NeurIPS 2026 Papers

Automatic evaluation is now central to text-to-image benchmarking, but the verifier that converts generated images into scores is often treated as an implementation detail. We argue that this is unsafe: an automatic benchmark score is a property of the image generator, prompt distribution, verifier, verifier-use protocol, and scoring rule, not of the generator alone. We study this issue in structural counting, a controlled setting where human-visible counts can be audited and where both instance-level object counts and parent-bound substructure counts arise naturally. We construct a verifier-centric audit suite over seven counting objects: cell phones, chairs, and traffic lights for object counting, and clover leaflets, dresser drawer fronts, power-strip sockets, and turbine blades for substructure counting. Across 6,240 generated images from Qwen-Image-2512 and FLUX.2-dev, we compare open MLLM verifiers under count-only, reject-aware, zero-shot and few-shot protocols, plus TIFA-like target-query variants and targeted frontier closed-model sanity checks on two hard objects. We also compare MLLMs with a detector baseline. On a balanced 2,280-image evaluation split, Qwen3.5-27B with few-shot reject/count achieves the best image-level agreement among open verifiers ($\kappa=0.754$) with a small aggregate score gap ($+1.54\text{pp}$), but changing the protocol, model size, or generator distribution can shift automatic scores by tens of points. Targeted GPT-5.5 and Claude Opus 4.7 checks do not remove the failure modes: GPT-5.5 still has only 59.92\% clover valid-count fidelity, while Claude Opus 4.7 has lower same-slice agreement ($\kappa=0.432$). We propose reporting a factorized verifier reliability profile---aggregate score gap, image-level agreement, valid-image count fidelity, rejection behavior, output compliance, and directional bias---rather than a single automatic benchmark score.

Large language models can now generate useful code from natural language, but their outputs still come without correctness guarantees. Verifiable code generation offers a path beyond testing by requiring models to produce not only executable code, but also formal specifications and machine-checkable proofs. Progress in this direction, however, is difficult to measure: existing benchmarks are often small, focus on only one part of the pipeline, lack ground-truth proofs or rigorous specification validation, or target verification settings far from mainstream software development. We present VeriContest, a benchmark of 946 competitive-programming problems from LeetCode and Codeforces for verifiable code generation in Rust with Verus. Each problem pairs a natural language description with expert-validated formal specifications, judge-accepted Rust code, Verus-checked proofs, and positive and negative test suites. VeriContest is constructed through a three-phase pipeline that scales from manually verified seed problems to semi-automated expansion with human-in-the-loop review. To further strengthen benchmark quality, we use testing as an additional quality-assurance layer for validating postcondition completeness. VeriContest supports both isolated and compositional evaluation of specification generation, code generation, proof generation, and end-to-end verified program synthesis. Evaluating ten state-of-the-art models reveals a sharp gap between ordinary coding ability and verifiable code generation: the strongest model reaches 92.18% on natural-language-to-code generation, but only 48.31% on specification generation, 13.95% on proof generation, and 5.29% end-to-end. These results identify proof and specification generation as the central bottlenecks for current models and establish VeriContest as a rigorous platform for measuring and training future systems that generate code with machine-checkable correctness.

The data fidelity term plays a crucial role in variational image segmentation. Recently, optimal transport (OT)-based variational models have improved segmentation by globally matching predicted feature distributions with reference distributions. However, existing OT-based methods usually rely on color or intensity similarity, which can be insufficient when foreground and background regions share similar appearance. We address this limitation by incorporating geodesic distance into the OT cost on a Riemannian feature manifold, allowing the transport cost to jointly encode spatial proximity, appearance similarity, and boundary information. The proposed model is well-defined: we prove existence of minimizers and convexity of the energy functional. It is also tractable: the OT terms admit differentiable transport-map representations, avoiding storage of the full pairwise transport matrix and enabling efficient gradient-based optimization. Experiments on BraTS and RESECT show that our method consistently outperforms traditional variational models, OT-based baselines, and prompt-based deep segmentation models, particularly when foreground and background have overlapping intensity or color patterns.

Unifying visual perception and generation poses a fundamental dichotomy: perception extracts semantics but discards details, while generation synthesizes fine-grained structures. Thus, existing works rely on decoupled architectures, as forcing these opposing information flows into one network inevitably triggers task interference and representation collapse. To break this bottleneck, we introduce the Visual Unified Model (VUM), a native framework that unifies both capabilities within a single architecture. Our key insight is that visual perception and generation can be unified by re-envisioning Masked Image Modeling and Diffusion Processes as complementary facets of data recovery. By establishing a shared degradation space that integrates both masking and noising, VUM optimizes a joint signal recovery objective: simultaneously predicting masked patches and denoising corrupted signals. This objective enforces the dual internalization of semantic abstraction and generative synthesis. Using a shared, unified backbone, VUM delivers highly competitive performance across a diverse spectrum of tasks, encompassing image generation, visual recognition and dense prediction tasks. Codes and pretrained checkpoints will be made publicly available.

Visual autoregressive generation spans two dominant paradigms: next-scale prediction for images and video, and next-frame prediction for video. Both decode block-by-block rather than token-by-token, yielding KV caches whose statistics diverge from those of language models. At scale, KV memory exceeds the weights and limits large-scale deployment caused by a large amount of visual tokens. Our analysis of these caches reveals three findings. First, a small set of massive-value channels carries the functional load: ablating these outlier channels collapses generation, whereas ablating a matched set of inlier channels leaves quality intact. Second, the outliers organize along two axes, feature and block, with magnitudes persistent within each cell and shifting across cells. Third, this structure arises from two independent mechanisms: projection bias and RoPE-induced scattering. Guided by these findings, we propose VAR-Q, a tuning-free KV-cache quantization framework that groups along the same two axes. The generation loop provides block boundaries for free, removing the need for outlier detection or calibration. Paired with bit-packing kernels for runtime memory reduction, VAR-Q delivers low-bit quantization across nine models spanning both paradigms, cutting KV memory by up to 78.5% with negligible quality degradation and enabling 6× larger inference batches.

Recent work on the sequence universality of State Space Models (SSMs) has introduced efficient, maximally expressive continuous-time approaches for time-series modelling. While these works focus on discriminative settings, we extend this perspective to generative time-series modelling by proving that maximally expressive Structured Linear Controlled Differential Equations (SLiCEs) are universal time-series generators, in the sense that they can approximate the induced path laws of continuous causal pushforwards on compact latent sets in $W_\infty$. Building on these theoretical results, we propose Generative SLiCEs (G-SLiCEs), a maximally expressive continuous-time model for flow matching on path-space. Empirically, we show that expressivity improves performance in probabilistic forecasting and downstream tasks, while retaining the advantages of continuous-time models such as generalising to arbitrary observation grids. This is particularly beneficial for irregular grids, where fixed-grid models often struggle.

Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, they still rely primarily on frozen parametric knowledge, which makes them struggle with real-world image generation involving long-tail and knowledge-intensive concepts. Inspired by the broad success of agents on real-world tasks, we explore agentic modeling to address this limitation. Specifically, we present Unify-Agent, a unified multimodal agent for world-grounded image synthesis, which reframes image generation as an agentic pipeline consisting of prompt understanding, multimodal evidence searching, grounded recaptioning, and final synthesis. To train our model, we construct a tailored multimodal data pipeline and curate 143K high-quality agent trajectories for world-grounded image synthesis, enabling effective supervision over the full agentic generation process. We further introduce FactIP, a benchmark covering 12 categories of culturally significant and long-tail factual concepts that explicitly requires external knowledge grounding. Extensive experiments show that our proposed Unify-Agent substantially improves over its base unified model across diverse benchmarks and real world generation tasks, while approaching the world knowledge capabilities of the strongest closed-source models. As an early exploration of agent-based modeling for world-grounded image synthesis, our work highlights the value of tightly coupling reasoning, searching, and generation for reliable open-world agentic image synthesis.

Despite rapid progress in synthetic image detection, detectors that perform well on known generators often become brittle when the source model, post-processing pipeline, or scene composition changes. A key reason is that standard binary supervision teaches models to separate training distributions rather than to identify authenticity-relevant evidence: low-level artifacts become shortcuts, while higher-level semantic implausibilities remain weakly grounded. To address this limitation, we propose **UniFPL**, a unified forensics preference learning framework that converts multimodal large language model (MLLM) forensic knowledge into image-specific preference supervision. UniFPL constructs forensic preference data from both controlled artifact synthesis and observed artifact harvesting, then learns from list-level evidence rankings that encode which visual-textual cues are more diagnostic of synthetic manipulation. On top of a CLIP-based discriminative detector, UniFPL jointly optimizes authenticity classification, artifacts-aware preference alignment, and semantic structure regularization, allowing the model to inherit contextual forensic reasoning while retaining the stable and efficient inference of a discriminative encoder. Across eleven curated and in-the-wild benchmarks, UniFPL achieves an average balanced accuracy of 93.4\% and improves the worst-case accuracy from 81.4\% to 86.1\% over the strongest baseline, demonstrating stronger cross-generator generalization and robustness to real-world image degradations.

In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across diverse camera systems, such as large-field-of-view fisheye lenses. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically, 2D semantic embeddings and 3D spatial features are jointly encoded and decoded by UniK3D to support Gaussian construction, while a ray-based universal representation organizes Gaussian primitives along rays and radial distances. To comprehensively evaluate our method, we construct a benchmark covering diverse imaging systems, including pinhole, fisheye and panoramic cameras, across various scenes. The benchmark is further stratified by field of view, spanning narrow perspective, wide-FoV, fisheye, and full panoramic settings. Extensive experiments on the proposed benchmark demonstrate the effectiveness of UniSHARP, outperforming alternative methods by a large margin. Our models, training code, and dataset will be publicly available.

Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple reference images. Existing VLM-enhanced diffusion models commonly rely on decoupled visual conditioning: semantic ViT features are processed by the VLM for instruction understanding, whereas appearance-rich VAE features are injected later into the diffusion backbone. Despite its intuitive design, this separation makes it difficult for the model to associate each semantically grounded subject with visual details from the correct reference image. As a result, the model may recognize which subject is being referred to, but fail to preserve its identity and fine-grained appearance, leading to attribute leakage and cross-reference confusion in complex multi-reference settings. To address this issue, we propose UniCustom, a unified visual conditioning framework that fuses ViT and VAE features before VLM encoding. This early fusion exposes the VLM to both semantic cues and appearance-rich details, enabling its hidden states to jointly encode the referred subject and corresponding visual appearance with only a lightweight linear fusion layer. To learn such unified representations, we adopt a two-stage training strategy: reconstruction-oriented pretraining that preserves reference-specific appearance details in the fused hidden states, followed by supervised finetuning on single- and multi-reference generation tasks. We further introduce a slot-wise binding regularization that encourages each image slot to preserve low-level details of its corresponding reference, thereby reducing cross-reference entanglement. Experiments on two multi-reference generation benchmarks demonstrate that UniCustom consistently improves subject consistency, instruction following, and compositional fidelity over strong baselines. Our code, checkpoints, and the training dataset will be released soon.

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.

Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the representation encoder. Experiments show that Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception. These results show that pretrained vision encoders are not necessary for multimodal modelling, and end-to-end pixel-space learning offers a scalable path toward stronger visual representations for both generation and perception.

Pose-guided text-to-image generation often suffers from limb distortions and feature crosstalk in complex multi-person scenarios. While existing UNet-based adapters struggle with long-range spatial dependencies, emerging Multimodal Diffusion Transformers (MM-DiTs) offer superior global modeling. However, naive signal concatenation in MM-DiTs severely disrupts pre-trained latent distributions. To address this, we propose TrioPose, a native pose-driven framework built upon the SD3.5M architecture. Specifically, we introduce a Triple-Stream Pose-Aware DiT (TSPA-DiT) that treats pose as an independent modality. It employs layer-wise activation and zero-initialized dual-residual injection to smoothly enforce geometric constraints while preserving pre-trained latent stability. To resolve severe multi-instance occlusions, we design a Learnable Relational Bias Mask that categorizes topological connectivity into fine-grained physical states, mapping them into continuous attention soft constraints to effectively decouple inter-instance interference. Furthermore, a Pose-Guided Spatial Loss Weighting strategy modulates the native diffusion objective using heatmap-derived error maps, focusing anatomical supervision strictly on distortion-prone regions. Extensive experiments demonstrate that TrioPose achieves state-of-the-art performance across challenging benchmarks, including Human-Art, CrowdPose, and OCHuman. Notably, it attains an AP of $64.33$ on Human-Art, representing a $30 \\%$ improvement over prior arts, while setting new standards for visual fidelity and text-image semantic alignment in complex multi-human generation.

Autoregressive (AR) video diffusion has emerged as a leading paradigm for efficient video generation, yet its practical deployment remains bottlenecked by the trade-off between generation quality and inference efficiency. We attribute this bottleneck to three error sources in AR rollouts: the base model error, the train–inference distribution mismatch, and the upstream error propagation. Building on this decomposition, we derive closed-form upper bounds on the per-step and cumulative errors, providing a principled mechanism for jointly optimizing generation quality and inference efficiency. Guided by this analysis, we propose **TriTD**, a **Tri**-Partite **T**rajectory–**D**istribution co-optimized distillation framework with three complementary modules that each target a distinct error term in the bound. First, for ODE initialization, we adopt a Next-Node Trajectory Distillation (NTD) objective and prove a strictly tighter error bound than conventional consistency distillation, reducing the base model error at its source. Second, we introduce Chunk-Graded Noising (CGN), a monotonically non-decreasing per-chunk noising schedule that provably narrows the train–inference noise mismatch and removes redundant KV Cache updates, yielding substantial speedups at no quality cost. Third, we propose Orthogonal-Parallel DMD (OP-DMD), a distribution-matching loss that preserves the original DMD gradient direction while explicitly suppressing unsupervised off-axis drift in the orthogonal subspace, improving both training stability and final generation quality. Extensive experiments show that TriTD consistently surpasses state-of-the-art baselines in visual quality while reaching a real-time throughput of **26.8 FPS** on a single H100 GPU, delivering a balanced quality-efficiency solution for interactive streaming video generation.

Recent video diffusion models achieve strong visual quality and temporal coherence, but still lack coordinated control over scene layout, customized subject identity, and camera/subject motion. We study controllable video generation from three prompts: a first-frame scene image, 3D-aware multi-view subject references, and a motion-driving signal. This setting is challenging because background regions are often trackable under camera motion, while foreground subjects can rotate, self-occlude, and reveal new regions that require identity-consistent appearance. We introduce Tri-Prompting, a video diffusion framework that combines multi-view subject conditioning with dual-conditioned motion control. Tri-Prompting uses XYZ tracking points for visible background motion and low-resolution RGB proxies for foreground subject pose, allowing the model to recover fine appearance from multi-view references while retaining flexibility for plausible subject-scene interactions. An inference-time ControlNet scale schedule further balances motion controllability and visual realism. We evaluate Tri-Prompting against specialized baselines: DaS for motion reconstruction and Phantom for subject-driven generation. Tri-Prompting achieves competitive or improved reconstruction quality, stronger multi-view identity preservation, and better 3D consistency, while enabling 3D-aware subject insertion and in-scene manipulation.

Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Trellis4D, a dynamic mesh generation framework by inheriting the expressive representation of Trellis2, adapting it from image-to-3D to video-conditioned 4D generation. Our design arises from two key questions: (a) how to enable Trellis2's frame-local attention to share information across frames while preserving its pretrained quality on rare cases such as transparent objects and inner surfaces, and (b) how to inject temporal information into a purely 3D positional encoding without breaking pretrained capabilities. We address (a) with a sliding-window cross-frame attention and anchor on the first frame. The first frame is generated by the base Trellis2 model and injected into our model, letting it inherit Trellis2's quality in rare cases through cross-frame attention. We address (b) with a 4D temporal encoding that repurposes redundant low-frequency spatial RoPE bands for time, extending the encoding from 3D with no additional parameters. Extensive experiments show the effectiveness of Trellis4D for high-quality dynamic mesh generation on ActionBench and our own challenging complex dynamics set.

Data augmentation improves visual recognition by exposing models to synthetic training examples that encourage generalization beyond the observed data. Mixed-sample methods extend this idea by combining multiple images. However, existing approaches either mix only pairs of images or rely on fixed small layouts, limiting control over source count, visible area proportions, and induced supervision. We propose TreemapMix, a distribution-controlled multi-image augmentation that samples source weights from a Dirichlet distribution and assigns them to area-proportional regions using a treemap partition. The resulting known region areas support two complementary objectives. TreemapMix with soft cross-entropy (SCE) treats areas as soft class-probability targets, while TreemapMix with a Plackett-Luce (PL) objective converts areas into ordinal supervision. On ImageNet-1K under a matched training protocol, TreemapMix-SCE achieves substantially lower calibration error than evaluated mixed-sample baselines, while TreemapMix-PL achieves the strongest Top-1 accuracy. Transfer experiments on object detection and instance segmentation suggest that TreemapMix-pretrained features remain useful beyond classification. These results show that controlled multi-image composition can expose the same region-area information as either probability-matching or rank-matching supervision.

Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines, released as a continual pre-training corpus and benchmark data for three evaluation tasks with complementary metrics. Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations without any explicit mapping. These results demonstrate that transit route planning can be learned entirely from data, enabling end-to-end, map-free route generation directly from origin-destination information. The dataset and benchmark are available at https://huggingface.co/datasets/GD-ML/TransitLM, with evaluation code at https://github.com/HotTricker/TransitLM.