AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer

Existing video-to-audio (V2A) generation methods predominantly rely on text prompts alongside visual information to synthesize audio. However, two critical bottlenecks persist: semantic granularity gaps in training data, such as conflating acoustically distinct sounds under coarse labels, and textual ambiguity in describing micro-acoustic features. These bottlenecks make it difficult to perform fine-grained sound synthesis using text-controlled modes. To address these limitations, we propose AC-Foley, an audio-conditioned V2A model that directly leverages reference audio to achieve precise and fine-grained control over generated sounds. This approach enables fine-grained sound synthesis, timbre transfer, zero-shot sound generation, and improved audio quality. By directly conditioning on audio signals, our approach bypasses the semantic ambiguities of text descriptions while enabling precise manipulation of acoustic attributes. Empirically, AC-Foley achieves state-of-the-art performance for Foley generation when conditioned on reference audio, while remaining competitive with state-of-the-art video-to-audio methods even without audio conditioning.

Learning Latent Proxies for Controllable Single-Image Relighting

Single-image relighting is highly under-constrained: small illumination changes can produce large, nonlinear variations in shading, shadows, and specularities, while geometry and materials remain unobserved. Existing diffusion-based approaches either rely on intrinsic or G-buffer pipelines that require dense and fragile supervision, or operate purely in latent space without physical grounding, making fine-grained control of direction, intensity, and color unreliable. We observe that a full intrinsic decomposition is unnecessary and redundant for accurate relighting. Instead, sparse but physically meaningful cues, indicating where illumination should change and how materials should respond, are sufficient to guide a diffusion model. Based on this insight, we introduce LightCtrl that integrates physical priors at two levels: a few-shot latent proxy encoder that extracts compact material-geometry cues from limited PBR supervision, and a lighting-aware mask that identifies sensitive illumination regions and steers the denoiser toward shading relevant pixels. To compensate for scarce PBR data, we refine the proxy branch using a DPO-based objective that enforces physical consistency in the predicted cues. We also present ScaLight, a large-scale object-level dataset with systematically varied illumination and complete camera-light metadata, enabling physically consistent and controllable training. Across object and scene level benchmarks, our method achieves photometrically faithful relighting with accurate continuous control, surpassing prior diffusion and intrinsic-based baselines, including gains of up to +2.4 dB PSNR and 35% lower RMSE under controlled lighting shifts.

LoopViT: Scaling Visual ARC with Looped Transformers

Recent advances in visual reasoning have leveraged vision transformers to tackle the ARC-AGI benchmark. However, we argue that the feed-forward architecture, where computational depth is strictly bound to parameter size, falls short of capturing the iterative, algorithmic nature of human induction. In this work, we propose a recursive architecture called Loop-ViT, which decouples reasoning depth from model capacity through weight-tied recurrence. Loop-ViT iterates a weight-tied Hybrid Block, combining local convolutions and global attention, to form a latent chain of thought. Crucially, we introduce a parameter-free Dynamic Exit mechanism based on predictive entropy: the model halts inference when its internal state ``crystallizes" into a low-uncertainty attractor. Empirical results on the ARC-AGI-1 benchmark validate this perspective: our 18M model achieves 65.8% accuracy, outperforming massive 73M-parameter ensembles. These findings demonstrate that adaptive iterative computation offers a far more efficient scaling axis for visual reasoning than simply increasing network width. The code is available at https://github.com/WenjieShu/LoopViT.

RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention

In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applications. Furthermore, with hardware advancements, a wide range of devices besides graphics processing unit (GPU), such as application-specific integrated circuit (ASIC), have been increasingly adopted for model inference. Sparse attention, which leverages the inherent sparsity of attention by skipping computations for insignificant tokens, is an effective approach to mitigate computational costs. However, existing sparse attention methods have two critical limitations: the overhead of sparse pattern prediction and the lack of hardware generality, as most of these methods are designed for GPU. To address these challenges, this study proposes RainFusion2.0, which aims to develop an online adaptive, hardware-efficient, and low-overhead sparse attention mechanism to accelerate both video and image generative models, with robust performance across diverse hardware platforms. Key technical insights include: (1) leveraging block-wise mean values as representative tokens for sparse mask prediction; (2) implementing spatiotemporal-aware token permutation; and (3) introducing a first-frame sink mechanism specifically designed for video generation scenarios. Experimental results demonstrate that RainFusion2.0 can achieve 80% sparsity while achieving an end-to-end speedup of 1.5~1.8x without compromising video quality. Moreover, RainFusion2.0 demonstrates effectiveness across various generative models and validates its generalization across diverse hardware platforms.

OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation

Despite the promising progress in subject-driven image generation, current models often deviate from the reference identities and struggle in complex scenes with multiple subjects. To address this challenge, we introduce OpenSubject, a video-derived large-scale corpus with 2.5M samples and 4.35M images for subject-driven generation and manipulation. The dataset is built with a four-stage pipeline that exploits cross-frame identity priors. (i) Video Curation. We apply resolution and aesthetic filtering to obtain high-quality clips. (ii) Cross-Frame Subject Mining and Pairing. We utilize vision-language model (VLM)-based category consensus, local grounding, and diversity-aware pairing to select image pairs. (iii) Identity-Preserving Reference Image Synthesis. We introduce segmentation map-guided outpainting to synthesize the input images for subject-driven generation and box-guided inpainting to generate input images for subject-driven manipulation, together with geometry-aware augmentations and irregular boundary erosion. (iv) Verification and Captioning. We utilize a VLM to validate synthesized samples, re-synthesize failed samples based on stage (iii), and then construct short and long captions. In addition, we introduce a benchmark covering subject-driven generation and manipulation, and then evaluate identity fidelity, prompt adherence, manipulation consistency, and background consistency with a VLM judge. Extensive experiments show that training with OpenSubject improves generation and manipulation performance, particularly in complex scenes.

Distribution Matching Distillation Meets Reinforcement Learning

Distribution Matching Distillation (DMD) distills a pre-trained multi-step diffusion model to a few-step one to improve inference efficiency. However, the performance of the latter is often capped by the former. To circumvent this dilemma, we propose DMDR, a novel framework that combines Reinforcement Learning (RL) techniques into the distillation process. We show that for the RL of the few-step generator, the DMD loss itself is a more effective regularization compared to the traditional ones. In turn, RL can help to guide the mode coverage process in DMD more effectively. These allow us to unlock the capacity of the few-step generator by conducting distillation and RL simultaneously. Meanwhile, we design the dynamic distribution guidance and dynamic renoise sampling training strategies to improve the initial distillation process. The experiments demonstrate that DMDR can achieve leading visual quality, prompt coherence among few-step methods, and even exhibit performance that exceeds the multi-step teacher.

Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising

We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a zero-shot framework that focuses on preserving the multi-level structures from synthetic videos into the enhanced one in both spatial and temporal domains, built upon a diffusion video foundational model without further fine-tuning. Specifically, we incorporate an effective modification to have the generation/denoising process conditioned on estimated structure-aware information from the synthetic video, such as depth maps, semantic maps, and edge maps, by an auxiliary model, rather than extracting the information from a simulator. This guidance ensures that the enhanced videos are consistent with the original synthetic video at both the structural and semantic levels. Our approach is a simple yet general and powerful approach to enhancing synthetic video realism: we show that our approach outperforms existing baselines in structural consistency with the original video while maintaining state-of-the-art photorealism quality in our experiments.

Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose Follow-Your-Shape, a training-free and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a Scheduled KV Injection mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce ReShapeBench, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement.

Enhancing Vector Quantization with Distributional Matching: A Theoretical and Empirical Study

The success of autoregressive models largely depends on the effectiveness of vector quantization, a technique that discretizes continuous features by mapping them to the nearest code vectors within a learnable codebook. Two critical issues in existing vector quantization methods are training instability and codebook collapse. Training instability arises from the gradient discrepancy introduced by the straight-through estimator, especially in the presence of significant quantization errors, while codebook collapse occurs when only a small subset of code vectors are utilized during training. A closer examination of these issues reveals that they are primarily driven by a mismatch between the distributions of the features and code vectors, leading to unrepresentative code vectors and significant data information loss during compression. To address this, we employ the Wasserstein distance to align these two distributions, achieving near 100\% codebook utilization and significantly reducing the quantization error. Both empirical and theoretical analyses validate the effectiveness of the proposed approach.

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the content, frequently generating semantically plausible yet visually incorrect answers, which we refer to as semantic hallucination. In this work, we investigate the underlying causes of semantic hallucination and identify a key finding: Transformer layers in LLM with stronger attention focus on scene text regions are less prone to producing semantic hallucinations. Thus, we propose a training-free semantic hallucination mitigation framework comprising two key components: (1) ZoomText, a coarse-to-fine strategy that identifies potential text regions without external detectors; and (2) Grounded Layer Correction, which adaptively leverages the internal representations from layers less prone to hallucination to guide decoding, correcting hallucinated outputs for non-semantic samples while preserving the semantics of meaningful ones. To enable rigorous evaluation, we introduce TextHalu-Bench, a benchmark of over 1,730 samples spanning both semantic and non-semantic cases, with manually curated question-answer pairs designed to probe model hallucinations. Extensive experiments demonstrate that our method not only effectively mitigates semantic hallucination but also achieves strong performance on public benchmarks for scene text spotting and understanding.