time. To scale to dense view regimes, we replace several global interaction blocks at the bottleneck with a grouping and swapping scheme that preserves cross-view information flow at lower cost. U-MVP performs competitively with feed-forward and optimization-based baselines from 16 to 256 views, generalizes to unseen datasets, and achieves strong results on 3D reconstruction and novel-view synthesis in posed and unposed settings.

Recent long-tailed recognition methods increasingly adopt two-stage fine-tuning, where a generic representation is first learned and imbalance-aware adaptation is then performed in a lightweight second stage. However, existing second-stage designs often allocate objective emphasis using delayed empirical summaries, such as historical class-wise performance or validation feedback, and commonly restrict adaptation to classifier heads. These choices may make routing unreliable when empirical feedback is noisy or skewed, and may also limit the feature plasticity required for rare categories. In this paper, we propose U-MOF, an uncertainty-guided parameter-efficient multi-objective fine-tuning framework for long-tailed recognition. U-MOF introduces lightweight residual adapters into a shared-backbone expert committee, uses entropy-based committee statistics as diagnostic routing proxies to modulate tail-oriented and smoothing-oriented objectives, and applies conflict-aware orthogonal projection to coordinate heterogeneous objective gradients. Experiments on CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018 show that U-MOF improves rare-category and overall performance in controlled stage-two comparisons and remains competitive with strong published long-tailed recognition baselines, while preserving the efficiency advantages of decoupled adaptation. These results indicate that reliable stage-two long-tailed fine-tuning benefits not only from selecting appropriate objectives, but also from diagnosing when each objective should dominate and from retaining limited feature-level plasticity. An anonymized implementation is included in the Supplementary Material.

Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread adoption, there is still no comprehensive benchmark to systematically evaluate their performance and utility, largely because of insufficient statistical validation and limited consideration of efficiency and generalization across diverse datasets. To bridge this gap, we present U-Bench, the first large-scale, statistically rigorous 2D benchmark that evaluates 100 U-Net variants across 28 datasets and 10 imaging modalities. Our contributions are threefold: (1) Comprehensive Evaluation: U-Bench evaluates models along three key dimensions: statistical robustness, zero-shot generalization, and computational efficiency. We introduce a novel metric, U-Score, which jointly captures the performance-efficiency trade-off, offering a deployment-oriented perspective on model progress. (2) Systematic Analysis and Model Selection Guidance: We summarize key findings from the large-scale evaluation and systematically analyze the impact of dataset characteristics and architectural paradigms on model performance. Based on these insights, we propose a model advisor agent to guide researchers in selecting the most suitable models for specific datasets and tasks. (3) Public Availability: We provide all code, models, protocols, and weights, enabling the community to reproduce our results and extend the benchmark with future methods. In summary, U-Bench not only exposes gaps in previous evaluations but also establishes a foundation for fair, reproducible, and practically relevant benchmarking in the next decade of U-Net-based segmentation models. The weights, datasets, and results will be released after the acceptance.

Probabilistic weather forecasting requires not only accurate trajectories, but calibrated distributions over plausible atmospheric futures. Recent data-driven systems have achieved remarkable deterministic skill, and diffusion-based ensemble forecasters have substantially improved sample realism and uncertainty quantification. However, their inference cost scales with forecast horizon, ensemble size, and the number of denoising steps required for each transition, making large operational ensembles expensive. To address this, we present Tyche, a one-step conditional flow model for efficient probabilistic weather forecasting. Tyche models the conditional forecast distribution with a destination-aware average-velocity flow that maps Gaussian noise directly to future weather states in a single function evaluation (1-NFE). To make this one-step transport learnable in high-dimensional geophysical fields, we derive a JVP-regularized rectification objective that enforces temporal self-consistency across source and destination flow timesteps without explicitly forming Jacobians. The transport field is parameterized by an isotropic Swin-style transformer that preserves fine-scale spatial structure while remaining scalable on global grids. To improve ensemble reliability under autoregressive forecasting, we further introduce a rollout-based finetuning stage with curriculum CRPS calibration supervision. Experiments on ERA5 at 1.5$^\circ$ and 6-hour resolution show that our Tyche, using merely a single NFE, matches or exceeds the forecast skill and calibration of state-of-the-art multi-step generative baselines and the operational ECMWF IFS ensemble. Codes are available.

Two-sided matching platforms rely on preferences from both sides, yet participants can evaluate only a small fraction of potential partners. In practice, they use low-cost pre-match screening, e.g., interviews, profile views, or trial tasks, to form noisy impressions before committing to applications and offers. We study bandit learning in matching markets with interviews, modeling these interactions as queried *hints* [Bhaskara et al., 2022] that reveal partial preference information to both sides while constraining subsequent applications. Our framework also allows firm-side uncertainty: firms, like agents, learn their preferences and may make early hiring mistakes. To address this, we introduce strategic deferral, a firm-side action that permits temporary vacancy, corrects premature commitments, and enables decentralized learning under coarse anonymous feedback. We design algorithms for centralized and decentralized markets and show that a constant number of interviews per round suffices for horizon-independent regret, improving over the $O(\log T)$ guarantees known without interviews. Our bounds are near-optimal: the centralized guarantee is within a factor $m$ of an information-theoretic lower bound, while decentralized algorithms match it up to polynomial factors in structured markets and remain horizon-independent in general markets.