Stimulated Raman scattering (SRS)-induced inter-channel power transfer introduces global cross-channel coupling in the amplitude domain, causing power fluctuations across the spectrum that further interact with accumulated Kerr nonlinearities. The C + L-band system modeling and generalization become challenging under various nonlinear effects, especially with power pre-tilt. In this Letter, we propose an enhanced self-attention-assisted multi-channel waveform modeling to achieve efficient and accurate modeling with SRS and non-flat launch power. To capture these cross-channel and long-range dependencies, we apply rotary positional encoding to the query (Q) and key (K) matrices in the attention mechanism. Benefitting from enhanced self-attention, we realize waveform modeling with strong generalization ability across different non-flat launch power profiles and transmission distances in ultra-wideband (UWB) wavelength-division multiplexing (WDM) systems. We compare the split-step Fourier method (SSFM) with the proposed method over a 10-span link at the optimal launch power, and the Q-factor differs from SSFM by only 0.31 dB. In a 5-span scenario with pronounced nonlinear effects, our method reduces runtime by 99.4% while maintaining a Q-factor deviation of just 0.24 dB from SSFM.

Video creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence of a structured video representation that is both faithful to film content and directly usable for agentic reasoning and manipulation. To address the challenge, we propose the Agentic Video Auto-Encoder (AVA-Encoder), a novel auto-encoding framework driven by agentic self-evolution to learn agent-native video representations. AVA-Encoder transforms a video into a Film Knowledge Graph (KG) representation and then reconstructs it back into video. This Film KG representation explicitly captures entities, events, assets, and their multimodal relationships in a structured form that can be easily understood, queried, and manipulated by agents. The reconstruction residual drives a dual-loop textual-gradient optimization framework that jointly improves the Film KG representation and the Agentic Video Encoder. Extensive experiments show that AVA-Encoder achieves a 20.7-percentage-point absolute gain, or a 73.1

Current multimodal approaches predominantly treat visual generation as an external process, relying on pixel rendering or code execution, thereby overlooking the native visual representation capabilities latent within Large Language Models (LLMs). In this work, we unlock this potential through ASCII art, a compact, efficient, and text-native visual format. We introduce SVE-ASCII, a unified framework designed to elicit and benchmark Symbolic Visual Expression directly within the pure text space. To address the scarcity of systematic resources, we construct ASCIIArt-7K, a high-quality dataset synthesized via a novel "Seed-and-Evolve" pipeline that augments human-curated anchors through in-context stylistic editing. We further implement a unified instruction-tuning strategy that jointly optimizes for both Generation (Text-to-ASCII) and Understanding (ASCII-to-Text). Crucially, our experiments reveal a critical phenomenon regarding task duality: while it is established that perception aids generation, we provide compelling evidence that generative training significantly enhances visual comprehension. This confirms a mutually reinforcing cycle in symbolic visual processing, a relationship previously hypothesized but rarely empirically demonstrated in the visual domain. We release our dataset, the ASCIIArt-Bench benchmark, and the SVE-ASCII model, establishing a robust baseline for native text-based visual intelligence.

Pose-driven human animation synthesizes a video of a target person from a single reference image and a driving pose stream. Real-time generation is essential for interactive applications such as live streaming, telepresence, and virtual avatars, yet diffusion-based systems require minutes to hours per clip, precluding responsive interaction. We present LiveAnimate, to our knowledge the first animation system to combine real-time streaming with stable long-form generation at billion scale, built on a 14B-parameter video Diffusion Transformer (DiT). A two-stage training pipeline first adapts a pretrained bidirectional DiT into a block-causal autoregressive generator through Reference-Anchored Teacher-Forcing Adaptation, and then reduces the sampling budget to three steps through Block-wise Self-Forcing Distillation. To preserve appearance over extended streams, we introduce Pose-Retrieval Sink Attention (PR-Sink), a bounded KV-cache mechanism combining a Static Sink that permanently anchors the first generated block, a Dynamic Sink that holds a pose-retrieved historical block, and a three-slot Rolling Window. When a pose recurs, PR-Sink restores the relevant appearance context without retaining the entire sequence, so memory and per-block latency remain constant regardless of stream duration. Together with Ulysses sequence parallelism and operator fusion, these designs enable 19.63 FPS streaming inference on two NVIDIA H100 GPUs. On a three-minute benchmark, LiveAnimate maintains nearly constant perceptual quality and identity from the first 30 seconds to the final minute (IQA 4.047 vs. 4.026), while prior systems degrade substantially or require hours of offline computation for the same rollout. These results establish a new operating point in quality, latency, and duration for interactive full-body animation.

While diffusion-based methods have shown impressive capabilities in capturing diverse and complex hairstyles, their ability to generate consistent and high-quality multi-view outputs—crucial for real-world applications such as digital humans and virtual avatars—remains underexplored. In this paper, we propose Stable-Hair v2, a novel diffusion-based multi-view hair transfer framework. To the best of our knowledge, this is the first work to leverage multiple-view diffusion models for robust, high-fidelity, and view-consistent hair transfer across multiple perspectives. We introduce a comprehensive multi-view training data generation pipeline to generate high-quality triplet data, including bald images, reference hairstyles, and view-aligned source-bald pairs. Our multi-view hair transfer model integrates polar-azimuth embeddings for pose conditioning and temporal attention layers to ensure smooth transitions between views. To optimize this model, we design a novel multi-stage training strategy consisting of Pose-Controllable Latent IdentityNet training, Hair Extractor training, and Temporal Attention training. Extensive experiments demonstrate that our method accurately transfers detailed and realistic hairstyles to source subjects while achieving seamless and consistent results across views, significantly outperforming existing methods and establishing a new benchmark in multi-view hair transfer.

On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally extend velocity matching to the CFG-composed prediction, directly matching teacher and student guided velocities. We show that this objective is under-identified at the branch level: positive- and negative-branch errors can compensate in the guided prediction. Through two contrasting cases, we find that naive matching remains effective under shared negative conditioning, where both branch errors decrease jointly. When the model's native CFG schema retains privileged information in the teacher's negative branch that is unavailable to the student, however, this joint reduction breaks down and the composed objective induces antagonistic branch-error dynamics, reducing the positive-branch error while increasing the negative-branch error. We term this failure mode Negative Branch Asymmetry (NBA). To address NBA, we introduce Positive--Direction Matching (PDM), a branch-aware OPD objective that separately constrains the positive prediction and the CFG conditional direction. We apply PDM to dense-to-sparse video control, where naive guided matching is highly sensitive to inference guidance scales, while branch-aware supervision enables more robust and effective knowledge transfer.

High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic attention complexity and prohibitive memory requirements. A prevalent workaround employs a two-stage pipeline: editing at low resolution followed by independent super-resolution. However, this approach suffers from two critical issues: information divergence, where hallucinated details contradict the original high-resolution (HR) source, and texture degradation, manifesting as over-smoothed or over-sharpened artifacts. We propose EditBridge, a diffusion bridge framework for efficient ultra high-resolution editing. Unlike conventional diffusion that regenerates from noise, we formulate refinement as structured data-to-data translation from the low-resolution (LR) edited result to its HR counterpart, explicitly conditioned on the original HR source to preserve authentic details. To efficiently incorporate HR source guidance, we introduce a prior-guided block-wise sparse attention mechanism that exploits semantic correspondence from first-stage editing to constrain cross-image interactions to spatially aligned regions, significantly reducing computational overhead. Extensive experiments demonstrate that EditBridge achieves high-fidelity editing with superior perceptual quality at resolutions up to 4K, delivering 3.6–8.4× speedup at 2K and enabling practical 4K editing in 61 seconds.

Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending entities, post-cutoff events, and more. This world-knowledge bottleneck is structural: generators are trained on fixed corpora, but the visual world is open-ended. We construct SearchGen-20K and SearchGen-Bench, with 20,839 prompts spanning twelve failure categories and twenty-two domains, paired with a pre-executed multimodal SearchGen-Corpus-1M to support offline, reproducible research. On SearchGen-Bench, frontier open generators score only 21 to 28 out of 100, a 40-point collapse invisible to existing benchmarks. The natural remedy is to employ search tools, enabling agentic visual generation. However, we find that naive search fails: it retrieves indiscriminately, injecting noise into prompts the generator already handles. We trace the root cause to a generator-specific, evolving knowledge boundary: the divide between what a generator can internalize through training and what must remain in external context. Although this boundary is hard to specify in advance, we show that it is discoverable through a teach-then-search co-training framework. Even a minimal version of this co-training recipe produces monotonic improvement, laying the foundation for recursive self-improvement in visual generation that can meet world-knowledge-grounded requests. We release the full dataset, co-training corpus, and search corpus as a replayable harness for tool-augmented, world-knowledge-grounded visual generation.

Talking-video character replacement requires coordinated transfer of appearance and voice while preserving the source motion, scene, linguistic content, and audio-video timing. Existing methods use separately optimized models for the two modalities, making audio-visual consistency difficult to enforce. We present UniSwap, the first framework for streaming joint audio-visual identity replacement in talking videos. Given a source video, a reference image, and a reference voice clip, UniSwap transfers the reference appearance and vocal timbre within a single audio-visual diffusion transformer while preserving the source content and dynamics. To address the scarcity of aligned cross-identity training pairs, we introduce a swap-and-reconstruct pipeline that removes visual and vocal identity from real clips and uses the original clips as reconstruction targets. Starting from a bidirectional backbone, we progressively adapt the model through In-context Pretraining for joint replacement, Conditional Streaming Adaptation for block-causal KV-cached generation, and Efficient Self-forcing DMD for mitigating exposure bias and reducing sampling from 30 to 3 denoising steps per block. Efficient Multi-LoRA Switching enables the three DMD roles to share a single frozen backbone. Feature-RoPE Decomposition keeps cached positions within the training range, supporting stable long-form inference. Experiments demonstrate strong audio-visual synchronization, competitive identity preservation, efficient streaming, and stable long-form generation.

Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dynamically loading numerous these effect LoRAs significantly increases deployment overhead. Furthermore, current pipelines typically cascade these effect LoRAs with acceleration modules for fast generation, which triggers severe parameter interference and results in concept bleeding and style degradation. We propose CollectionLoRA, a multi-teacher on-policy distillation framework capable of distilling the concepts of up to 50 different effect LoRAs along with few-step generation capabilities into a single LoRA. This fundamentally resolves the feature interference issue and significantly reduces deployment costs. Specifically, the method introduces (i) a Probabilistic Dual-Stream Routing mechanism that enables the model to randomly switch between data sources during training, effectively enhancing its generalization in unseen scenarios; (ii) an Asymmetric Orthogonal Prompting strategy to achieve concept isolation within the prompt space; (iii) a Coarse-to-Fine Distillation Objective to mitigate the distribution gap between the teacher and student models. Extensive evaluations show that CollectionLoRA distills all customized effects and few-step generation into a single LoRA, reducing deployment overhead while achieving concept fidelity comparable to or better than independently trained teacher models.

Visual text rendering represents a fundamental capability of large-scale text-to-image (T2I) models, yet achieving precise word-level controllability remains a significant challenge in this domain. While existing approaches primarily focus on text content accuracy, they often fail to provide fine-grained control over typographic attributes at the word level. To address this limitation, we introduce a comprehensive solution comprising three key components: (1) a novel word-level controlled scene text dataset and benchmark, (2) the Text-Image Alignment (TIA) framework that leverages cross-modal correspondence between textual queries and local image regions through grounding models, and (3) WordCon, a hybrid parameter-efficient fine-tuning (PEFT) method that employs selective parameter reparameterization to enhance both computational efficiency and model portability. The proposed framework incorporates additive supervision mechanisms: a masked loss at the latent level to focus on text regions, and a joint-attention loss at the feature level to promote disentanglement between different words. Extensive experimental evaluations demonstrate that our approach outperforms state-of-the-art methods in both qualitative and quantitative metrics. The proposed method exhibits remarkable versatility, enabling seamless integration with diverse pipelines, including artistic text rendering and image-conditioned text generation. Our datasets, source code, and models will be available for academic research.

Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation – capabilities fundamentally at odds with the sequential denoising and long-horizon drift of current diffusion models. We present Live Avatar, an algorithm-system co-designed framework that addresses both challenges for a 14-billion-parameter diffusion model. On the algorithm side, a two-stage pipeline distills a pretrained bidirectional model into a causal, few-step streaming one, while a set of complementary long-horizon strategies eliminate identity drift and visual artifacts, enabling stable autoregressive generation exceeding 10000 seconds. On the system side, Timestep-forcing Pipeline Parallelism (TPP) assigns each GPU a fixed denoising timestep, converting the sequential diffusion chain into an asynchronous spatial pipeline that simultaneously boosts throughput and improves temporal consistency. Live Avatar achieves 45 FPS with a TTFF of 1.21 s on 5 H800 GPUs, and to our knowledge is the first to enable practical real-time streaming of a 14B diffusion model for infinite-length avatar generation. We further introduce GenBench, a standardized long-form benchmark, to facilitate reproducible evaluation. Our project page is at https://liveavatar.github.io/.

Conversational assistants increasingly recommend follow-up edits to help users continue a task. Existing systems primarily target text-only interactions, leaving image-creation conversations underexplored. In image-creation tasks, useful follow-up edit suggestions must reflect user preferences, offer diverse directions, and remain executable on the current image. We collected 100,000 real multi-turn image-creation conversation samples from Qwen App and found that 80.1

Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an under-explored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.

We introduce PhotoDoodle, a novel image editing framework designed to facilitate photo doodling by enabling artists to overlay decorative elements onto photographs. Photo doodling is challenging because the inserted elements must appear seamlessly integrated with the background, requiring realistic blending, perspective alignment, and contextual coherence. Additionally, the background must be preserved without distortion, and the artist's unique style must be captured efficiently from limited training data. These requirements are not addressed by previous methods that primarily focus on global style transfer or regional inpainting. The proposed method, PhotoDoodle, employs a two-stage training strategy. Initially, we train a general-purpose image editing model, OmniEditor, using large-scale data. Subsequently, we fine-tune this model with EditLoRA using a small, artist-curated dataset of before-and-after image pairs to capture distinct editing styles and techniques. To enhance consistency in the generated results, we introduce a positional encoding reuse mechanism. Additionally, we release a PhotoDoodle dataset featuring six high-quality styles. Extensive experiments demonstrate the advanced performance and robustness of our method in customized image editing, opening new possibilities for artistic creation.

Recent advancements in Unet-based diffusion models, such as ControlNet and IP-Adapter, have introduced effective spatial and subject control mechanisms. However, the DiT (Diffusion Transformer) architecture still struggles with efficient and flexible control. To tackle this issue, we propose EasyControl, a novel framework designed to unify condition-guided diffusion transformers with high efficiency and flexibility. Our framework is built on three key innovations. First, we introduce a lightweight Condition Injection LoRA Module. This module processes conditional signals in isolation, acting as a plug-and-play solution. It avoids modifying the base model weights, ensuring compatibility with customized models and enabling the flexible injection of diverse conditions. Notably, this module also supports harmonious and robust zero-shot multi-condition generalization, even when trained only on single-condition data. Second, we propose a Position-Aware Training Paradigm. This approach standardizes input conditions to fixed resolutions, allowing the generation of images with arbitrary aspect ratios and flexible resolutions. At the same time, it optimizes computational efficiency, making the framework more practical for real-world applications. Third, we develop a Causal Attention Mechanism combined with the KV Cache technique, adapted for conditional generation tasks. This innovation significantly reduces the latency of image synthesis, improving the overall efficiency of the framework. Through extensive experiments, we demonstrate that EasyControl achieves exceptional performance across various application scenarios. These innovations collectively make our framework highly efficient, flexible, and suitable for a wide range of tasks.

Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to guide 3D object generation. These methods enable the synthesis of detailed and photorealistic textured objects. However, the appearance of 3D objects produced by such text-to-3D models is often unpredictable, and it is hard for single-image-to-3D methods to deal with images lacking a clear subject, complicating the generation of appearance-controllable 3D objects from complex images. To address these challenges, we present IPDreamer, a novel method that captures intricate appearance features from complex **I**mage **P**rompts and aligns the synthesized 3D object with these extracted features, enabling high-fidelity, appearance-controllable 3D object generation. Our experiments demonstrate that IPDreamer consistently generates high-quality 3D objects that align with both the textual and complex image prompts, highlighting its promising capability in appearance-controlled, complex 3D object generation.

We introduce ArtEditor, a novel framework for instruction-based image editing that learns unique editing styles from few-shot examples. While image editing has seen significant advancements, customized instructional editing remains underexplored. Existing methods often rely on complex, multi-stage pipelines that are difficult to adapt to specific styles. Additionally, this domain lacks a standardized benchmark, making it challenging to evaluate progress. To address these issues, we propose ArtEditor, a two-stage training framework. In the first stage, we train ArtEditorBase, a general-purpose image editing model, on largescale datasets to build a strong foundational capability. In the second stage, we fine-tune this model using ArtEditorLoRA, a lightweight adaptation module, on a small dataset of before-and-after image pairs. This approach enables the model to efficiently learn distinct editing styles and techniques with minimal data. To enhance the performance of a pre-trained Diffusion Transformer (DiT) model, we introduce two key innovations: position encoding cloning and a noise-free conditioning paradigm. These techniques ensure stable and coherent edits, even when adapting to new styles. To support research in this area, we contribute the DoodleArt dataset, the first benchmark specifically designed for customized image editing. DoodleArt features six highquality artistic styles created by professional artists and designers, providing a valuable resource for evaluating and advancing future work. Extensive experiments demonstrate that ArtEditor achieves superior performance and robustness in customized image editing. Our framework opens new possibilities for artistic creation, offering artists intuitive and flexible tools to bring their visions to life. Codes are available at https://github.com/showlab/PhotoDoodle.

Interleaved text-image generation aims to jointly produce coherent visual frames and aligned textual descriptions within a single sequence, enabling tasks such as style transfer, compositional synthesis, and procedural tutorials. We present Loom, a unified diffusion-transformer framework for interleaved text-image generation. Loom extends the Bagel unified model via full-parameter fine-tuning and an interleaved architecture that alternates textual and visual embeddings for multi-condition reasoning and sequential planning. A language planning strategy first decomposes a user instruction into stepwise prompts and frame embeddings, which guide temporally consistent synthesis. For each frame, Loom conditions on a small set of sampled prior frames together with the global textual context, rather than concatenating all history, yielding controllable and efficient long-horizon generation. Across style transfer, compositional generation, and tutorial-like procedures, Loom delivers superior compositionality, temporal coherence, and text-image alignment. Experiments demonstrate that Loom substantially outperforms the open-source baseline Anole, achieving an average gain of 2.6 points (on a 5-point scale) across temporal and semantic metrics in text-to-interleaved tasks. We also curate a 50K interleaved tutorial dataset and demonstrate strong improvements over unified and diffusion editing baselines.