Searcharxiv⌕ Search

arXiv subjects

Xiangyang Luo

Publications and source records attributed to Xiangyang Luo.

At least 19 recordsLinked to original sources
arXiv2026

SingDance: Compositional Zero-Shot Singing-and-Dancing Video Generation with Role-Aware Audio Conditioning

Generating personalized dance videos from a reference image, text prompt, and audio track requires music-conditioned body motion. Singing-and-dancing adds a second requirement: the visible subject must also articulate the vocals. Existing music-conditioned methods focus primarily on choreography, while speech-driven models generally assume that the visible subject produces the input voice, leaving this combined setting largely underexplored. We introduce SingDance, a unified video diffusion framework that formulates controllable vocal articulation as a semantic role: the visible subject is either the source, who produces the vocal signal, or the listener, who receives it from an off-screen performer. Hard-compact routing selects task-relevant speech, music, and role conditions, which are composed through frame-wise joint audio injection; source and listener retain the same speech pathway. Training uses asymmetric supervision: on-screen speaking and curated off-screen conversational-response videos establish role control, while instrumental and song-based dancing-only videos establish music-conditioned body motion. The target Song/Source configuration is never observed during training. At inference, assigning the source role to a song composes separately learned articulation and song-conditioned dance capabilities, enabling compositional zero-shot singing-and-dancing. Experiments demonstrate strong motion--beat alignment and visual fidelity, reliable paired switching of vocal articulation while preserving music-aligned body motion, and highly competitive lip synchronization with substantially fewer generation-time parameters than the strongest speech-driven baseline evaluated.

cs.SD↗
arXiv2026

ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing

Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate operations over fixed inputs. Practical creation unfolds across multiple shots, requiring one model to generate from text, follow a reference, or edit source footage while maintaining shared history. We formalize this setting as interactive multi-shot video creation (IMVC) and introduce ContextMaster, a unified model with a role-aware context representation for these operations. An interactive model must retain access to an expanding history without allowing the context read cost at each denoising step to grow. ContextMaster combines reusable clean context states with fixed budget sparse context routing and uses ConstraintSink to keep task constraints visible. To address the dual challenges of sparse context access and inference with few denoising steps, we propose a two-stage privileged context distillation framework, which transfers full context behavior from a dense teacher through consistency distillation and then refines deployment rollouts with distribution matching. Experiments on the three primitive tasks demonstrate improved task fulfillment and consistency across shots over specialized baselines. User studies further validate flexibly composed workflows, while the model reaches 16 FPS on a single GPU.

cs.CV↗
arXiv2026

Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching

Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inference. Existing mitigation strategies typically rely on static constraints or external heuristics. In this work, we propose that exposure bias itself inherently contains dynamic signals that can guide its own rectification. To leverage this, we introduce DEFAR (DirEctional-Frequency Adaptive Rectification). This framework simulates the single-step inference process during training to identify exposure bias. It utilizes directional and frequency-adaptive feedback signals from the bias itself to enhance the model's bias tolerance. It consists of two key components: (1) Anti-Drift Rectification (ADR). ADR treats inference-time drift as a signal to learn the direction to steer deviated states back toward the target. ADR endows the model with intrinsic active self-rectification capabilities; (2) Frequency Compensation (FC). Empirically, we observe that accumulated bias often stems from a lack of low-frequency components in high-noise stages, and exposure bias carries the missing frequency. FC leverages the bias itself as a self-feedback weighting factor to reinforce the missing frequency components. Experiments on CIFAR-10, CelebA-64, and ImageNet-256/512 show that DEFAR outperforms prior baselines and further demonstrates favorable scalability, compatibility, and inference robustness.

cs.CV↗
arXiv2026

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

Raw multimodal streams are abundant but noisy, redundant, and unaligned with any particular training objective. Turning them into supervision today means either brittle heuristics or repeatedly querying a proprietary vision-language model, a cost that recurs with every new sample. We ask whether this conversion can instead be learned once and reused, and formalise intent-conditioned Data Tailoring: given a raw stream and a high-level intent, a model must return schema-aligned, evidence-grounded training instances. Training DataClaw0 at 4B, 9B and 27B, we find that whether five heterogeneous domains should share one model depends on capacity. A jointly trained model is worse than per-domain experts at the two smaller scales and better at the largest, placing the crossover near 18B parameters. Matched-data comparisons, in which the joint model sees exactly the same data per domain as that domain's expert, attribute the reversal to cross-domain transfer rather than to data volume: it gains most where a domain is data-poor, and recovers 59\% of in-domain performance on domains withheld from training entirely. Downstream post-training reproduces this ordering on GUI navigation, action video generation and spatio-temporal VQA, and the joint configuration is also the cheaper to deploy, serving one model instead of five. Github: https://github.com/vancyland/DataClaw0

cs.LG↗
arXiv2026

TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift. In this paper, we propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation. TetherCache organizes the cache into sink, memory, and recent regions, and introduces two complementary mechanisms. First, GRAB (Gated Recall with Attention-Diversity Balancing) selects long-range memory frames using a gated score that combines attention-based relevance with temporal diversity, preserving informative yet diverse historical context under a fixed cache budget. Second, TAME (Trusted Alignment via Memory Editing) lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution, reducing the pollution caused by drifted historical features. Built on Self-Forcing, TetherCache consistently improves long-video generation quality on VBench-Long across 30s, 60s, and 240s settings. In particular, for 240s generation, it substantially improves overall and semantic scores while reducing quality drift from 7.84 to 1.33, demonstrating its effectiveness for stable long-horizon autoregressive video diffusion.

cs.CV↗
arXiv2026

When Vision Misleads, Let Location Speak: A Worldwide Image Geo-Localization Method via Location Attention Mechanism and Large Multimodal Models

Worldwide image geo-localization aims to determine the capture location of an image on a global scale. Existing methods often mislocalize images by matching them to visually similar scenes from different geographic regions, which limits reliability in practical applications. To address this issue, we propose TransGeoCLIP, a novel retrieval-based framework that integrates a location attention mechanism and large multimodal models (LMMs). Using the Transformer encoder with location attention to encode GPS coordinates, TransGeoCLIP can effectively distinguish geographic features among visually similar images. The framework consists of two stages: 1) Retrieval database construction, which employs Transformers equipped with location attention mechanisms to encode labeled GPS coordinates and enhance location semantics, subsequently enables joint image-text-GPS embedding through CLIP; 2) Retrieval-augmented inference, which leverages LMMs to infer the final image location prediction from retrieved database results. Extensive experimental results on diverse datasets, including IM2GPS, IM2GPS3k, YFCC4k, and YFCC26k, demonstrate that TransGeoCLIP significantly enhances localization performance for visually similar images. Particularly, street-level localization accuracy (within 1 km error) is substantially improved, surpassing state-of-the-art methods by 1.5%, 1.07%, 7.18%, and 9.75% on these benchmarks, respectively.

cs.CV↗
arXiv2026

IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation

With the rapid advancement of diffusion models, talking face generation has made remarkable progress. However, existing diffusion-based methods still require task-specific fine-tuning and large-scale audiovisual datasets, resulting in high computational costs that hinder scalability and accessibility of diffusion-based approaches across the research community. To address this, we propose a finetuning-free paradigm that directly performs talking face generation using the pretrained weights of Stable Diffusion and IP-Adapter. This backbone leverages the visual embedding capability of IP-Adapter to mine lip-related semantics from the pretrained Stable Diffusion. To address the challenges of identity drift, synchronization errors, and temporal instability, we also design three trainable-parameterfree components: (1) the Structurist, which explicitly disentangles and reassembles lip and appearance features to mitigate identity drift and appearance distortion; (2) the Structure Controller, which adaptively refines embeddings based on quasi-monotonic motion trends for precise lip synchronization; and (3) the Noise Sensor, which introduces Gaussian prior to detect and suppress flicker and jitter artifacts and enhance temporal consistency. Experimental results show that our method outperforms existing SOTA approaches in both lip-sync accuracy (at least 0.16 gain in PCLD) and visual fidelity (at least 0.7 improvement in FID), establishing a novel fine-tuning-free diffusion framework for talking face generation.

cs.CV↗
arXiv2026

DualGeo: A Dual-View Framework for Worldwide Image Geo-localization

Worldwide image geo-localization aims to infer the geographic location of an image captured anywhere on Earth, spanning street, city, regional, national, and continental scales. Existing methods rely on visual features that are sensitive to environmental variations (e.g., lighting, season, and weather) and lack effective post-processing to filter outlier candidates, limiting localization accuracy. To address these limitations, we propose DualGeo, a two-stage framework for worldwide image geo-localization. First, it establishes a geo-representational foundation by fusing image and semantic segmentation features via bidirectional cross-attention. The fused features are then aligned with GPS coordinates through dual-view contrastive learning to build a global retrieval database. Second, it performs geo-cognitive refinement by re-ranking retrieved candidates using geographic clustering. It then feeds them into large multimodal models (LMMs) for final coordinate prediction. Experiments on IM2GPS, IM2GPS3k, and YFCC4k show that DualGeo outperforms state-of-the-art methods, improving street-level (<1 km) and city-level (<25 km) localization accuracy by 3.6%-16.58% and 1.29%-8.77%, respectively. Our code and datasets are available : https://github.com/CJ310177/DualGeo.

cs.CV↗
arXiv2026

CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation

Synthesizing human--object interaction (HOI) videos has broad practical value in e-commerce, digital advertising, and virtual marketing. However, current diffusion models, despite their photorealistic rendering capability, still frequently fail on (i) the structural stability of sensitive regions such as hands and faces and (ii) physically plausible contact (e.g., avoiding hand--object interpenetration). We present CoInteract, an end-to-end framework for HOI video synthesis conditioned on a person reference image, a product reference image, text prompts, and speech audio. CoInteract introduces two complementary designs embedded into a Diffusion Transformer (DiT) backbone. First, we propose a Human-Aware Mixture-of-Experts (MoE) that routes tokens to lightweight, region-specialized experts via spatially supervised routing, improving fine-grained structural fidelity with minimal parameter overhead. Second, we propose Spatially-Structured Co-Generation, a dual-stream training paradigm that jointly models an RGB appearance stream and an auxiliary HOI structure stream to inject interaction geometry priors. During training, the HOI stream attends to RGB tokens and its supervision regularizes shared backbone weights; at inference, the HOI branch is removed for zero-overhead RGB generation. Experimental results demonstrate that CoInteract significantly outperforms existing methods in structural stability, logical consistency, and interaction realism.

cs.CV↗
arXiv2026

Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training

Recent advances in video generation models have achieved impressive results. However, these models heavily rely on the use of high-quality data that combines both high visual quality and high motion quality. In this paper, we identify a key challenge in video data curation: the Motion-Vision Quality Dilemma. We discovered that visual quality and motion intensity inherently exhibit a negative correlation, making it hard to obtain golden data that excels in both aspects. To address this challenge, we first examine the hierarchical learning dynamics of video diffusion models and conduct gradient-based analysis on quality-degraded samples. We discover that quality-imbalanced data can produce gradients similar to golden data at appropriate timesteps. Based on this, we introduce the novel concept of Timestep selection in Training Process. We propose Timestep-aware Quality Decoupling (TQD), which modifies the data sampling distribution to better match the model's learning process. For certain types of data, the sampling distribution is skewed toward higher timesteps for motion-rich data, while high visual quality data is more likely to be sampled during lower timesteps. Through extensive experiments, we demonstrate that TQD enables training exclusively on separated imbalanced data to achieve performance surpassing conventional training with better data, challenging the necessity of perfect data in video generation. Moreover, our method also boosts model performance when trained on high-quality data, showcasing its effectiveness across different data scenarios.

cs.CV↗
arXiv2026

AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models

Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and static sampling strategies. These methods treat all prompts and denoising steps uniformly, ignoring substantial variations in sample learning value as well as the dynamic nature of critical exploration moments. To address this issue, we conduct a detailed analysis of the internal attention dynamics during GRPO training and uncover a key insight: attention entropy can serve as a powerful dual-signal proxy. First, across different samples, the relative change in attention entropy ({\Delta}Entropy), which reflects the divergence between the current policy and the base policy, acts as a robust indicator of sample learning value. Second, during the denoising process, the peaks of absolute attention entropy (Entropy(t)), which quantify attention dispersion, effectively identify critical timesteps where high-value exploration occurs. Building on this observation, we propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy. At the global level, AEGPO uses {\Delta}Entropy to dynamically allocate rollout budgets, prioritizing prompts with higher learning value. At the local level, it exploits the peaks of Entropy(t) to guide exploration selectively at critical high-dispersion timesteps rather than uniformly across all denoising steps. By focusing computation on the most informative samples and the most critical moments, AEGPO enables more efficient and effective policy optimization. Experiments on text-to-image generation tasks demonstrate that AEGPO significantly accelerates convergence and achieves superior alignment performance compared to standard GRPO variants.

cs.LG↗
arXiv2026

CIEC: Coupling Implicit and Explicit Cues for Multimodal Weakly Supervised Manipulation Localization

To mitigate the threat of misinformation, multimodal manipulation localization has garnered growing attention. Consider that current methods rely on costly and time-consuming fine-grained annotations, such as patch/token-level annotations. This paper proposes a novel framework named Coupling Implicit and Explicit Cues (CIEC), which aims to achieve multimodal weakly-supervised manipulation localization for image-text pairs utilizing only coarse-grained image/sentence-level annotations. It comprises two branches, image-based and text-based weakly-supervised localization. For the former, we devise the Textual-guidance Refine Patch Selection (TRPS) module. It integrates forgery cues from both visual and textual perspectives to lock onto suspicious regions aided by spatial priors. Followed by the background silencing and spatial contrast constraints to suppress interference from irrelevant areas. For the latter, we devise the Visual-deviation Calibrated Token Grounding (VCTG) module. It focuses on meaningful content words and leverages relative visual bias to assist token localization. Followed by the asymmetric sparse and semantic consistency constraints to mitigate label noise and ensure reliability. Extensive experiments demonstrate the effectiveness of our CIEC, yielding results comparable to fully supervised methods on several evaluation metrics.

cs.CV↗
arXiv2026

Lossless Copyright Protection via Intrinsic Model Fingerprinting

The exceptional performance of diffusion models establishes them as high-value intellectual property but exposes them to unauthorized replication. Existing protection methods either modify the model to embed watermarks, which impairs performance, or extract model fingerprints by manipulating the denoising process, rendering them incompatible with black-box APIs. In this paper, we propose TrajPrint, a completely lossless and training-free framework that verifies model copyright by extracting unique manifold fingerprints formed during deterministic generation. Specifically, we first utilize a watermarked image as an anchor and exactly trace the path back to its trajectory origin, effectively locking the model fingerprint mapped by this path. Subsequently, we implement a joint optimization strategy that employs dual-end anchoring to synthesize a specific fingerprint noise, which strictly adheres to the target manifold for robust watermark recovery. As input, it enables the protected target model to recover the watermarked image, while failing on non-target models. Finally, we achieved verification via atomic inference and statistical hypothesis testing. Extensive experiments demonstrate that TrajPrint achieves lossless verification in black-box API scenarios with superior robustness against model modifications.

cs.CR↗
arXiv2026

MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models

Deepfake detection is a widely researched topic that is crucial for combating the spread of malicious content, with existing methods mainly modeling the problem as classification or spatial localization. The rapid advancements in generative models impose new demands on Deepfake detection. In this paper, we propose multimodal alignment and reinforcement for explainable Deepfake detection via vision-language models, termed MARE, which aims to enhance the accuracy and reliability of Vision-Language Models (VLMs) in Deepfake detection and reasoning. Specifically, MARE designs comprehensive reward functions, incorporating reinforcement learning from human feedback (RLHF), to incentivize the generation of text-spatially aligned reasoning content that adheres to human preferences. Besides, MARE introduces a forgery disentanglement module to capture intrinsic forgery traces from high-level facial semantics, thereby improving its authenticity detection capability. We conduct thorough evaluations on the reasoning content generated by MARE. Both quantitative and qualitative experimental results demonstrate that MARE achieves state-of-the-art performance in terms of accuracy and reliability.

cs.CV↗
arXiv2026

Safeguarding Facial Identity against Diffusion-based Face Swapping via Cascading Pathway Disruption

The rapid evolution of diffusion models has democratized face swapping but also raises concerns about privacy and identity security. Existing proactive defenses, often adapted from image editing attacks, prove ineffective in this context. We attribute this failure to an oversight of the structural resilience and the unique static conditional guidance mechanism inherent in face swapping systems. To address this, we propose VoidFace, a systemic defense method that views face swapping as a coupled identity pathway. By injecting perturbations at critical bottlenecks, VoidFace induces cascading disruption throughout the pipeline. Specifically, we first introduce localization disruption and identity erasure to degrade physical regression and semantic embeddings, thereby impairing the accurate modeling of the source face. We then intervene in the generative domain by decoupling attention mechanisms to sever identity injection, and corrupting intermediate diffusion features to prevent the reconstruction of source identity. To ensure visual imperceptibility, we perform adversarial search in the latent manifold, guided by a perceptual adaptive strategy to balance attack potency with image quality. Extensive experiments show that VoidFace outperforms existing defenses across various diffusion-based swapping models, while producing adversarial faces with superior visual quality.

cs.CV↗
arXiv2025

FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion

Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consistency across shots and flexibly generating videos of arbitrary length and shot count. To address these limitations, we introduce \textbf{FilmWeaver}, a novel framework designed to generate consistent, multi-shot videos of arbitrary length. First, it employs an autoregressive diffusion paradigm to achieve arbitrary-length video generation. To address the challenge of consistency, our key insight is to decouple the problem into inter-shot consistency and intra-shot coherence. We achieve this through a dual-level cache mechanism: a shot memory caches keyframes from preceding shots to maintain character and scene identity, while a temporal memory retains a history of frames from the current shot to ensure smooth, continuous motion. The proposed framework allows for flexible, multi-round user interaction to create multi-shot videos. Furthermore, due to this decoupled design, our method demonstrates high versatility by supporting downstream tasks such as multi-concept injection and video extension. To facilitate the training of our consistency-aware method, we also developed a comprehensive pipeline to construct a high-quality multi-shot video dataset. Extensive experimental results demonstrate that our method surpasses existing approaches on metrics for both consistency and aesthetic quality, opening up new possibilities for creating more consistent, controllable, and narrative-driven video content. Project Page: https://filmweaver.github.io

cs.CV↗
arXiv2025

ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching

Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model lacks generalization to biased inputs during training, and (2) insufficient low-frequency content captured during early denoising, leading to accumulated bias. Based on these insights, we propose ReflexFlow, a simple and effective reflexive refinement of the Flow Matching learning objective that dynamically corrects exposure bias. ReflexFlow consists of two components: (1) Anti-Drift Rectification (ADR), which reflexively adjusts prediction targets for biased inputs utilizing a redesigned loss under training-time scheduled sampling; and (2) Frequency Compensation (FC), which reflects on missing low-frequency components and compensates them by reweighting the loss using exposure bias. ReflexFlow is model-agnostic, compatible with all Flow Matching frameworks, and improves generation quality across datasets. Experiments on CIFAR-10, CelebA-64, and ImageNet-256 show that ReflexFlow outperforms prior approaches in mitigating exposure bias, achieving a 35.65% reduction in FID on CelebA-64.

cs.CV↗
arXiv2025

LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis

LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention. However, existing methods have notable limitations: many methods do not incorporate target-domain data, while gradient-based methods exploit data only at a shallow level by relying on one-step gradient decomposition. In this paper, we establish a theoretical framework for data-aware LoRA initialization. Starting from minimizing the expectation of the parameter discrepancy between the fine-tuned and target models, we derive an optimization problem with two components: a bias term, which is related to the parameter distance between the fine-tuned and target models, and is approximated using a Fisher-gradient formulation to preserve anisotropy; and a variance term, which accounts for the uncertainty introduced by sampling stochasticity through the Fisher information. Solving this problem yields an optimal initialization strategy for LoRA, based on which we develop an efficient algorithm, LoRA-DA. Empirical results across multiple benchmarks demonstrate that LoRA-DA consistently improves final accuracy over existing initialization methods. Additional studies show faster, more stable convergence, robustness across ranks, and only a small initialization overhead for LoRA-DA. The source code is available at https://github.com/zqy0126/LoRA-DA.

cs.LG↗