NeurIPS 2026 论文列表

Training-free safeguards for text-to-image diffusion models often rely on a reusable safety signal, such as an unsafe direction or global toxic subspace, applied broadly across prompts. We provide a controlled geometric analysis of this global-unsafety assumption and reveal a consistent coverage-selectivity trade-off: compact unsafe subspaces fail to cover heterogeneous unsafe semantics, whereas broader aggregation increasingly distorts safety-adjacent benign prompts. Motivated by this finding, we propose CALM (Counterfactual Adaptive Local Modulation), a training-free safeguard that replaces uniform global removal with prompt-local counterfactual correction. Using matched unsafe-benign anchors, CALM routes each prompt to active unsafe categories, minimally edits only violating token representations toward the safe side, and suppresses positively aligned unsafe residual components. Across broad evaluation, CALM improves unsafe-content suppression while preserving benign utility, demonstrating that local counterfactual correction provides a more selective alternative to global unsafe-signal removal.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable effectiveness in general video understanding. Human motion understanding, a dominant topic in video analytics, however, still remains as a bottleneck due to the lack of explicit structural cues in 2D visual patches and the significant motion information loss caused by sparse visual temporal sampling. To address this, we propose Iris (Integrating representations of in-the-wild skeletons), a novel pose-augmented video MLLM tailored for human-centric motion understanding. Iris adopts an asymmetric dual-stream architecture, pairing the traditional sparse vision stream with a lightweight, high-frequency human pose stream to provide spatially structured and temporally dense kinematic signals. To enable pose-vision modality correspondence awareness, we design a cross-modal spatiotemporal binding mechanism, featuring a pose-structured 3D RoPE for precise temporal alignment and a person-grounded cross-attention module for explicit spatial visual grounding. Furthermore, to enable robust large-scale training, we construct an automated pose curation pipeline that organizes pose data into a delicate heterogeneous representation. Extensive experiments demonstrate that Iris achieves superior performance on multiple fine-grained motion benchmarks, while also maintaining highly efficient token computation overhead. Code will be available upon publication.

Text-to-CAD generation aims to make CAD modeling more accessible by generating executable CAD programs from natural-language descriptions. However, practical CAD workflows require more than executable geometry: generated programs should also expose reusable structure that supports later modification. We introduce intent-oriented text-to-CAD generation, where design intent is expressed as recoverable code-level signals: semantic features, reusable parameters, and lightweight parametric relations. Rather than changing the model architecture or decoding procedure, we investigate how supervision representation granularity affects both CAD generation and zero-shot intent-preserving editing. To enable this study, we construct IntentCAD-100K, a 100K paired text--code dataset built by converting low-level CAD construction traces into executable CadQuery programs. We further construct IntentCAD-Edit-1K to evaluate zero-shot intent-preserving editing from the same representation perspective. Intent2CAD uses a two-stage conservative lifting pipeline: semantic lifting rewrites reliable primitive groups into feature-level operations, while parametric lifting exposes lightweight parametric relations. Under controlled fine-tuning, semantic lifting mainly improves generation reliability and feature recovery, reducing IR from 2.39% to 0.22% and achieving 99.96% API Recovery, while parametric lifting makes reusable relation structure explicit and further improves relation-aware zero-shot editing.

Video virtual try-on is a highly constrained editing task requiring the precise replacement of a target person's clothing while strictly preserving the original video's spatial structure and temporal dynamics. Existing methods heavily rely on auxiliary handcrafted spatial priors (e.g., masks, poses) for editing control. However, these priors are prone to failure in unconstrained real-world videos and often compress rich visual context into incomplete structural signals. Furthermore, standard reconstruction objectives fail to fully capture try-on-specific human preferences. To address these challenges, we propose InstructVVT, an instruction-driven and reference-guided video virtual try-on framework based on a Diffusion Transformer (DiT) that operates without inference-time spatial priors. Our core insight is to recover fine-grained control directly from the input triplet (source video, reference garment, and instruction) via a dual-level reference conditioning scheme. Specifically, an MLLM infers semantic edit tokens for target disambiguation and structural preservation, while a lightweight conditioning pathway explicitly injects fine-grained visual garment details. Finally, we design a try-on-specific reward and utilize the DiffusionNFT algorithm to align the model with human preferences. Extensive experiments on ViViD-S and TripVVT-Bench demonstrate that InstructVVT outperforms state-of-the-art open-source methods in garment fidelity, structural preservation, and temporal consistency, despite requiring fewer inference-time controls.

Recent diffusion models have advanced image-conditioned video generation, but their accessibility raises risks of unauthorized manipulation. Image immunization has emerged as a promising defense for Image-to-Video (I2V) protection, yet existing methods often rely on degrading visual quality or temporal coherence. In this work, we revisit I2V immunization as reducing source-content preservation, shifting the focus from output degradation to weakening source-conditioned content propagation. To this end, we propose I2V-DETACH, an image immunization method that prevents unauthorized I2V generation through source grounding detachment. I2V models preserve source content by propagating source-image cues into video latents during denoising. Accordingly, I2V-DETACH disrupts this process in two complementary ways: it suppresses source-video grounding to reduce source cue propagation, and strengthens intra-video interactions to shift denoising toward video-side dynamics with reduced reliance on the source image. To obtain informative optimization signals, we initialize auxiliary video latents with source-oriented states that remain within the source-conditioned generation regime while deviating from source-preserving trajectories. Extensive experiments across diverse diffusion architectures show that I2V-DETACH substantially reduces source-content preservation, improves over prior immunization methods, and exhibits strong black-box transferability.

Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundamentally constrained by the quadratic complexity of the self-attention mechanism. Recent clustering-based sparse attention methods improve the quality-speed trade-off by grouping semantically similar tokens, but their practical efficiency remains limited by two bottlenecks: substantial clustering overhead and low CTA utilization caused by irregular cluster-induced blocks. We propose HyperVAttention (HVA), a training-free sparse attention framework that addresses both bottlenecks jointly. To reduce clustering overhead, we introduce 3D local-window clustering, which exploits the spatio-temporal locality of video tokens to restrict centroid search to fixed local neighborhoods, and implement it with a custom Triton kernel for efficient execution. We further propose a hybrid clustering strategy that performs full clustering only at anchor steps and updates only subset tokens at intermediate steps, leveraging the temporal stability of cluster assignments across denoising steps. To improve CTA utilization, we present hardware-aware cluster merging that minimizes CTA-aligned execution cost through parallel agglomerative merging, improving block density and approximation fidelity by utilizing idle tile capacity. Together, these components reduce clustering overhead, avoid redundant updates, and better align sparse attention with the fixed tile structure of modern GPU kernels. Experiments on Text-to-Video generation show that HVA establishes a new Pareto frontier for training-free sparse attention in video diffusion, reducing end-to-end latency by up to $2.13\times$ while improving fidelity over existing training-free sparse attention baselines.

Video generation models have achieved remarkable visual fidelity and have strong potential to become general-purpose world simulators. Despite this progress, they still fail to generate videos which adhere to laws of physics. The problem becomes even more apparent in realistic settings where multiple physical principles must work together within the same video; for example, "a balloon floating upward while steam rises from a pot" requires buoyancy and fluid dynamics to unfold coherently and simultaneously. Yet existing methods largely ignore multi-principle interactions, focusing on a single principle per video. We propose HiPhy (Hierarchical Physical Alignment), a reinforcement learning framework that grounds video generation in physical laws through a dual-level objective: locally enforcing the temporal dynamics of individual physical principles, and globally ensuring the physical and semantic coherence of the entire scene. To support multi-principle generation, we construct a 50K-prompt dataset and introduce a prompt benchmark MultiPhyBench, spanning a diverse range of co-occurring physical events. Our experiments show that HiPhy significantly outperforms prior methods and baselines, improving physical commonsense and semantic alignment significantly across various benchmarks, with the largest gains on scenes involving multiple concurrent physical principles where competing methods degrade most sharply.

In self-supervised pretraining for Handwritten Text Recognition (HTR), pixel reconstruction methods tend to outperform contrastive ones, a pattern that sits awkwardly with recent evidence that pixel reconstruction yields uninformative features for natural-image classification. We argue this discrepancy is not an accident, but a consequence of how HTR signal is distributed in pixel space. By probing the input distribution directly, we show that HTR's discriminative content is concentrated in the high-variance pixel subspace and is essentially absent from the low-variance one, the inverse of the structure observed for image classification. Under this view, the right SSL family becomes predictable: objectives that preserve high-variance pixel content should transfer best. We test this prediction across six SSL methods spanning three families (pixel-grounded MIM, JEPA-style, contrastive image--image and image--text), under matched encoder, data, and evaluation protocols on six handwriting benchmarks across five languages. Pixel-grounded SSL produces the lowest CER on every benchmark and every probe, exposes per-position character information that other families recover only via the readout, and is the only family that benefits from real-data pretraining. A geometric property of the encoder, its alignment with the high-variance pixel subspace, predicts CER within every SSL method we test. With a pretrained LLM decoder, a frozen pixel-grounded encoder is already competitive with fully fine-tuned supervised baselines, and full fine-tuning beats them on the mean and ranks first or second on every benchmark. These results challenge the prevailing view that pixel reconstruction wastes capacity on irrelevant detail: whether reconstruction is wasted depends on where the discriminative signal lives in the input.

Human-object-centric video personalization (HOCVP) is a core task within subject-driven video generation. However, existing methods suffer from two key limitations. First, most approaches focusing on $\textit{inter-subject}$ personalization still struggle to strike a balance between high subject fidelity and accurate interaction patterns between humans and diverse objects, especially when objects represent abstract concepts such as logos. Second, while $\textit{intra-subject}$ references ($\textit{e.g.}$, OCR maps, multi-view inputs) are expected to enhance subject fidelity, most existing works lack mechanisms to understand such latent correspondence. To address both challenges, we propose HOMIE, an HOCVP framework that tackles both inter- and intra-subject input settings in a unified manner. Compared to previous approaches, HOMIE proposes a better MLLM integration strategy to extract knowledge of reference-level relationships without compromising the controllability of text encoders or incurring costly re-alignment. Specifically, we introduce global multimodal guidance within self-attention to better align MLLM-derived semantic features with VAE tokens. Furthermore, we propose modality-reference embedding to differentiate tokens from MLLM features and VAE tokens and associate intra-subject reference image tokens. Extensive experiments validate that our method achieves state-of-the-art performance across various HOCVP tasks. Anonymous project page with videos is available at https://homie-demo.github.io/.

Rendering accurate text remains difficult for image generation and editing models, especially when the target contains long, complex, and densely arranged text or rare characters. Existing approaches either improve native text rendering through stronger backbones and data-centric training without explicit glyph priors, or incorporate glyph priors through specialized designs that remain insufficiently accurate and robust under challenging scenarios. We introduce GlyphAnchor, a novel text-rendering enhancement method for both text-to-image and image-editing diffusion transformer models. GlyphAnchor enhances the backbone with lightweight glyph patch conditions whose positions are anchored to the target image through the model's native positional encoding. We train this capability with staged supervised finetuning and further refine it with text-aware post-training to improve robustness. We also introduce InfoTextBench, a benchmark for evaluating text-rich visual text rendering in both generation and editing settings. Experiments across multiple backbones and benchmarks, including long, complex, and densely arranged text and rare character scenarios, show that GlyphAnchor consistently improves text fidelity while preserving overall image quality.

Autoregressive video diffusion models have demonstrated effectiveness in interactive game generation, with Minecraft gameplay serving as a representative application. To faithfully simulate gameplay, a model must generate natural content when exploring new scenes while preserving spatial consistency when revisiting explored areas. Under limited computation budgets, it must compress and exploit historical cues within a finite context window, which exposes a trade-off: models relying solely on temporal context offer flexible exploration but suffer from poor revisit consistency, whereas adding spatial memory strengthens consistency but may degrade new scene generation quality when the model over-relies on sparse or unreliable spatial context. We present GeoMemory, a learning framework that pairs training protocols with a geometry-indexed spatial memory. Specifically, our Hybrid Training exposes the model to both exploration and revisitation regimes, guiding the model to rely on temporal memory in new scenes while effectively incorporating spatial memory upon revisits. Chained Forward Training creates larger pose variations and encourages reliance on spatial memory for maintaining consistency. For spatial memory, we integrate Point-to-Frame Retrieval with an incremental 3D cache generated by VGGT, enabling constant-time retrieval of relevant historical context regardless of sequence length. Extensive experiments demonstrate that GeoMemory achieves superior performance in both long-term spatial consistency and visual quality in new scenes with real-time interaction.

Text-to-image models can generate plausible street scenes from prompts such as “a street in New York City,” but it remains unclear whether these images resemble the requested place or show a generic city appearance. Commonly used evaluation metrics mainly measure image quality or text alignment and do not directly assess geographic fidelity. We introduce GeoFidelity-Bench, a benchmark for evaluating whether generated street-view images match a target location at the level of named street blocks. The benchmark contains 112 street blocks from 25 cities across six continents, each paired with a panel of real Mapillary images and geographic metadata. From this metadata we build prompts with the city only, with street and neighborhood names, and with these names plus raw GPS coordinates. Across six open-weight text-to-image models, street and neighborhood names improve similarity to the target location, while raw GPS coordinates add only a small and uneven gain. Control prompts that swap in the names of other blocks while keeping the city fixed reduce retrieval accuracy, with larger decreases when the neighborhood name or both names are replaced. Generated images also distinguish their target blocks from local alternatives less reliably than held-out real images. CLIP alignment between generated images and their prompts is nearly uninformative about whether the images achieve block-level geographic fidelity. GeoFidelity-Bench provides a controlled testbed for studying location-conditioned generation and for measuring progress beyond generic city-level plausibility.

Individual-level wildlife identification often suffers from data scarcity, as varying observations of the same animal under diverse poses, viewpoints, and motions are rarely available. Image-to-video (I2V) generation offers a promising way to mitigate this limitation by synthesizing additional observations from a single reference image. However, existing I2V models mainly emphasize global layout, semantics, and motion, and therefore often fail to preserve fine-grained local appearance cues that distinguish one wildlife individual from another, such as fur texture, stripe boundaries, spot configurations, and contour transitions. We observe that these identity-critical cues are closely related to high-frequency information, which is essential for distinguishing individuals. To address this challenge, we propose WildIcon, a high-frequency-guided I2V framework for wildlife individual consistency. Specifically, WildIcon introduces a frequency-aware identity encoding branch that extracts individual-specific high-frequency cues from the reference image. Combined with isolated foreground information, the resulting identity tokens are then injected into cross-attention blocks as identity conditioning. Building on a frozen backbone with lightweight identity adaptation, WildIcon strengthens fine-grained identity preservation while retaining the motion controllability and semantic fidelity of the base I2V model. In addition, to support the training and evaluation of wildlife individual-consistent I2V, we construct WildlifeVid, a wildlife-centric video dataset with high-quality, temporally coherent clips and individual-level identity labels. Experiments on both I2V and downstream animal re-identification (ReID) show that WildIcon achieves stronger individual consistency than existing baselines and provides useful, reliable synthetic data to improve downstream ReID performance.

Artistic styles are rooted in specific socio-historical contexts that encode social hierarchies, including distinct constructions of gender. Yet in AI research, style has long been treated as a surface-level visual property: a filter of color, brushstroke, and texture applied to otherwise content-neutral scenes. We introduce the first dataset to investigate the interplay between gender representation and style in both historical and generated images. StyleGender comprises 74k images spanning 19 artistic styles, comprising art historical images with style and gender annotations, T2I-generated images under controlled style and gender prompts, and a semantically aligned set enabling direct art history-to-generation comparison. By proposing two Set Gender Artifact (SGA) metrics (PixelSGA and MaskSGA), capturing gender signals at the pixel level and in compositional structure, we show that (1) gender representation shapes visual features across artistic styles, (2) style keywords carry these patterns into T2I generation, and (3) generative models tend to amplify gender artifacts beyond what is observed in historical sources.

Recent advances in visual storytelling have leveraged powerful text-to-image diffusion models to generate sequences of images featuring consistent subjects and styles. While such methods achieve impressive identity preservation across the sequence, they often produce scenes with limited structural diversity---images that are overly similar in subject pose and spatial layout. Existing evaluation protocols primarily measure identity consistency using metrics such as DreamSim, which can inadvertently conflate identity preservation with subject pose. The inability to independently evaluate structural diversity inhibits progress on identity preserving image generation methods. We address this limitation by introducing a new metric based on the Gromov Wasserstein distance to quantify structural diversity independently of identity. Our metric provides an interpretable and generalizable measure of spatial variation across generated images, enabling a more balanced assessment of identity consistency and pose diversity. Using this framework, we systematically evaluate several recent visual storytelling and subject-consistent generation methods. Furthermore, we evaluate the effect of latent initialization methods on structural diversity in several popular text-to-image models.

Action-conditioned surgical video generation is a critical yet highly challenging problem for robotic surgery. The core difficulty is that low-dimensional control vectors must precisely govern complex image-space evolution. In this work, we propose a kinematic-to-visual lifting paradigm that converts articulated kinematics into a unified set of five image-aligned control modalities. Building on this representation, we introduce a hierarchically routed visual control framework that selectively activates the most relevant control modalities and motion scales. Instead of uniformly applying all control signals, our model performs hierarchical routing to dynamically allocate conditioning capacity. We further design kinematic-prior-guided routing loss functions to ensure physically meaningful, temporally stable, and efficient expert utilization. To improve efficiency, we propose a budgeted training and inference scheme that leverages routing-induced sparsity. By selectively discarding low-significance control pathways during training and execution, our approach enables adaptive computation that is complementary to standard distillation. We additionally construct a new benchmark with curated articulated annotations, obtained through human-in-the-loop semantic labeling and differentiable pose tracking, providing realistic supervision for action-conditioned surgical video generation. Extensive experiments demonstrate that our method consistently improves action faithfulness, visual fidelity, and cross-domain generalization over diverse baselines. Moreover, our efficient variant achieves substantial reductions in latency while maintaining strong control accuracy.

Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality challenging. Existing methods mostly select historical frames based on attention scores, but their context decisions remain coarse. When multiple frames are generated in the same chunk, these methods often apply a shared history selection to the whole chunk, score historical frames solely by attention, and assign head-wise budgets either uniformly or by attention-pattern heuristics rather than explicit head-importance estimation. We show that frames within the same generated chunk can depend on distinct historical frames, that the same historical frame can receive different attention scores as its relative temporal distance to the current frames changes, and that masking different heads induces unequal generation degradation. Motivated by these findings, we propose \textbf{Focused Forcing}, a training-free KV selection method that focuses cached history along both generated-frame and head dimensions. For each generated frame, Focused Forcing preserves the most relevant and distinctive historical frames by combining attention scores with diversity scores of historical frames, while assigning larger budgets to heads with higher estimated importance. Across multiple autoregressive generation paradigms, Focused Forcing achieves up to $\textbf{1.48}\times$ end-to-end acceleration without training, while \textbf{improving visual quality and text alignment}. \textit{Our code will be released on GitHub.}

Text-guided video editing requires applying a semantic change while keeping source motion, layout, and unchanged content stable. Recent inversion-free flow editors derive effective edit signals from target-source velocity differences, yet typically inject these signals directly at each solver step. In neural video sampling, however, this direct execution rule overlooks an important distinction: the velocity difference is an online, state-dependent observation rather than a fixed endpoint-displacement command. As the target branch evolves under previous injections, direct injection may accumulate temporal fluctuations and off-target perturbations, producing motion drift, identity flicker, or unintended changes in weak-response regions. We propose FlowTrack, a causal execution controller for inversion-free flow video editing. FlowTrack leaves the pretrained generator and raw edit signal unchanged, but executes the signal through a carried displacement-like direction and response-aware attenuation. We derive this update as the closed-form solution of a local execution objective that balances current signal tracking, temporal carrying, and weak-response suppression. On the full FiVE-Bench protocol, FlowTrack improves motion fidelity, unedited-region fidelity, and structure consistency over strong training-free diffusion- and flow-based editors while maintaining competitive target-prompt alignment. Code is available at https://anonymous.4open.science/r/FlowTrack.

Portrait video relighting aims to modify the illumination of a portrait video while preserving photorealism and temporal stability. The task becomes particularly challenging under dynamic lighting, where illumination direction, intensity, and color vary over time. To tackle this problem, we introduce FlashRelight, a novel two-stage framework for dynamic portrait video relighting. FlashRelight first suppresses the source illumination through delighting, and then synthesizes the target dynamic lighting on an illumination-neutral portrait video. FlashRelight supports three complementary control modalities: envmap sequences for explicit frame-level lighting control, dynamic lighting text for semantic illumination editing, and lighting reference videos for visual lighting transfer. Training follows a low-cost hybrid strategy that combines static one-light-at-a-time (OLAT) data with generated dynamic-lighting portrait videos, covering both controlled illumination variation and realistic portrait motion. Extensive experiments show that FlashRelight achieves temporally coherent and photorealistic dynamic relighting while enabling flexible cross-video lighting transfer.