arXiv subjects

Jinchao Zhang

Publications and source records attributed to Jinchao Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance

Classifier-Free Guidance (CFG) serves as the de facto control mechanism for conditional diffusion, yet high guidance scales notoriously induce oversaturation, texture artifacts, and structural collapse. We attribute this failure to a geometric mismatch: standard CFG performs Euclidean extrapolation in ambient space, inadvertently driving sampling trajectories off the high-density data manifold. To resolve this, we present Manifold-Optimal Guidance (MOG), a framework that reformulates guidance as a local optimal control problem. MOG yields a closed-form, geometry-aware Riemannian update that corrects off-manifold drift without requiring retraining. Leveraging this perspective, we further introduce Auto-MOG, a dynamic energy-balancing schedule that adaptively calibrates guidance strength, effectively eliminating the need for manual hyperparameter tuning. Extensive validation demonstrates that MOG yields superior fidelity and alignment compared to baselines, with virtually no added computational overhead.

cs.CV↗

arXiv2026

Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity

Recent advances in text-to-image (T2I) generation have greatly improved visual quality, yet producing images that appear visually authentic to real-world photography remains challenging. This is partly due to biases in existing evaluation paradigms: human ratings and preference-trained metrics often favor visually vivid images with exaggerated saturation and contrast, which make generations often too vivid to be real even when prompted for realistic-style images. To address this issue, we present Color Fidelity Dataset (CFD) and Color Fidelity Metric (CFM) for objective evaluation of color fidelity in realistic-style generations. CFD contains over 1.3M real and synthetic images with ordered levels of color realism, while CFM employs a multimodal encoder to learn perceptual color fidelity. In addition, we propose a training-free Color Fidelity Refinement (CFR) that adaptively modulates spatial-temporal guidance scale in generation, thereby enhancing color authenticity. Together, CFD supports CFM for assessment, whose learned attention further guides CFR to refine T2I fidelity, forming a progressive framework for assessing and improving color fidelity in realistic-style T2I generation. The dataset and code are available at https://github.com/ZhengyaoFang/CFM.

cs.CV↗

arXiv2026

Tutti: Expressive Multi-Singer Synthesis via Structure-Level Timbre Control and Vocal Texture Modeling

While existing Singing Voice Synthesis systems achieve high-fidelity solo performances, they are constrained by global timbre control, failing to address dynamic multi-singer arrangement and vocal texture within a single song. To address this, we propose Tutti, a unified framework designed for structured multi-singer generation. Specifically, we introduce a Structure-Aware Singer Prompt to enable flexible singer scheduling evolving with musical structure, and propose Complementary Texture Learning via Condition-Guided VAE to capture implicit acoustic textures (e.g., spatial reverberation and spectral fusion) that are complementary to explicit controls. Experiments demonstrate that Tutti excels in precise multi-singer scheduling and significantly enhances the acoustic realism of choral generation, offering a novel paradigm for complex multi-singer arrangement. Audio samples are available at https://annoauth123-ctrl.github.io/Tutii_Demo/.

cs.SD↗

arXiv2026

Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection

Detecting deepfakes has become increasingly challenging as forgery faces synthesized by AI-generated methods, particularly diffusion models, achieve unprecedented quality and resolution. Existing forgery detection approaches relying on spatial and frequency features demonstrate limited efficacy against high-quality, entirely synthesized forgeries. In this paper, we propose a novel detection method grounded in the observation that facial attributes governed by complex physical laws and multiple parameters are inherently difficult to replicate. Specifically, we focus on illumination, particularly the specular reflection component in the Phong illumination model, which poses the greatest replication challenge due to its parametric complexity and nonlinear formulation. We introduce a fast and accurate face texture estimation method based on Retinex theory to enable precise specular reflection separation. Furthermore, drawing from the mathematical formulation of specular reflection, we posit that forgery evidence manifests not only in the specular reflection itself but also in its relationship with corresponding face texture and direct light. To address this issue, we design the Specular-Reflection-Inconsistency-Network (SRI-Net), incorporating a two-stage cross-attention mechanism to capture these correlations and integrate specular reflection related features with image features for robust forgery detection. Experimental results demonstrate that our method achieves superior performance on both traditional deepfake datasets and generative deepfake datasets, particularly those containing diffusion-generated forgery faces.

cs.CV↗

arXiv2026

StyleDecoupler: Generalizable Artistic Style Disentanglement

Representing artistic style is challenging due to its deep entanglement with semantic content. We propose StyleDecoupler, an information-theoretic framework that leverages a key insight: multi-modal vision models encode both style and content, while uni-modal models suppress style to focus on content-invariant features. By using uni-modal representations as content-only references, we isolate pure style features from multi-modal embeddings through mutual information minimization. StyleDecoupler operates as a plug-and-play module on frozen Vision-Language Models without fine-tuning. We also introduce WeART, a large-scale benchmark of 280K artworks across 152 styles and 1,556 artists. Experiments show state-of-the-art performance on style retrieval across WeART and WikiART, while enabling applications like style relationship mapping and generative model evaluation. We release our method and dataset at this url.

cs.CV↗

arXiv2025

RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation

Recently, significant advancements have been achieved in video generation technology, but applying it to resource-constrained downstream tasks like multi-frame animated sticker generation (ASG) characterized by low frame rates, abstract semantics, and long tail frame length distribution-remains challenging. Parameter-efficient fine-tuning (PEFT) techniques (e.g., Adapter, LoRA) for large pre-trained models suffer from insufficient fitting ability and source-domain knowledge interference. In this paper, we propose Resource-Efficient Dual-Mask Training Framework (RDTF), a dedicated solution for multi-frame ASG task under resource constraints. We argue that training a compact model from scratch with million-level samples outperforms PEFT on large models, with RDTF realizing this via three core designs: 1) a Discrete Frame Generation Network (DFGN) optimized for low-frame-rate ASG, ensuring parameter efficiency; 2) a dual-mask based data utilization strategy to enhance the availability and diversity of limited data; 3) a difficulty-adaptive curriculum learning method that decomposes sample entropy into static and adaptive components, enabling easy-to-difficult training convergence. To provide high-quality data support for RDTFs training from scratch, we construct VSD2M-a million-level multi-modal animated sticker dataset with rich annotations (static and animated stickers, action-focused text descriptions)-filling the gap of dedicated animated data for ASG task. Experiments demonstrate that RDTF is quantitatively and qualitatively superior to state-of-the-art PEFT methods (e.g., I2V-Adapter, SimDA) on ASG tasks, verifying the feasibility of our framework under resource constraints.

cs.MM↗

arXiv2025

F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model

Traditional dialogue retrieval aims to select the most appropriate utterance or image from recent dialogue history. However, they often fail to meet users' actual needs for revisiting semantically coherent content scattered across long-form conversations. To fill this gap, we define the Fine-grained Fragment Retrieval (FFR) task, requiring models to locate query-relevant fragments, comprising both utterances and images, from multimodal long-form dialogues. As a foundation for FFR, we construct MLDR, the longest-turn multimodal dialogue retrieval dataset to date, averaging 25.45 turns per dialogue, with each naturally spanning three distinct topics. To evaluate generalization in real-world scenarios, we curate and annotate a WeChat-based test set comprising real-world multimodal dialogues with an average of 75.38 turns. Building on these resources, we explore existing generation-based Vision-Language Models (VLMs) on FFR and observe that they often retrieve incoherent utterance-image fragments. While optimized for generating responses from visual-textual inputs, these models lack explicit supervision to ensure semantic coherence within retrieved fragments. To this end, we propose F2RVLM, a generative retrieval model trained in a two-stage paradigm: (1) supervised fine-tuning to inject fragment-level retrieval knowledge, and (2) GRPO-based reinforcement learning with multi-objective rewards promoting semantic precision, relevance, and contextual coherence. To handle varying intra-fragment complexity, from locally dense to sparsely distributed, we introduce difficulty-aware curriculum sampling that ranks training instances by model-predicted difficulty and gradually exposes the model to harder samples. This boosts reasoning ability in long, multi-turn contexts. F2RVLM outperforms popular VLMs in both in-domain and real-domain settings, demonstrating superior retrieval performance.

cs.CV↗

arXiv2025

A Synthetic-to-Real Dehazing Method based on Domain Unification

Due to distribution shift, the performance of deep learning-based method for image dehazing is adversely affected when applied to real-world hazy images. In this paper, we find that such deviation in dehazing task between real and synthetic domains may come from the imperfect collection of clean data. Owing to the complexity of the scene and the effect of depth, the collected clean data cannot strictly meet the ideal conditions, which makes the atmospheric physics model in the real domain inconsistent with that in the synthetic domain. For this reason, we come up with a synthetic-to-real dehazing method based on domain unification, which attempts to unify the relationship between the real and synthetic domain, thus to let the dehazing model more in line with the actual situation. Extensive experiments qualitatively and quantitatively demonstrate that the proposed dehazing method significantly outperforms state-of-the-art methods on real-world images.

eess.IV↗

arXiv2025

Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models

Large Vision-Language Models (LVLMs) usually generate texts which satisfy context coherence but don't match the visual input. Such a hallucination issue hinders LVLMs' applicability in the real world. The key to solving hallucination in LVLM is to make the text generation rely more on the visual content. Most previous works choose to enhance/adjust the features/output of a specific modality (i.e., visual or textual) to alleviate hallucinations in LVLM, which do not explicitly or systematically enhance the visual reliance. In this paper, we comprehensively investigate the factors which may degenerate the visual reliance in text generation of LVLM from a Bayesian perspective. Based on our observations, we propose to mitigate hallucination in LVLM from three aspects. Firstly, we observe that not all visual tokens are informative in generating meaningful texts. We propose to evaluate and remove redundant visual tokens to avoid their disturbance. Secondly, LVLM may encode inappropriate prior information, making it lean toward generating unexpected words. We propose a simple yet effective way to rectify the prior from a Bayesian perspective. Thirdly, we observe that starting from certain steps, the posterior of next-token prediction conditioned on visual tokens may collapse to a prior distribution which does not depend on any informative visual tokens at all. Thus, we propose to stop further text generation to avoid hallucination. Extensive experiments on three benchmarks including POPE, CHAIR, and MME demonstrate that our method can consistently mitigate the hallucination issue of LVLM and performs favorably against previous state-of-the-arts.

cs.CV↗

arXiv2025

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets

Vision-language models (VLMs) often struggle with compositional reasoning due to insufficient high-quality image-text data. To tackle this challenge, we propose a novel block-based diffusion approach that automatically generates counterfactual datasets without manual annotation. Our method utilizes large language models to identify entities and their spatial relationships. It then independently generates image blocks as "puzzle pieces" coherently arranged according to specified compositional rules. This process creates diverse, high-fidelity counterfactual image-text pairs with precisely controlled variations. In addition, we introduce a specialized loss function that differentiates inter-set from intra-set samples, enhancing training efficiency and reducing the need for negative samples. Experiments demonstrate that fine-tuning VLMs with our counterfactual datasets significantly improves visual reasoning performance. Our approach achieves state-of-the-art results across multiple benchmarks while using substantially less training data than existing methods.

cs.CV↗

arXiv2025

From Imitation to Innovation: The Emergence of AI Unique Artistic Styles and the Challenge of Copyright Protection

Current legal frameworks consider AI-generated works eligible for copyright protection when they meet originality requirements and involve substantial human intellectual input. However, systematic legal standards and reliable evaluation methods for AI art copyrights are lacking. Through comprehensive analysis of legal precedents, we establish three essential criteria for determining distinctive artistic style: stylistic consistency, creative uniqueness, and expressive accuracy. To address these challenges, we introduce ArtBulb, an interpretable and quantifiable framework for AI art copyright judgment that combines a novel style description-based multimodal clustering method with multimodal large language models (MLLMs). We also present AICD, the first benchmark dataset for AI art copyright annotated by artists and legal experts. Experimental results demonstrate that ArtBulb outperforms existing models in both quantitative and qualitative evaluations. Our work aims to bridge the gap between the legal and technological communities and bring greater attention to the societal issue of AI art copyrights.

cs.CV↗

arXiv2025

Uneven Event Modeling for Partially Relevant Video Retrieval

Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments, wherein event modeling is crucial for partitioning the video into smaller temporal events that partially correspond to the text. Previous methods typically segment videos into a fixed number of equal-length clips, resulting in ambiguous event boundaries. Additionally, they rely on mean pooling to compute event representations, inevitably introducing undesired misalignment. To address these, we propose an Uneven Event Modeling (UEM) framework for PRVR. We first introduce the Progressive-Grouped Video Segmentation (PGVS) module, to iteratively formulate events in light of both temporal dependencies and semantic similarity between consecutive frames, enabling clear event boundaries. Furthermore, we also propose the Context-Aware Event Refinement (CAER) module to refine the event representation conditioned the text's cross-attention. This enables event representations to focus on the most relevant frames for a given text, facilitating more precise text-video alignment. Extensive experiments demonstrate that our method achieves state-of-the-art performance on two PRVR benchmarks. Code is available at https://github.com/Sasa77777779/UEM.git.

cs.CV↗

arXiv2025

Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark

Multimodal language analysis is a rapidly evolving field that leverages multiple modalities to enhance the understanding of high-level semantics underlying human conversational utterances. Despite its significance, little research has investigated the capability of multimodal large language models (MLLMs) to comprehend cognitive-level semantics. In this paper, we introduce MMLA, a comprehensive benchmark specifically designed to address this gap. MMLA comprises over 61K multimodal utterances drawn from both staged and real-world scenarios, covering six core dimensions of multimodal semantics: intent, emotion, dialogue act, sentiment, speaking style, and communication behavior. We evaluate eight mainstream branches of LLMs and MLLMs using three methods: zero-shot inference, supervised fine-tuning, and instruction tuning. Extensive experiments reveal that even fine-tuned models achieve only about 60%~70% accuracy, underscoring the limitations of current MLLMs in understanding complex human language. We believe that MMLA will serve as a solid foundation for exploring the potential of large language models in multimodal language analysis and provide valuable resources to advance this field. The datasets and code are open-sourced at https://github.com/thuiar/MMLA.

cs.CL↗

arXiv2025

VSD2M: A Large-scale Vision-language Sticker Dataset for Multi-frame Animated Sticker Generation

As a common form of communication in social media,stickers win users' love in the internet scenarios, for their ability to convey emotions in a vivid, cute, and interesting way. People prefer to get an appropriate sticker through retrieval rather than creation for the reason that creating a sticker is time-consuming and relies on rule-based creative tools with limited capabilities. Nowadays, advanced text-to-video algorithms have spawned numerous general video generation systems that allow users to customize high-quality, photo-realistic videos by only providing simple text prompts. However, creating customized animated stickers, which have lower frame rates and more abstract semantics than videos, is greatly hindered by difficulties in data acquisition and incomplete benchmarks. To facilitate the exploration of researchers in animated sticker generation (ASG) field, we firstly construct the currently largest vision-language sticker dataset named VSD2M at a two-million scale that contains static and animated stickers. Secondly, to improve the performance of traditional video generation methods on ASG tasks with discrete characteristics, we propose a Spatial Temporal Interaction (STI) layer that utilizes semantic interaction and detail preservation to address the issue of insufficient information utilization. Moreover, we train baselines with several video generation methods (e.g., transformer-based, diffusion-based methods) on VSD2M and conduct a detailed analysis to establish systemic supervision on ASG task. To the best of our knowledge, this is the most comprehensive large-scale benchmark for multi-frame animated sticker generation, and we hope this work can provide valuable inspiration for other scholars in intelligent creation.

cs.HC↗

arXiv2025

WalkVLM:Aid Visually Impaired People Walking by Vision Language Model

Approximately 200 million individuals around the world suffer from varying degrees of visual impairment, making it crucial to leverage AI technology to offer walking assistance for these people. With the recent progress of vision-language models (VLMs), applying VLMs to offer walking guidance has become popular. However, the existing methods of walking guidance are mainly based on self-curated question-answering datasets that are not publicly accessible, without a standardized benchmark for training or evaluation. Moreover, walking assistance often requires real-time streaming video analysis and the generation of concise yet informative reminders, making VLMs struggle due to excessive responses and low efficiency in inferences. In this paper, we introduce the first large-scale dataset dedicated to walking assistance, comprising 12,000 video-annotation pairs, to provide a unified benchmark for training and evaluating systems to help visually-impaired individuals walk. Furthermore, a WalkVLM model is proposed, which employs chain of thought for hierarchical planning to generate concise but informative reminders and utilizes temporal-aware adaptive prediction to reduce the temporal redundancy of reminders. Finally, we have established a solid benchmark for blind walking task and verified the advantages of WalkVLM in stream video processing for this task compared to other VLMs. Our dataset and code are available at https://walkvlm2024.github.io.

cs.CV↗

arXiv2025

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking

The rise of Large Language Models (LLMs) has led to significant applications but also introduced serious security threats, particularly from jailbreak attacks that manipulate output generation. These attacks utilize prompt engineering and logit manipulation to steer models toward harmful content, prompting LLM providers to implement filtering and safety alignment strategies. We investigate LLMs' safety mechanisms and their recent applications, revealing a new threat model targeting structured output interfaces, which enable attackers to manipulate the inner logit during LLM generation, requiring only API access permissions. To demonstrate this threat model, we introduce a black-box attack framework called AttackPrefixTree (APT). APT exploits structured output interfaces to dynamically construct attack patterns. By leveraging prefixes of models' safety refusal response and latent harmful outputs, APT effectively bypasses safety measures. Experiments on benchmark datasets indicate that this approach achieves higher attack success rate than existing methods. This work highlights the urgent need for LLM providers to enhance security protocols to address vulnerabilities arising from the interaction between safety patterns and structured outputs.

cs.CR↗

arXiv2025

Control-CLIP: Decoupling Category and Style Guidance in CLIP for Specific-Domain Generation

Text-to-image diffusion models have shown remarkable capabilities of generating high-quality images closely aligned with textual inputs. However, the effectiveness of text guidance heavily relies on the CLIP text encoder, which is trained to pay more attention to general content but struggles to capture semantics in specific domains like styles. As a result, generation models tend to fail on prompts like "a photo of a cat in Pokemon style" in terms of simply producing images depicting "a photo of a cat". To fill this gap, we propose Control-CLIP, a novel decoupled CLIP fine-tuning framework that enables the CLIP model to learn the meaning of category and style in a complement manner. With specially designed fine-tuning tasks on minimal data and a modified cross-attention mechanism, Control-CLIP can precisely guide the diffusion model to a specific domain. Moreover, the parameters of the diffusion model remain unchanged at all, preserving the original generation performance and diversity. Experiments across multiple domains confirm the effectiveness of our approach, particularly highlighting its robust plug-and-play capability in generating content with various specific styles.

cs.CV↗

arXiv2025

Semantic to Structure: Learning Structural Representations for Infringement Detection

Structural information in images is crucial for aesthetic assessment, and it is widely recognized in the artistic field that imitating the structure of other works significantly infringes on creators' rights. The advancement of diffusion models has led to AI-generated content imitating artists' structural creations, yet effective detection methods are still lacking. In this paper, we define this phenomenon as "structural infringement" and propose a corresponding detection method. Additionally, we develop quantitative metrics and create manually annotated datasets for evaluation: the SIA dataset of synthesized data, and the SIR dataset of real data. Due to the current lack of datasets for structural infringement detection, we propose a new data synthesis strategy based on diffusion models and LLM, successfully training a structural infringement detection model. Experimental results show that our method can successfully detect structural infringements and achieve notable improvements on annotated test sets.

cs.CV↗