arXiv subjects

Yunhai Tong

Publications and source records attributed to Yunhai Tong.

At least 19 recordsLinked to original sources

arXiv2026

Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation

Multi-subject video generation faces two key challenges: uncontrollable fidelity strength and potential semantic drift. We address these by analyzing the internal mechanisms of Diffusion Transformers (DiTs). We found that certain attention blocks naturally form an Intrinsic Spatial Grounding Map (ISGM) that precisely locates reference subjects. Building on this insight, we propose Dual-phase Intrinsic Attention Leveraging (DIAL), a framework that uses these internal signals for both training and inference. In low-noise stages, we use ISGM to guide the attention mechanism, allowing precise control over fidelity strength during inference without retraining. In high-noise stages, we use these same maps to automatically build preference pairs at no additional cost for Reinforcement Learning (RL). This RL procedure effectively anchors the model's attention to reference subjects and mitigates semantic drift. Extensive experiments show that DIAL significantly outperforms baseline models on the OpenS2V-Eval benchmark, consistently improving identity consistency and enabling controllable fidelity strength.

cs.CV↗

arXiv2026

Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos

This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal single-stage instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, advanced vision-language models, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction tokens that guide SAM-2 in producing precise masks, enabling a grounded, multi-modal understanding of both static and dynamic visual content. Additionally, we introduce Ref-SAV, an auto-labeled dataset containing over 72k object expressions in complex video scenes, designed to boost model performance. We also manually validate 2k video objects in the Ref-SAV datasets to benchmark referring video object segmentation in complex environments. Experiments show that Sa2VA achieves strong performance across multiple tasks, particularly in referring video object segmentation, highlighting its potential for complex real-world applications. In addition, Sa2VA can be easily extended into various MLLMs, including Qwen-VL and Intern-VL, which can be updated with rapid process in current open-sourced MLLMs. Code and models have been provided to the community.

cs.CV↗

arXiv2026

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DLMs. Specifically, we introduce efficient prompting and structured attention masking to enable simultaneous perception of multiple masked regions, allowing the model to generate region descriptions in parallel at both the sequence and token levels. This design significantly improves inference efficiency compared with existing approaches that process regions sequentially. To systematically evaluate the parallelism property of visual perception capability for DLMs, we construct a new Parallel Detailed Localized Captioning Benchmark (ParaDLC-Bench) by scaling the DLC-Bench to include multiple region masks per image, enabling joint evaluation of both caption quality and inference efficiency. Experiments demonstrate that PerceptionDLM maintains competitive performance in region captioning while achieving substantial speed improvements for multi-region perception tasks. Our results highlight the potential of multimodal diffusion language models for efficient, parallel visual perception. To the best of our knowledge, we are the first to achieve parallel region caption and perception by leveraging the advantages of diffusion language models. Code, models, and datasets are released.

cs.CV↗

arXiv2026

LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing

Developing unified video generation and editing models capable of interpreting interleaved multimodal inputs is a promising yet challenging frontier field. Existing unified frameworks predominantly rely on massive models (typically 13B parameters or more) and incorporate source video conditions for editing by concatenating sequence tokens. This concatenation inevitably doubles the sequence length, quadrupling the computational complexity of the self-attention mechanism and introducing prohibitive overhead. To address these bottlenecks, we present LoomVideo, a highly efficient 5B-parameter unified architecture for both video generation and editing. LoomVideo replaces the standard text encoder with a Multimodal Large Language Model (MLLM) and employs Deepstack injection mechanism to align multi-layer MLLM features with the Diffusion Transformer (DiT). Crucially, we introduce a zero-overhead Scale-and-Add conditioning approach for video editing. By scaling and directly adding the clean source video latent to the noised target latent, this elegant design eliminates the need for token concatenation, drastically reducing computational cost while maintaining robust capabilities for complex, non-rigid edits. Furthermore, a Negative Temporal RoPE strategy is seamlessly integrated to handle multiple reference images. Extensive experiments demonstrate that our compact 5B model achieves state-of-the-art or highly competitive performance across comprehensive benchmarks, exhibiting exceptional superiority in e-commerce and fashion generation scenarios. Benefiting from the zero-overhead conditioning mechanism, LoomVideo achieves at least a 5.41x acceleration in inference speed compared to models of similar capabilities, paving the way for highly practical and efficient video foundation models.

cs.CV↗

arXiv2026

Watch, Remember, Reason: Human-View Video Understanding with MLLMs

Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios. These scenarios require models to handle sparse evidence, long-range dependencies, multimodal alignment, and reliable inference under limited computational budgets. This work presents a human-view perspective on LLM-based video understanding, organized around three functional abilities: watching, remembering, and reasoning. Rather than treating video tasks as isolated benchmarks, this view provides a unified structure for analyzing how video MLLMs acquire evidence, preserve context, and produce grounded outputs. We introduce a formulation that characterizes video understanding systems by their perceptual representations, memory states, reasoning traces, and final predictions. Based on this formulation, we identify challenges in spatio-temporal perception, efficient long-video processing, memory modeling, streaming understanding, and faithful reasoning. Representative methods are organized by their roles in video MLLM systems. Watching covers fine-grained, comprehensive, audio-visual, and efficient perception. Remembering includes offline and streaming memory, while reasoning covers text-only reasoning and thinking with videos. We further examine application domains such as egocentric, sports, instructional, medical, and narrative videos, and cover training datasets and evaluation benchmarks across task types, supervision formats, modalities, and capability dimensions. Finally, we outline open problems and future directions for scalable, memory-aware, and evidence-grounded video intelligence. Related works will be continuously traced at https://github.com/marinero4972/Awesome-HumanView-VideoUnderstanding.

cs.CV↗

arXiv2026

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer from slow inference due to sequential decoding, and non-autoregressive unified models suffer from weak generalization due to limited pretrained backbones. We introduce the second-generation Meissonic: Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities. Unlike prior unified diffusion models trained from scratch, Muddit integrates strong visual priors from a pretrained text-to-image backbone with a lightweight text decoder, enabling flexible and high-quality multimodal generation under a unified architecture. Empirical results show that Muddit achieves competitive or superior performance compared to significantly larger autoregressive models in both quality and efficiency. The work highlights the potential of purely discrete diffusion, when equipped with strong visual priors, as a scalable and effective backbone for unified generation.

cs.LG↗

arXiv2026

One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double compute, or by introducing specialized parameterizations and multi-stage pipelines that fragment optimization. In this paper, we introduce Fixed-Point Distillation (FPD), an end-to-end framework that constructs local correction targets by partially corrupting the student's one-step draft and refining it with a single teacher step. To compute the training objective in a semantically meaningful space, we lift discrete tokens into continuous features and apply a multi-bandwidth drift loss that iteratively accumulates these corrections. To backpropagate through the discrete bottleneck, we employ a straight-through estimator that feeds exact hard-sampled tokens to the teacher and decoder during the forward pass, ensuring that training and inference operate on the same codebook manifold, while routing continuous gradients back to the student logits. This fully differentiable pathway additionally accommodates an optional unconditional adversarial objective to enhance perceptual realism. Evaluations on both class- and text-conditional generation validate the effectiveness of our framework. FPD achieves competitive visual fidelity and structural alignment within a single inference step, narrowing the gap to multi-step teachers while outperforming existing discrete distillation baselines.

cs.CV↗

arXiv2026

Towards Customized Multimodal Role-Play

Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style, and visual identity while maintaining output consistency across modalities remains largely unexplored. To mitigate this gap, we introduce a new task, Customized Multimodal Role-Play (CMRP). We construct the RoleScape-20 dataset comprising 20 characters, including training and evaluation data that cover persona, stylistic descriptions, visual/expressive cues, and text-image interactions. Building on a unified model, we devise UniCharacter, a two-stage training framework containing Unified Supervised Finetuning (Unified-SFT) and character-specific group relative policy optimization (Character-GRPO). Given only 10 images plus corresponding interaction examples, the model acquires the target character and exhibits coherent persona, style, and visual identity in both generated text and images. This process takes about 100 GPU hours. Experiments on the RoleScape-20 dataset show that the proposed method substantially outperforms prior approaches. Ablation studies further validate the effectiveness of our cross-modal consistency design and few-shot customization strategy. We argue that CMRP, coupled with unified modeling, provides a basis for next-generation characterful and immersive interactive agents.

cs.LG↗

arXiv2026

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual understanding and reasoning, and (2) answer correctness is often measured without verifying whether models identify the precise spatio-temporal evidence supporting their predictions. To address this, we present VideoZeroBench, a hierarchical benchmark designed for challenging long-video question answering that rigorously verifies spatio-temporal evidence. It comprises 500 manually annotated questions across 13 domains, paired with temporal intervals and spatial bounding boxes as evidence. To disentangle answering generation, temporal grounding, and spatial grounding, we introduce a five-level evaluation protocol that progressively tightens evidence requirements. Experiments show that even Gemini-3-Pro correctly answers fewer than 17% of questions under the standard end-to-end QA setting (Level-3). When grounding constraints are imposed, performance drops sharply: No model exceeds 1% accuracy when both correct answering and accurate spatio-temporal localization are required (Level-5), with most failing to achieve any correct grounded predictions. These results expose a significant gap between surface-level answer correctness and genuine evidence-based reasoning, revealing that grounded video understanding remains a bottleneck for long-video QA. We further analyze performance across minimal evidence spans, atomic abilities, and inference paradigms, providing insights for future research in grounded video reasoning. The benchmark and code will be made publicly available.

cs.CV↗

arXiv2026

Rethinking Vector Field Learning for Generative Segmentation

Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic mismatch between continuous flow matching objectives and discrete perception tasks. In this work, we revisit diffusion segmentation from the perspective of vector field learning. We identify two key limitations of the commonly used flow matching objective: gradient vanishing and trajectory traversing, which result in slow convergence and poor class separation. To tackle these issues, we propose a principled vector field reshaping strategy that augments the learned velocity field with a detached distance-aware correction term. This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework. Furthermore, we design a computationally efficient, quasi-random category encoding scheme inspired by Kronecker sequences, which integrates seamlessly with an end-to-end pixel neural field framework for pixel-level semantic alignment. Extensive experiments consistently demonstrate significant improvements over vanilla flow matching approaches, substantially narrowing the performance gap between generative segmentation and strong discriminative specialists.

cs.CV↗

arXiv2026

Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence

Most video reasoning models only generate textual reasoning traces without indicating when and where key evidence appears. Recent models such as OpenAI-o3 have sparked wide interest in evidence-centered reasoning for images, yet extending this ability to videos is more challenging due to the need for joint temporal tracking and spatial localization across dynamic scenes. We introduce Open-o3-Video, a non-agent framework that integrates explicit spatio-temporal evidence into video reasoning by highlighting key timestamps, objects, and bounding boxes, making the reasoning process traceable and verifiable. To enable this capability, we first construct high-quality datasets STGR that provide unified spatio-temporal supervision, which is absent in existing resources. We further adopt a cold-start reinforcement learning strategy with specially designed rewards that jointly encourage answer accuracy, temporal alignment, and spatial precision. On the V-STAR benchmark, Open-o3-Video achieves state-of-the-art performance, improving mAM by 14.4% and mLGM by 24.2% over the Qwen2.5-VL baseline, and shows consistent gains across a range of video understanding benchmarks. Beyond accuracy, the grounded reasoning traces produced by Open-o3-Video support confidence-aware test-time scaling, improving answer reliability.

cs.CV↗

arXiv2026

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs

While Multimodal Large Language Models (MLLMs) excel at holistic understanding, they struggle in capturing the dense world with complex scenes, requiring fine-grained analysis of intricate details and object inter-relationships. Region-level MLLMs have been a promising step. However, previous attempts are generally optimized to understand given regions in isolation, neglecting crucial global contexts. To address this, we introduce Grasp Any Region (GAR) for comprehen- sive region-level visual understanding. Empowered by an effective RoI-aligned feature replay technique, GAR supports (1) precise perception by leveraging necessary global contexts, and (2) modeling interactions between multiple prompts. Together, it then naturally achieves (3) advanced compositional reasoning to answer specific free-form questions about any region, shifting the paradigm from passive description to active dialogue. Moreover, we construct GAR-Bench, which not only provides a more accurate evaluation of single-region comprehension, but also, more importantly, measures interactions and complex reasoning across multiple regions. Extensive experiments have demonstrated that GAR-1B not only maintains the state-of-the-art captioning capabilities, e.g., outperforming DAM-3B +4.5 on DLC-Bench, but also excels at modeling relationships between multiple prompts with advanced comprehension capabilities, even surpassing InternVL3-78B on GAR-Bench-VQA. More importantly, our zero-shot GAR-8B even outperforms in-domain VideoRefer-7B on VideoRefer-BenchQ, indicating its strong capabilities can be easily transferred to videos.

cs.CV↗

arXiv2025

RecTok: Reconstruction Distillation along Rectified Flow

Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between dimensionality and generation quality, constraining existing methods to low-dimensional latent spaces. Although recent works have leveraged vision foundation models to enrich the semantics of visual tokenizers and accelerate convergence, high-dimensional tokenizers still underperform their low-dimensional counterparts. In this work, we propose RecTok, which overcomes the limitations of high-dimensional visual tokenizers through two key innovations: flow semantic distillation and reconstruction--alignment distillation. Our key insight is to make the forward flow in flow matching semantically rich, which serves as the training space of diffusion transformers, rather than focusing on the latent space as in previous works. Specifically, our method distills the semantic information in VFMs into the forward flow trajectories in flow matching. And we further enhance the semantics by introducing a masked feature reconstruction loss. Our RecTok achieves superior image reconstruction, generation quality, and discriminative performance. It achieves state-of-the-art results on the gFID-50K under both with and without classifier-free guidance settings, while maintaining a semantically rich latent space structure. Furthermore, as the latent dimensionality increases, we observe consistent improvements. Code and model are available at https://shi-qingyu.github.io/rectok.github.io.

cs.CV↗

arXiv2025

Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation

Recent audio-video generative systems suggest that coupling modalities benefits not only audio-video synchrony but also the video modality itself. We pose a fundamental question: Does audio-video joint denoising training improve video generation, even when we only care about video quality? To study this, we introduce a parameter-efficient Audio-Video Full DiT (AVFullDiT) architecture that leverages pre-trained text-to-video (T2V) and text-to-audio (T2A) modules for joint denoising. We train (i) a T2AV model with AVFullDiT and (ii) a T2V-only counterpart under identical settings. Our results provide the first systematic evidence that audio-video joint denoising can deliver more than synchrony. We observe consistent improvements on challenging subsets featuring large and object contact motions. We hypothesize that predicting audio acts as a privileged signal, encouraging the model to internalize causal relationships between visual events and their acoustic consequences (e.g., collision $\times$ impact sound), which in turn regularizes video dynamics. Our findings suggest that cross-modal co-training is a promising approach to developing stronger, more physically grounded world models. Code and dataset will be made publicly available.

cs.CV↗

arXiv2025

Guiding Visual Autoregressive Models through Spectrum Weakening

Classifier-free guidance (CFG) has become a widely adopted and practical approach for enhancing generation quality and improving condition alignment. Recent studies have explored guidance mechanisms for unconditional generation, yet these approaches remain fundamentally tied to assumptions specific to diffusion models. In this work, we propose a spectrum-weakening framework for visual autoregressive (AR) models. This method works without the need for re-training, specific conditions, or any architectural modifications. It achieves this by constructing a controllable weak model in the spectral domain. We theoretically show that invertible spectral transformations preserve information, while selectively retaining only a subset of spectrum introduces controlled information reduction. Based on this insight, we perform spectrum selection along the channel dimension of internal representations, which avoids the structural constraints imposed by diffusion models. We further introduce two spectrum renormalization strategies that ensures numerical stability during the weakening process. Extensive experiments were conducted on both discrete and continuous AR models, with text or class conditioning. The results demonstrate that our method enables high-quality unconditional generation while maintaining strong prompt alignment for conditional generation.

cs.CV↗

arXiv2025

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxically degrade performance due to error propagation. To systematically analyze this issue, we propose ParaBench, a new benchmark designed to evaluate both text and image output modalities. Our analysis using ParaBench reveals that this performance degradation is strongly correlated with poor alignment between the generated reasoning and the final image. To resolve this, we propose a parallel multimodal diffusion framework, MMaDA-Parallel, that enables continuous, bidirectional interaction between text and images throughout the entire denoising trajectory. MMaDA-Parallel is trained with supervised finetuning and then further optimized by Parallel Reinforcement Learning (ParaRL), a novel strategy that applies semantic rewards along the trajectory to enforce cross-modal consistency. Experiments validate that our model significantly improves cross-modal alignment and semantic consistency, achieving a 6.9\% improvement in Output Alignment on ParaBench compared to the state-of-the-art model, Bagel, establishing a more robust paradigm for thinking-aware image synthesis. Our code is open-sourced at https://github.com/tyfeld/MMaDA-Parallel

cs.CV↗

arXiv2025

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

Recent progress in panoramic image generation has underscored two critical limitations in existing approaches. First, most methods are built upon diffusion models, which are inherently ill-suited for equirectangular projection (ERP) panoramas due to the violation of the identically and independently distributed (i.i.d.) Gaussian noise assumption caused by their spherical mapping. Second, these methods often treat text-conditioned generation (text-to-panorama) and image-conditioned generation (panorama outpainting) as separate tasks, relying on distinct architectures and task-specific data. In this work, we propose a unified framework, Panoramic AutoRegressive model (PAR), which leverages masked autoregressive modeling to address these challenges. PAR avoids the i.i.d. assumption constraint and integrates text and image conditioning into a cohesive architecture, enabling seamless generation across tasks. To address the inherent discontinuity in existing generative models, we introduce circular padding to enhance spatial coherence and propose a consistency alignment strategy to improve generation quality. Extensive experiments demonstrate competitive performance in text-to-image generation and panorama outpainting tasks while showcasing promising scalability and generalization capabilities.

cs.CV↗

arXiv2025

MMaDA: Multimodal Large Diffusion Language Models

We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. The approach is distinguished by three key innovations: (i) MMaDA adopts a unified diffusion architecture with a shared probabilistic formulation and a modality-agnostic design, eliminating the need for modality-specific components. This architecture ensures seamless integration and processing across different data types. (ii) We implement a mixed long chain-of-thought (CoT) fine-tuning strategy that curates a unified CoT format across modalities. By aligning reasoning processes between textual and visual domains, this strategy facilitates cold-start training for the final reinforcement learning (RL) stage, thereby enhancing the model's ability to handle complex tasks from the outset. (iii) We propose UniGRPO, a unified policy-gradient-based RL algorithm specifically tailored for diffusion foundation models. Utilizing diversified reward modeling, UniGRPO unifies post-training across both reasoning and generation tasks, ensuring consistent performance improvements. Experimental results demonstrate that MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation. These achievements highlight MMaDA's effectiveness in bridging the gap between pretraining and post-training within unified diffusion architectures, providing a comprehensive framework for future research and development. We open-source our code and trained models at: https://github.com/Gen-Verse/MMaDA

cs.CV↗