NeurIPS 2025 Papers

Visual AutoRegressive (VAR) modeling employs a next-scale decoding paradigm that progresses from coarse structures to fine details. While enhancing fidelity and scalability, this approach challenges two fundamental assumptions of conventional dynamic inference: semantic stability (intermediate outputs approximating final results) and monotonic locality (smooth representation evolution across layers), which renders existing dynamic inference methods ineffective for VAR models. To address this challenge, we propose FreqExit, a unified training framework that enables dynamic inference in VAR without altering its architecture or compromising output quality. FreqExit is based on a key insight: high-frequency details are crucial for perceptual quality and tend to emerge only in later decoding stages. Leveraging this insight, we design targeted mechanisms that guide the model to learn more effectively through frequency-aware supervision. The proposed framework consists of three components: (1) a curriculum-based supervision strategy with progressive layer dropout and early exit loss; (2) a wavelet-domain high-frequency consistency loss that aligns spectral content across different generation steps; and (3) a lightweight self-supervised frequency-gated module that guides adaptive learning of both structural and detailed spectral components. On ImageNet 256×256, FreqExit achieves up to 2× speedup with only minor degradation, and delivers 1.3× acceleration without perceptible quality loss. This enables runtime-adaptive acceleration within a unified model, offering a favorable trade-off between efficiency and fidelity for for practical and flexible deployment.

Inspired by the in-context learning mechanism of large language models (LLMs), a new paradigm of generalizable visual prompt-based image editing is emerging. Existing single-reference methods typically focus on style or appearance adjustments and struggle with non-rigid transformations. To address these limitations, we propose leveraging source-target image pairs to extract and transfer content-aware editing intent to novel query images. To this end, we introduce RelationAdapter, a lightweight module that enables Diffusion Transformer (DiT) based models to effectively capture and apply visual transformations from minimal examples. We also introduce Relation252K, a comprehensive dataset comprising 218 diverse editing tasks, to evaluate model generalization and adaptability in visual prompt-driven scenarios. Experiments on Relation252K show that RelationAdapter significantly improves the model’s ability to understand and transfer editing intent, leading to notable gains in generation quality and overall editing performance.

Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. The rapid advancement of multi-modal large language models (MLLMs) has significantly broadened the scope of IQA, moving toward comprehensive image quality understanding that incorporates content analysis, degradation perception, and comparison reasoning beyond mere numerical scoring. Previous MLLM-based methods typically either generate numerical scores lacking interpretability or heavily rely on supervised fine-tuning (SFT) using large-scale annotated datasets to provide descriptive assessments, limiting their flexibility and applicability. In this paper, we propose Q-Insight, a reinforcement learning-based model built upon group relative policy optimization (GRPO), which demonstrates strong visual reasoning capability for image quality understanding while requiring only a limited amount of rating scores and degradation labels. By jointly optimizing score regression and degradation perception tasks with carefully designed reward functions, our approach effectively exploits their mutual benefits for enhanced performance. Extensive experiments demonstrate that Q-Insight substantially outperforms existing state-of-the-art methods on both score regression and degradation perception tasks, while exhibiting impressive zero-shot generalization and superior comparison reasoning capability. The code and models are available at https://github.com/bytedance/Q-Insight.

$360^\circ$ videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees. To achieve more accessible and personalized content creation in $360^\circ$ video format, we seek to lift standard perspective videos into $360^\circ$ equirectangular videos. To this end, we introduce **Imagine360**, the first perspective-to-$360^\circ$ video generation framework that creates high-quality $360^\circ$ videos with rich and diverse motion patterns from video anchors. Imagine360 learns fine-grained spherical visual and motion patterns from limited $360^\circ$ video data with several key designs. **1)** Firstly we adopt the dual-branch design, including a perspective and a panorama video denoising branch to provide local and global constraints for $360^\circ$ video generation, with motion module and spatial LoRA layers fine-tuned on $360^\circ$ videos. **2)** Additionally, an antipodal mask is devised to capture long-range motion dependencies, enhancing the reversed camera motion between antipodal pixels across hemispheres. **3)** To handle diverse perspective video inputs, we propose rotation-aware designs that adapt to varying video masking due to changing camera poses across frames. **4)** Lastly, we introduce a new 360 video dataset featuring 10K high-quality, trimmed 360 video clips with structured motion to facilitate training. Extensive experiments show Imagine360 achieves superior graphics quality and motion coherence with our curated dataset among state-of-the-art $360^\circ$ video generation methods. We believe Imagine360 holds promise for advancing personalized, immersive $360^\circ$ video creation.

Despite significant advances in Vision Language Models (VLMs), they remain constrained by the complexity and redundancy of visual input. When images contain large amounts of irrelevant information, VLMs are susceptible to interference, thus generating excessive task-irrelevant reasoning processes or even hallucinations. This limitation stems from their inability to discover and process the required regions during reasoning precisely. To address this limitation, we present the Chain of Foresight-Focus Thought (CoFFT), a novel training-free approach that enhances VLMs' visual reasoning by emulating human visual cognition. Each Foresight-Focus Thought consists of three stages: (1) Diverse Sample Generation: generates diverse reasoning samples to explore potential reasoning paths, where each sample contains several reasoning steps; (2) Dual Foresight Decoding: rigorously evaluates these samples based on both visual focus and reasoning progression, adding the first step of optimal sample to the reasoning process; (3) Visual Focus Adjustment: precisely adjust visual focus toward regions most beneficial for future reasoning, before returning to stage (1) to generate subsequent reasoning samples until reaching the final answer. These stages function iteratively, creating an interdependent cycle where reasoning guides visual focus and visual focus informs subsequent reasoning. Empirical results across multiple benchmarks using Qwen2.5-VL, InternVL-2.5, and Llava-Next demonstrate consistent performance improvements of 3.1-5.8\% with controllable increasing computational overhead.

Lip synchronization is the task of aligning a speaker’s lip movements in video with corresponding speech audio, and it is essential for creating realistic, expressive video content. However, existing methods often rely on reference frames and masked-frame inpainting, which limit their robustness to identity consistency, pose variations, facial occlusions, and stylized content. In addition, since audio signals provide weaker conditioning than visual cues, lip shape leakage from the original video will affect lip sync quality. In this paper, we present OmniSync, a universal lip synchronization framework for diverse visual scenarios. Our approach introduces a mask-free training paradigm using Diffusion Transformer models for direct frame editing without explicit masks, enabling unlimited-duration inference while maintaining natural facial dynamics and preserving character identity. During inference, we propose a flow-matching-based progressive noise initialization to ensure pose and identity consistency, while allowing precise mouth-region editing. To address the weak conditioning signal of audio, we develop a Dynamic Spatiotemporal Classifier-Free Guidance (DS-CFG) mechanism that adaptively adjusts guidance strength over time and space. We also establish the AIGC-LipSync Benchmark, the first evaluation suite for lip synchronization in diverse AI-generated videos. Extensive experiments demonstrate that OmniSync significantly outperforms prior methods in both visual quality and lip sync accuracy, achieving superior results in both real-world and AI-generated videos.

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi–Head Self–Attention (MHSA) layer still performs a quadratic query–key interaction for \emph{every} token pair, spending the bulk of computation on visually weak or redundant correlations. We introduce \emph{Visual–Contrast Attention} (VCA), a drop-in replacement for MHSA that injects an explicit notion of discrimination while reducing the theoretical complexity from $\mathcal{O}(N^{2}C)$ to $\mathcal{O}(N n C)$ with $n\!\ll\!N$. VCA first distils each head’s dense query field into a handful of spatially pooled \emph{visual–contrast tokens}, then splits them into a learnable \emph{positive} and \emph{negative} stream whose differential interaction highlights what truly separates one region from another. The module adds fewer than $0.3$\,M parameters to a DeiT-Tiny backbone, requires no extra FLOPs, and is wholly architecture-agnostic. Empirically, VCA lifts DeiT-Tiny top-1 accuracy on ImageNet-1K from $72.2\%$ to \textbf{$75.6\%$} (+$3.4$) and improves three strong hierarchical ViTs by up to $3.1$\%, while in class-conditional ImageNet generation it lowers FID-50K by $2.1$ to $5.2$ points across both diffusion (DiT) and flow (SiT) models. Extensive ablations confirm that (i) spatial pooling supplies low-variance global cues, (ii) dual positional embeddings are indispensable for contrastive reasoning, and (iii) combining the two in both stages yields the strongest synergy. VCA therefore offers a simple path towards faster and sharper Vision Transformers. The source code is available at \href{https://github.com/LeapLabTHU/LinearDiff}{https://github.com/LeapLabTHU/LinearDiff}.

With the rapid progress of large language models (LLMs) and diffusion models, there has been growing interest in personalized content generation. However, current conversational systems often present the same recommended content to all users, falling into the dilemma of "one-size-fits-all." To break this limitation and boost user engagement, in this paper, we introduce PCG (**P**ersonalized Visual **C**ontent **G**eneration), a unified framework for personalizing item images within conversational systems. We tackle two key bottlenecks: the depth of personalization and the fidelity of generated images. Specifically, an LLM-powered Inclinations Analyzer is adopted to capture user likes and dislikes from context to construct personalized prompts. Moreover, we design a dual-stage LoRA mechanism—Global LoRA for understanding task-specific visual style, and Local LoRA for capturing preferred visual elements from conversation history. During training, we introduce the visual content condition method to ensure LoRA learns both historical visual context and maintains fidelity to the original item images. Extensive experiments on benchmark conversational datasets—including objective metrics and GPT-based evaluations—demonstrate that our framework outperforms strong baselines, which highlight its potential to redefine personalization in visual content generation for conversational scenarios like e-commerce and real-world recommendation.

As Visual Language Models (VLMs) continue to evolve, they have demonstrated increasingly sophisticated logical reasoning capabilities and multimodal thought generation, opening doors to widespread applications. However, this advancement raises serious concerns about content security, particularly when these models process complex multimodal inputs requiring intricate reasoning. When faced with these safety challenges, the critical competition between logical reasoning and safety objectives of VLMs is often overlooked in previous works. In this paper, we introduce Visualization-of-Thought Attack (\textbf{VoTA}), a novel and automated attack framework that strategically constructs chains of images with risky visual thoughts to challenge victim models. Our attack provokes the inherent conflict between the model's logical processing and safety protocols, ultimately leading to the generation of unsafe content. Through comprehensive experiments, VoTA achieves remarkable effectiveness, improving the average attack success rate (ASR) by 26.71\% (from 63.70\% to 90.41\%) on 9 open-source and 6 commercial VLMs, compared to the state-of-the-art methods. These results expose a critical vulnerability: current VLMs struggle to maintain safety guarantees when processing insecure multimodal visualization-of-thought inputs, highlighting the urgency and necessity of enhancing safety alignment. Our code and dataset are available at https://github.com/Hongqiong12/VoTA. Content Warning: This paper contains harmful contents that may be offensive.

Audio-visual understanding is a rapidly evolving field that seeks to integrate and interpret information from both auditory and visual modalities. Despite recent advances in multi-modal learning, existing benchmarks often suffer from strong visual bias -- when answers can be inferred from visual data alone -- and provide only aggregate scores that conflate multiple sources of error. This makes it difficult to determine whether models struggle with visual understanding, audio interpretation, or audio-visual alignment. In this work, we introduce DAVE: Diagnostic Audio Visual Evaluation, a novel benchmark dataset designed to systematically evaluate audio-visual models across controlled settings. DAVE alleviates existing limitations by (i) ensuring both modalities are necessary to answer correctly and (ii) decoupling evaluation into atomic subcategories. Our detailed analysis of state-of-the-art models reveals specific failure modes and provides targeted insights for improvement. By offering this standardized diagnostic framework, we aim to facilitate more robust development of audio-visual models. Dataset: https://huggingface.co/datasets/gorjanradevski/dave Code: https://github.com/gorjanradevski/dave

We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models, enabling visual correspondence in a manner analogous to the well-established semantic correspondence. While diffusion model backbones are known to encode semantically rich features, they must also contain visual features to support their image synthesis capabilities. However, isolating these visual features is challenging due to the absence of annotated datasets. To address this, we introduce an automated pipeline that constructs image pairs with annotated semantic and visual correspondences based on existing subject-driven image generation datasets, and design a contrastive architecture to separate the two feature types. Leveraging the disentangled representations, we propose a new metric, Visual Semantic Matching (VSM), that quantifies visual inconsistencies in subject-driven image generation. Empirical results show that our approach outperforms global feature-based metrics such as CLIP, DINO, and vision--language models in quantifying visual inconsistencies while also enabling spatial localization of inconsistent regions. To our knowledge, this is the first method that supports both quantification and localization of inconsistencies in subject-driven generation, offering a valuable tool for advancing this task.

Hallucination remains a major challenge in multimodal large language models (MLLMs). To address this, various contrastive decoding (CD) methods have been proposed that contrasts original logits with hallucinated logits generated from perturbed inputs. While CD has shown promise in vision-language models (VLMs), it is not well-suited for AV-LLMs, where hallucinations often emerge from both unimodal and cross-modal combinations involving audio, video, and language. These intricate interactions call for a more adaptive and modality-aware decoding strategy. In this paper, we propose Audio-Visual Contrastive Decoding (AVCD)—a novel, training-free decoding framework designed to model trimodal interactions and suppress modality-induced hallucinations in AV-LLMs. Unlike previous CD methods in VLMs that corrupt a fixed modality, AVCD leverages attention distributions to dynamically identify less dominant modalities and applies attentive masking to generate perturbed output logits. To support CD in a trimodal setting, we also reformulate the original CD framework to jointly handle audio, visual, and textual inputs. Finally, to improve efficiency, we introduce entropy-guided adaptive decoding, which selectively skips unnecessary decoding steps based on the model’s confidence in its predictions. Extensive experiments demonstrate that AVCD consistently outperforms existing decoding methods. Especially, on the AVHBench dataset, it improves accuracy by 2% for VideoLLaMA2 and 7% for video-SALMONN, demonstrating strong robustness and generalizability. Our code is available at : https://github.com/kaistmm/AVCD.

This work challenges the residual prediction paradigm in visual autoregressive modeling and presents FlexVAR, a new Flexible Visual AutoRegressive image generation paradigm. FlexVAR facilitates autoregressive learning with ground-truth prediction, enabling each step to independently produce plausible images. This simple, intuitive approach swiftly learns visual distributions and makes the generation process more flexible and adaptable. Trained solely on low-resolution images (< 256px), FlexVAR can: (1) Generate images of various resolutions and aspect ratios, even exceeding the resolution of the training images. (2) Support various image-to-image tasks, including image refinement, in/out-painting, and image expansion. (3) Adapt to various autoregressive steps, allowing for faster inference with fewer steps or enhancing image quality with more steps. Our 1.0B model outperforms its VAR counterpart on the ImageNet 256 × 256 benchmark. Moreover, when zero-shot transfer the image generation process with 13 steps, the performance further improves to 2.08 FID, outperforming state-of-the-art autoregressive models AiM/VAR by 0.25/0.28 FID and popular diffusion models LDM/DiT by 1.52/0.19 FID, respectively. When transferring our 1.0B model to the ImageNet 512 × 512 benchmark in a zero-shot manner, FlexVAR achieves competitive results compared to the VAR 2.3B model, which is a fully supervised model trained at 512 × 512 resolution.

Audio-driven human animation methods, such as talking head and talking body generation, have made remarkable progress in generating synchronized facial movements and appealing visual quality videos. However, existing methods primarily focus on single human animation and struggle with multi-stream audio inputs, facing incorrect binding problems between audio and persons. Additionally, they exhibit limitations in instruction-following capabilities. To solve this problem, in this paper, we propose a novel task: Multi-Person Conversational Video Generation, and introduce a new framework, MultiTalk, to address the challenges during multi-person generation. Specifically, for audio injection, we investigate several schemes and propose the Label Rotary Position Embedding (L-RoPE) method to resolve the audio and person binding problem. Furthermore, during training, we observe that partial parameter training and multi-task training are crucial for preserving the instruction-following ability of the base model. MultiTalk achieves superior performance compared to other methods on several datasets, including talking head, talking body, and multi-person datasets, demonstrating the powerful generation capabilities of our approach.

Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video generation. MTV explicitly separates audios into speech, effects, and music tracks, enabling disentangled control over lip motion, event timing, and visual mood, respectively—resulting in fine-grained and semantically aligned video generation. To support the framework, we additionally present DEMIX, a dataset comprising high-quality cinematic videos and demixed audio tracks. DEMIX is structured into five overlapped subsets, enabling scalable multi-stage training for diverse generation scenarios. Extensive experiments demonstrate that MTV achieves state-of-the-art performance across six standard metrics spanning video quality, text-video consistency, and audio-video alignment.

We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike prior approaches that rely on classifier-based or classifier-free guidance, MGAudio enables the generative model to guide itself through a dedicated training objective designed for video-conditioned audio generation. The framework integrates three main components: (1) a scalable flow-based Transformer denoiser, (2) a dual-role alignment mechanism where the audio-visual encoder serves both as a conditioning module and as a feature aligner to improve generation quality, and (3) a model-guided objective that enhances cross-modal coherence and audio realism. MGAudio achieves state-of-the-art performance on VGGSound, reducing FAD to 0.40, substantially surpassing the best classifier-free guidance baselines, and consistently outperforms existing methods across FD, IS, and alignment metrics. It also generalizes well to the challenging UnAV-100 benchmark. These results highlight model-guided dual-role alignment as a powerful and scalable paradigm for conditional video-to-audio generation. Code is available at: https://github.com/pantheon5100/mgaudio