Search arXiv⌕ Search

arXiv subjects

Zhe Lin

Publications and source records attributed to Zhe Lin.

At least 19 recordsLinked to original sources
arXiv2026

PixelControl: Fine-Grained Condition Fidelity in Text-to-Image Diffusion

Controllable text-to-image diffusion models can often follow the global layout of spatial conditions, yet still violate fine-grained structures such as object boundaries, thin contours, and medium/small conditioned regions. This limitation is especially problematic for VAE-based latent diffusion, where spatial compression can weaken high-frequency and low-area condition signals. We propose PixelControl, a pixel-space controllable diffusion framework for fine-grained condition fidelity. Built on a PixelDiT-style backbone, PixelControl avoids the latent bottleneck and introduces two complementary designs. First, Structure-Aware Control Injection derives a condition structure map and uses it to strengthen injected control residuals around spatially sensitive regions. Second, Multi-Scale Pyramid Cycle Loss verifies generated images against condition-derived structures across multiple resolutions, balancing global layout consistency with local boundary and detail accuracy. PixelControl supports depth, segmentation, edge, and their combinations through modality-specific control branches with lightweight gated fusion. Experiments across depth, segmentation, and edge control show that PixelControl improves structural fidelity and visual quality over existing controllable generation methods, with especially strong gains on boundaries and medium/small conditioned regions. The project page can be found at: https://linxin0.github.io/pixelcontrol_homepage/pixelcontrol-site/

cs.CV↗
arXiv2026

EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing

Interactive video generation and editing are becoming increasingly important for creative design. In this report, we introduce EditStream: a unified framework for interactive video generation and editing. EditStream unifies multiple video creation and manipulation tasks within a single DiT-based model through flexible task-specific conditioning, and further transforms it into a fast, few-step autoregressive model for efficient streaming. It supports Text-to-Video, Image-to-Video, Video-to-Video, Editing Propagation, Reference-guided Video Editing, and Camera Pose Change, enabling flexible control over video generation, transformation, and editing within one system. To make the unified model practical for interactive use, we develop a two-stage distillation approach that combines Velocity Moment Matching (VMM) with autoregressive unrolling. VMM matches conditional velocity moments at student-reached intermediate states to preserve generation quality and motion, while unrolling exposes the student to its own autoregressive predictions to improve temporal stability. Together, they alleviate common challenges in few-step autoregressive video generation, including over-saturation, degraded motion, temporal instability, and complex training. EditStream provides a practical and scalable solution that bridges high-quality diffusion-based video models with interactive creative workflows.

cs.CV↗
arXiv2026

Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning

The world evolves following its dynamics, i.e., its laws of motion. However, leading video diffusion models largely fit the pixels without modeling how the pixels transit over time. Thus, they render visually plausible frames but may not accurately obey the laws. To capture the dynamics purely from pixels, we introduce Latent Dynamics Reasoning (LDR). LDR casts the latent transition as an explicit kinematic integration, where the lower-order dynamics are integrated numerically and the model regresses only the third- and higher-order residual that drives the rollout. For this integration to extrapolate better, LDR runs it on a structured latent rather than dense convolutional features. Following PhyWorld, we validate LDR on a controlled white-box physics benchmark spanning five tasks (uniform motion, parabola, collision, bouncing, looming), focusing on out-of-distribution scenarios that reveal whether a model has truly learned the underlying dynamics. LDR extrapolates the learned dynamics far better: the gap between its in- and out-of-distribution error is over 20$\times$ smaller than the video diffusion baseline's, under both single- and joint-task training at 256$^2$ resolution, while using 26$\times$ fewer parameters and running 143$\times$ faster. LDR can even generalize under severe shift: for example, trained only on red balls moving left-to-right, it correctly predicts the motion of a blue square moving right-to-left. To our knowledge, this is the first video world model that extrapolates learned dynamics beyond its training distribution. Project page: https://lat-dyn-reason.github.io/

cs.CV↗
arXiv2026

AP-DRL: A Synergistic Algorithm-Hardware Framework for Automatic Task Partitioning of Deep Reinforcement Learning on Versal ACAP

Deep reinforcement learning has demonstrated remarkable success across various domains. However, the tight coupling between training and inference processes makes accelerating DRL training an essential challenge for DRL optimization. Two key issues hinder efficient DRL training: (1) the significant variation in computational intensity across different DRL algorithms and even among operations within the same algorithm complicates hardware platform selection, while (2) DRL's wide dynamic range could lead to substantial reward errors with conventional FP16+FP32 mixed-precision quantization. While existing work has primarily focused on accelerating DRL for specific computing units or optimizing inference-stage quantization, we propose AP-DRL to address the above challenges. AP-DRL is an automatic task partitioning framework that harnesses the heterogeneous architecture of AMD Versal ACAP (integrating CPUs, FPGAs, and AI Engines) to accelerate DRL training through intelligent hardware-aware optimization. Our approach begins with bottleneck analysis of CPU, FPGA, and AIE performance across diverse DRL workloads, informing the design principles for AP-DRL's inter-component task partitioning and quantization optimization. The framework then addresses the challenge of platform selection through design space exploration-based profiling and ILP-based partitioning models that match operations to optimal computing units based on their computational characteristics. For the quantization challenge, AP-DRL employs a hardware-aware algorithm coordinating FP32 (CPU), FP16 (FPGA/DSP), and BF16 (AI Engine) operations by leveraging Versal ACAP's native support for these precision formats. Comprehensive experiments indicate that AP-DRL can achieve speedup of up to 4.17$\times$ over programmable logic and up to 3.82$\times$ over AI Engine baselines while maintaining training convergence.

cs.AR↗
arXiv2026

LightMover: Generative Light Movement with Color and Intensity Controls

We present LightMover, a framework for controllable light manipulation in single images that leverages video diffusion priors to produce physically plausible illumination changes without re-rendering the scene. We formulate light editing as a sequence-to-sequence prediction problem in visual token space: given an image and light-control tokens, the model adjusts light position, color, and intensity together with resulting reflections, shadows, and falloff from a single view. This unified treatment of spatial (movement) and appearance (color, intensity) controls improves both manipulation and illumination understanding. We further introduce an adaptive token-pruning mechanism that preserves spatially informative tokens while compactly encoding non-spatial attributes, reducing control sequence length by 41% while maintaining editing fidelity. To train our framework, we construct a scalable rendering pipeline that generates large numbers of image pairs across varied light positions, colors, and intensities while keeping the scene content consistent with the original image. LightMover enables precise, independent control over light position, color, and intensity, and achieves high PSNR and strong semantic consistency (DINO, CLIP) across different tasks.

cs.CV↗
arXiv2026

SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation

Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a large VQ codebook remains challenging, typically requiring larger model size and a longer training schedule. In this work, we propose Stochastic Neighbor Cross Entropy Minimization (SNCE), a novel training objective designed to address the optimization challenges of large-codebook discrete image generators. Instead of supervising the model with a hard one-hot target, SNCE constructs a soft categorical distribution over a set of neighboring tokens. The probability assigned to each token is proportional to the proximity between its code embedding and the ground-truth image embedding, encouraging the model to capture semantically meaningful geometric structure in the quantized embedding space. We conduct extensive experiments across class-conditional ImageNet-256 generation, large-scale text-to-image synthesis, and image editing tasks. Results show that SNCE significantly improves convergence speed and overall generation quality compared to standard cross-entropy objectives.

cs.CV↗
arXiv2026

Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion

Recent video diffusion models have made remarkable strides in visual quality, yet precise, fine-grained control remains a key bottleneck that limits practical customizability for content creation. For AI video creators, three forms of control are crucial: (i) scene composition, (ii) multi-view consistent subject customization, and (iii) camera-pose or object-motion adjustment. Existing methods typically handle these dimensions in isolation, with limited support for multi-view subject synthesis and identity preservation under arbitrary pose changes. This lack of a unified architecture makes it difficult to support versatile, jointly controllable video. We introduce Tri-Prompting, a unified framework and two-stage training paradigm that integrates scene composition, multi-view subject consistency, and motion control. Our approach leverages a dual-condition motion module driven by 3D tracking points for background scenes and downsampled RGB cues for foreground subjects. To ensure a balance between controllability and visual realism, we further propose an inference ControlNet scale schedule. Tri-Prompting supports novel workflows, including 3D-aware subject insertion into any scenes and manipulation of existing subjects in an image. Experimental results demonstrate that Tri-Prompting significantly outperforms specialized baselines such as Phantom and DaS in multi-view subject identity, 3D consistency, and motion accuracy.

cs.CV↗
arXiv2026

How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation

Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow, generation quality rapidly collapses. In this work, we investigate the mechanism behind this failure and argue that it is distinct from standard long-context challenges. We reveal that in generation, accumulated visual history acts as a source of active pollution, a decay governed specifically by the number of image events rather than raw token count. We identify a structural vulnerability where dense visual tokens overwhelm the attention mechanism, creating noise that distorts future synthesis. Guided by these mechanistic insights, we propose UniLongGen, a training-free inference strategy that prioritizes safe conditioning over total recall. Instead of retaining all history, UniLongGen dynamically curates the model's memory, identifying and discarding interfering visual signals based on the model's own internal relevance rankings. Extensive experiments demonstrate that this active forgetting approach is essential for stability: UniLongGen significantly outperforms baselines in long-horizon fidelity and consistency, while simultaneously reducing memory footprint and inference time.

cs.CV↗
arXiv2026

LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a unified manner. In particular, LaViDa-R1 is built with a novel unified post-training framework that seamlessly integrates supervised finetuning (SFT) and multi-task reinforcement learning (RL). It employs several novel training techniques, including answer-forcing, tree search, and complementary likelihood estimation, to enhance effectiveness and scalability. Extensive experiments demonstrate LaViDa-R1's strong performance on a wide range of multimodal tasks, including visual math reasoning, reason-intensive grounding, and image editing.

cs.CV↗
arXiv2026

Rethinking Global Text Conditioning in Diffusion Transformers

Diffusion transformers typically incorporate textual information via attention layers and a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches discard modulation-based text conditioning and rely exclusively on attention. In this paper, we address whether modulation-based text conditioning is necessary and whether it can provide any performance advantage. Our analysis shows that, in its conventional usage, the pooled embedding contributes little to overall performance, suggesting that attention alone is generally sufficient for faithfully propagating prompt information. However, we reveal that the pooled embedding can provide significant gains when used from a different perspective-serving as guidance and enabling controllable shifts toward more desirable properties. This approach is training-free, simple to implement, incurs negligible runtime overhead, and can be applied to various diffusion models, bringing improvements across diverse tasks, including text-to-image/video generation and image editing.

cs.CV↗
arXiv2026

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

Autoregressive (AR) video diffusion models in the Self Forcing family generate a video chunk by chunk, each conditioned on the ones before it, so they can keep rolling out with no preset length. In practice they are trained on short, fixed clips (e.g., 5s). Once a rollout passes this training horizon, the cache fills with self-generated chunks the model never saw in training, and quality degrades: colors oversaturate, identities drift, structures collapse, and motion fades. We frame this failure as a cache-behavior mismatch, a domain shift between the within-horizon caches seen in training and those produced by open-ended testing, and address it with Rolling Sink, a training-free inference-time cache policy. Within the base model's fixed cache budget, Rolling Sink holds the cache close to its stable within-horizon behavior: it restores low-drift content, sliding temporal indices, and evolving semantics, and keeps a small recent context. Attention sink and temporal re-indexing are existing mechanisms. Our contribution is the mismatch formulation, the joint bounded-cache policy, and the Rolling Semantics schedule. On two 5s-trained bases, Self Forcing and Causal Forcing, Rolling Sink attains the best averaged rank on VBench-Long at both 1- and 5-minute rollouts under the same inference setting, at about 0.56% throughput change, and holds GPU memory constant. It also sustains a 30-minute qualitative rollout, 360 times its training horizon. We validate at 1- and 5-minute rollouts and do not claim guaranteed quality at arbitrary duration. Project page: https://rolling-sink.github.io/

cs.CV↗
arXiv2026

Burst Mode Ultrafast Laser Welding of Sapphire and Fe-36Ni Alloy with Non-optical Contact Condition

Ultrafast laser welding provides a promising approach for high precision integration of transparent and metallic materials. However, its practical application remains constrained by the precise regulation of the interfacial gap. This study investigates the interfacial response and bonding mechanism of sapphire and Fe-36Ni alloy joints under controlled non-optical contact conditions using burst mode ultrafast laser irradiation. A polymer interlayer was introduced between naturally stacked samples to establish a variable interfacial gap, allowing systematic evaluation of gap-dependent morphology, melting behavior, and elemental transport. By redistributing the pulse energy into sequential sub-pulses, the burst mode reconstructs the temporal energy-deposition process, yielding enhanced plasma-material coupling and stable thermal accumulation. Compared with single pulse irradiation, burst mode sustains continuous bonding across gaps exceeding 10 um--far beyond the failure threshold of the single pulse mode--and forms a fusion zone 82% larger. Fracture surface and cross-sectional analyses of SEM and EDS results confirm that sequential sub-pulses promote extensive sapphire melting, droplet-driven gap bridging, and enhanced Al-Fe interdiffusion at the interface. These results provide a scientific basis for high-gap-tolerance ultrafast laser welding and scalable integration of transparent-metal hybrid components in advanced optoelectronic and precision engineering applications.

physics.optics↗
arXiv2026

A Unified and Controllable Framework for Layered Image Generation with Visual Effects

Recent image generation models produce impressive composites, but often fail to preserve the identity of user-provided content when editing specific elements: the surrounding scene may shift, and even the edited object's appearance can drift from the original. Layered representation offer a natural remedy--they allow users to independently manipulate individual elements--but existing layered methods typically produce transparent foregrounds without realistic visual effects such as shadows and reflections, forcing the use of a second harmonization model after every edit, which in turn introduces drift. To overcome these limitations, we present LASAGNA, which generates a photorealistic background (BG) and an RGBA foreground with compelling visual effects in a single forward pass. By treating object-associated visual effects as part of the foreground (FG) layer, LASAGNA supports the dominant class of consumer edits (e.g., translation, scaling, recoloring, duplication) via alpha compositing alone, without invoking any model post-edit, thereby eliminating identity drift introduced by cascade editing pipelines. This single-pass design contrasts with prior layered methods that rely on separate expert models for each task. LASAGNA handles diverse conditional inputs--text prompts, FG, BG, and location masks--within a unified architecture. We further release two community resources: LASAGNA-48K, the first public dataset of 48K layered image triplets with photorealistic visual effects, and LASAGNA-BENCH, the first standardized benchmark for layer-centric generation and editing, comprising 242 expert-annotated samples across six diverse sources. Experiments show that LASAGNA outperforms both general-purpose editors and prior layered methods across three generation modes, and supports a wide range of post-edits without any model re-inference.

cs.CV↗
arXiv2025

Self-Evaluation Unlocks Any-Step Text-to-Image Generation

We introduce the Self-Evaluating Model (Self-E), a novel, from-scratch training approach for text-to-image generation that supports any-step inference. Self-E learns from data similarly to a Flow Matching model, while simultaneously employing a novel self-evaluation mechanism: it evaluates its own generated samples using its current score estimates, effectively serving as a dynamic self-teacher. Unlike traditional diffusion or flow models, it does not rely solely on local supervision, which typically necessitates many inference steps. Unlike distillation-based approaches, it does not require a pretrained teacher. This combination of instantaneous local learning and self-driven global matching bridges the gap between the two paradigms, enabling the training of a high-quality text-to-image model from scratch that excels even at very low step counts. Extensive experiments on large-scale text-to-image benchmarks show that Self-E not only excels in few-step generation, but is also competitive with state-of-the-art Flow Matching models at 50 steps. We further find that its performance improves monotonically as inference steps increase, enabling both ultra-fast few-step generation and high-quality long-trajectory sampling within a single unified model. To our knowledge, Self-E is the first from-scratch, any-step text-to-image model, offering a unified framework for efficient and scalable generation.

cs.CV↗
arXiv2025

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents. However, we empirically identify two fundamental obstacles in this paradigm: (1) the discriminative feature space lacks compact regularization, making diffusion models prone to off-manifold latents that lead to inaccurate object structures; and (2) the encoder's inherently weak pixel-level reconstruction hinders the generator from learning accurate fine-grained geometry and texture. In this paper, we propose a systematic framework to adapt understanding-oriented encoder features for generative tasks. We introduce a semantic-pixel reconstruction objective to regularize the latent space, enabling the compression of both semantic information and fine-grained details into a highly compact representation (96 channels with 16x16 spatial downsampling). This design ensures that the latent space remains semantically rich and achieves state-of-the-art image reconstruction, while remaining compact enough for accurate generation. Leveraging this representation, we design a unified Text-to-Image (T2I) and image editing model. Benchmarking against various feature spaces, we demonstrate that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both T2I and editing tasks, validating that representation encoders can be effectively adapted into robust generative components.

cs.CV↗
arXiv2025

Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models

Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, their inference speed remains suboptimal due to the need to repeatedly process redundant masked tokens at every sampling step. In this work, we propose Sparse-LaViDa, a novel modeling framework that dynamically truncates unnecessary masked tokens at each inference step to accelerate MDM sampling. To preserve generation quality, we introduce specialized register tokens that serve as compact representations for the truncated tokens. Furthermore, to ensure consistency between training and inference, we design a specialized attention mask that faithfully matches the truncated sampling procedure during training. Built upon the state-of-the-art unified MDM LaViDa-O, Sparse-LaViDa achieves up to a 2x speedup across diverse tasks including text-to-image generation, image editing, and mathematical reasoning, while maintaining generation quality.

cs.CV↗
arXiv2025

PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement

Latent Diffusion Models (LDMs) have markedly advanced the quality of image inpainting and local editing. However, the inherent latent compression often introduces pixel-level inconsistencies, such as chromatic shifts, texture mismatches, and visible seams along editing boundaries. Existing remedies, including background-conditioned latent decoding and pixel-space harmonization, usually fail to fully eliminate these artifacts in practice and do not generalize well across different latent representations or tasks. We introduce PixPerfect, a pixel-level refinement framework that delivers seamless, high-fidelity local edits across diverse LDM architectures and tasks. PixPerfect leverages (i) a differentiable discriminative pixel space that amplifies and suppresses subtle color and texture discrepancies, (ii) a comprehensive artifact simulation pipeline that exposes the refiner to realistic local editing artifacts during training, and (iii) a direct pixel-space refinement scheme that ensures broad applicability across diverse latent representations and tasks. Extensive experiments on inpainting, object removal, and insertion benchmarks demonstrate that PixPerfect substantially enhances perceptual fidelity and downstream editing performance, establishing a new standard for robust and high-fidelity localized image editing.

cs.CV↗
arXiv2025

HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generation

Recent unified models integrate understanding experts (e.g., LLMs) with generative experts (e.g., diffusion models), achieving strong multimodal performance. However, recent advanced methods such as BAGEL and LMFusion follow the Mixture-of-Transformers (MoT) paradigm, adopting a symmetric design that mirrors one expert to another for convenient initialization and fusion, which remains suboptimal due to inherent modality discrepancies. In this work, we propose HBridge, an asymmetric H-shaped architecture that enables heterogeneous experts to optimally leverage pretrained priors from their respective modality domains. Unlike prior dense fusion strategies that straightforwardly connect all layers between experts via shared attention, HBridge selectively bridges intermediate layers, reducing over 40% attention sharing, which improves efficiency and enhances generation quality. Shallow and deep layers, which capture modality-specific representations, are decoupled, while mid-layer bridging promotes semantic alignment. To further strengthen cross-modal coherence, we introduce semantic reconstruction tokens that explicitly guide the generative expert to reconstruct visual semantic tokens of the target image. Extensive experiments across multiple benchmarks demonstrate the effectiveness and superior performance of HBridge, establishing a new paradigm for unified multimodal generation.

cs.CV↗