论文检索

Computer Vision · Everything Else

Ye Lu, Jie Wang, Tianyi Liu, Jianjun Gao, Kim-Hui Yap

Stochastic Human Motion Prediction (HMP) has become an essential task for the realm of computer vision, for its capacity to anticipate accurate and diverse future human trajectories. Current diffusion-based techniques typically enforce skeletal consistency by encoding structural priors into network architectures. Although effective in promoting plausible kinematics, this approach provides only indirect control over the generative process and often fails to guarantee strict physical constraint satisfaction. In this work, we propose a structure-aligned and joint-aware diffusion framework that enforces physical constraints by embedding skeletal topology and joint-specific dynamics directly into the diffusion process. Specifically, our framework consists of two key modules, the Joint-Adaptive Noise Generator and the Structure-Aligned Constraint Enforcer. The former component, Joint-Adaptive Noise Generator, infers joint-specific dynamics and injects heterogeneous, instance-aware noise per joint and sample to capture spatial variability and enhance motion diversity. The latter component, Structure-Aligned Constraint Enforcer, encodes skeletal topology by modeling joint connectivity and bone lengths from historical motions, and it constrains each denoising step to preserve anatomical consistency. Through their synergistic operation, these modules grant KinemaDiff direct control over physical realism and motion diversity, addressing the common limitations of indirect structural priors and uniform noise application. Extensive experiments on multiple benchmarks demonstrate the effectiveness of our method, attributable to tailoring the diffusion process through structural alignment and joint-adaptive noise modeling.

Computer Vision · Everything Else

Sudarshan Rajagopalan, Kartik Narayan, Vishal Patel

The use of latent diffusion models (LDMs) such as Stable Diffusion has significantly improved the perceptual quality of All-in-One image Restoration (AiOR) methods, while also enhancing their generalization capabilities. However, these LDM-based frameworks suffer from slow inference due to their iterative denoising process, rendering them impractical for time-sensitive applications. Visual autoregressive modeling (VAR), a recently introduced approach for image generation, performs scale-space autoregression and achieves comparable performance to that of state-of-the-art diffusion transformers with drastically reduced computational costs. Moreover, our analysis reveals that coarse scales in VAR primarily capture degradations while finer scales encode scene detail, simplifying the restoration process. Motivated by this, we propose RestoreVAR, a novel VAR-based generative approach for AiOR that significantly outperforms LDM-based models in restoration performance while achieving over $\mathbf{10\times}$ faster inference. To optimally exploit the advantages of VAR for AiOR, we propose architectural modifications and improvements, including intricately designed cross-attention mechanisms and a latent-space refinement module, tailored for the AiOR task. Extensive experiments show that RestoreVAR achieves state-of-the-art performance among generative AiOR methods, while also exhibiting strong generalization capabilities.

Computer Vision · Vision Models & Multimodal

Guangyi Han, Wei Zhai, Yuhang Yang, Yang Cao, Zheng-Jun Zha

Hand-object interaction (HOI) is fundamental for humans to express intent. Existing HOI generation research is predominantly confined to fixed grasping patterns, where control is tied to physical priors such as force closure or generic intent instructions, even when expressed through elaborate language. Such an overly general conditioning imposes a strong inductive bias for stable grasps, thus failing to capture the diversity of daily HOI. To address these limitations, we introduce $\textbf{Free-Form HOI Generation}$, which aims to generate controllable, diverse, and physically plausible HOI conditioned on fine-grained intent, extending HOI from grasping to free-form interactions, like pushing, poking, and rotating. To support this task, we construct $\textbf{WildO2}$, an in-the-wild diverse 3D HOI dataset, which includes diverse HOI derived from internet videos. Specifically, it contains 4.4k unique interactions across 92 intents and 403 object categories, each with detailed semantic annotations. Building on this dataset, we propose $\textbf{TOUCH}$, a three-stage framework centered on a multi-level diffusion model that facilitates fine-grained semantic control to generate versatile hand poses beyond grasping priors. This process leverages explicit contact modeling for conditioning and is subsequently refined with contact consistency and physical constraints to ensure realism. Comprehensive experiments demonstrate our method's ability to generate controllable, diverse, and physically plausible hand interactions representative of daily activities.

Computer Vision · Vision Models & Multimodal

Hongyang Zhou, Xiaobin Zhu, Shengxiang Yu, Liuling Chen, Jingyan Qin, Xu-Cheng Yin

Single image super-resolution (SISR) often struggles to reconstruct high-resolution (HR) details from heavily degraded low-resolution (LR) inputs. Instead, reference-based super-resolution (RefSR) methods offer an alternative solution to generate promising results using high-quality reference (Ref) images to guide reconstruction. However, existing RefSR datasets focus on limited scene types, primarily featuring human activities and architectural scenes. Plant scenes exhibit complex textures and fine details, essential for advancing RefSR in natural and highly detailed scenes. To this end, we meticulously captured and manually selected high-quality images containing rich textures to construct a large-scale plant dataset, PlantRSR, comprising 16,585 HR–Ref pairs. The dataset captures the complexity and variability of plant scenes through extensive variations. In addition, we propose a novel RefSR method specifically designed to tackle the distinct challenges posed by plant imagery. It incorporates a Selective Key-Region Matching (SKRM) that selectively identifies and performs matching between LR and Ref images, focusing on distinctive botanical textures to improve matching efficiency. Additionally, a Texture-Guided Diffusion Module (TGDM) is proposed to refine LR textures by leveraging a diffusion process conditioned on the matched Ref textures. TGDM is effective in modeling irregular and fine textures, thereby facilitating more accurate SR results. The proposed method achieves significant improvements over state-of-the-art (SOTA) approaches on our PlantRSR dataset and other Benchmarks.

Deep Learning · Generative Models and Autoencoders

Jingyang Ou, Jiaqi Han, Minkai Xu, Shaoxuan Xu, Jianwen Xie, Stefano Ermon, Yi Wu, Chongxuan Li

Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges. The core difficulty lies in likelihood approximation: while autoregressive models naturally provide token-level conditional probabilities essential for token-level RL objectives (e.g., GRPO), dLLMs generate sequences through iterative non-autoregressive denoising steps that lack this factorization. To address this fundamental mismatch, we propose ELBO-based Sequence-level Policy Optimization (ESPO), a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy. Our method incorporates per-token normalization of importance ratios and robust KL-divergence estimation to ensure stable large-scale training. Extensive experiments on mathematical reasoning, coding, and planning tasks demonstrate that ESPO significantly outperforms token-level baselines, achieving dramatic improvements of 20-40 points on the Countdown task, while maintaining consistent gains on math and coding benchmarks. Our approach establishes sequence-level optimization as a principled and empirically effective paradigm for RL in dLLMs.

Computer Vision · Image and Video Generation

Zixin Yin, Xili Dai, Ling-Hao Chen, Deyu Zhou, Jianan Wang, Duomin Wang, Gang Yu, Lionel Ni, Lei Zhang, Heung-Yeung Shum

Text-guided color editing in images and videos is a fundamental yet unsolved problem, requiring fine-grained manipulation of color attributes, including albedo, light source color, and ambient lighting, while preserving physical consistency in geometry, material properties, and light-matter interactions. Existing training-free approaches provide broad applicability across editing tasks but struggle with precise color control and often introduce visual inconsistency in both edited and non-edited regions. In this work, we present ColorCtrl, a training-free color editing method that leverages the attention mechanisms of modern Multi-Modal Diffusion Transformers (MM-DiT). By disentangling structure and color through targeted manipulation of attention maps and value tokens, our method enables accurate and consistent color editing, along with word-level control of attribute intensity. Our method modifies only the intended regions specified by the prompt, leaving unrelated areas untouched. Extensive experiments on both SD3 and FLUX.1-dev demonstrate that ColorCtrl outperforms existing training-free approaches and achieves state-of-the-art performances in both edit quality and consistency. Furthermore, our method surpasses strong commercial models such as FLUX.1 Kontext Max and GPT-4o Image Generation in terms of consistency. When extended to video models like CogVideoX, our approach exhibits greater advantages, particularly in maintaining temporal coherence and editing stability. Finally, our method generalizes to instruction-based editing diffusion models such as Step1X-Edit and FLUX.1 Kontext dev, further demonstrating its versatility. Here is the website.

Computer Vision · Image and Video Generation

Zixin Yin, Xili Dai, Duomin Wang, Xianfang Zeng, Lionel Ni, Gang Yu, Heung-Yeung Shum

The reliance on implicit point matching via attention has become a core bottleneck in drag-based editing, resulting in a fundamental compromise on weakened inversion strength and costly test-time optimization (TTO). This compromise severely limits the generative capabilities, suppressing high-fidelity inpainting and text-guided creation. In this paper, we introduce LazyDrag, the first drag-based image editing method for Multi-Modal Diffusion Transformers, which directly eliminates the reliance on implicit point matching. In concrete terms, our method generates an explicit correspondence map from user drag inputs as a reliable reference to boost the attention control. This reliable reference opens the potential for a stable full-strength inversion process, which is the first in the drag-based editing task. It obviates the necessity for TTO and unlocks the generative capability of models. Therefore, LazyDrag naturally unifies precise geometric control with text guidance, enabling complex edits that were previously out of reach: opening the mouth of a dog and inpainting its interior, generating new objects like a ``tennis ball'', or for ambiguous drags, making context-aware changes like moving hands into pockets. Moreover, LazyDrag supports multi-round edits with simultaneous move and scale operations. Evaluated on DragBench, our method outperforms baselines in drag accuracy and perceptual quality, as validated by mean distances, VIEScore and user studies. LazyDrag not only sets new state-of-the-art performance, but also paves a new way to editing paradigms. Here is the project website.

Computer Vision · Image and Video Generation

Haoyu Wu, Diankun Wu, Tianyu He, Junliang Guo, Yang Ye, Yueqi Duan, Jiang Bian

Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned representations. To bridge this gap between video diffusion models and the underlying 3D nature of the physical world, we propose Geometry Forcing, a simple yet effective method that encourages video diffusion models to internalize latent 3D representations. Our key insight is to guide the model’s intermediate representations toward geometry-aware structure by aligning them with features from a pretrained geometric foundation model. To this end, we introduce two complementary alignment objectives: Angular Alignment, which enforces directional consistency via cosine similarity, and Scale Alignment, which preserves scale-related information by regressing unnormalized geometric features from normalized diffusion representation. We evaluate Geometry Forcing on both camera view–conditioned and action-conditioned video generation tasks. Experimental results demonstrate that our method substantially improves visual quality and 3D consistency over the baseline methods.

Computer Vision · Image and Video Generation

Yushi Huang, Ruihao Gong, Jing Liu, Yifu Ding, Chengtao Lv, Haotong Qin, Jun Zhang

Video diffusion models (DMs) have enabled high-quality video synthesis. Yet, their substantial computational and memory demands pose serious challenges to real-world deployment, even on high-end GPUs. As a commonly adopted solution, quantization has proven notable success in reducing cost for image DMs, while its direct application to video DMs remains ineffective. In this paper, we present *QVGen*, a novel quantization-aware training (QAT) framework tailored for high-performance and inference-efficient video DMs under extremely low-bit quantization (*e.g.*, $4$-bit or below). We begin with a theoretical analysis demonstrating that reducing the gradient norm is essential to facilitate convergence for QAT. To this end, we introduce auxiliary modules ($\Phi$) to mitigate large quantization errors, leading to significantly enhanced convergence. To eliminate the inference overhead of $\Phi$, we propose a *rank-decay* strategy that progressively eliminates $\Phi$. Specifically, we repeatedly employ singular value decomposition (SVD) and a proposed rank-based regularization $\mathbf{\gamma}$ to identify and decay low-contributing components. This strategy retains performance while zeroing out additional inference overhead. Extensive experiments across $4$ state-of-the-art (SOTA) video DMs, with parameter sizes ranging from $1.3\text{B}\sim14\text{B}$, show that QVGen is *the first* to reach full-precision comparable quality under $4$-bit settings. Moreover, it significantly outperforms existing methods. For instance, our $3$-bit CogVideoX-2B achieves improvements of $+25.28$ in Dynamic Degree and $+8.43$ in Scene Consistency on VBench. Code and models are available at https://github.com/ModelTC/QVGen.

Computer Vision · Image and Video Generation

Yuanzhi Zhu, Xi WANG, Stéphane Lathuilière, Vicky Kalogeiton

One-step generators distilled from Masked Diffusion Models (MDMs) compress multiple sampling steps into a single forward pass, enabling efficient text and image synthesis. However, they suffer two key limitations: they inherit modeling bias from the teacher, and their discrete token outputs block gradient flow, preventing post-distillation refinements such as adversarial training, reward-based fine-tuning, and Test-Time Embedding Optimization (TTEO). In this work, we introduce soft embeddings, a simple relaxation that replaces discrete tokens with the expected embeddings under the generator's output distribution. Soft embeddings preserve representation fidelity for one-step discrete generator while providing a fully differentiable continuous surrogate that is compatible with teacher backbones and tokenizer decoders while cause minimum bias. Integrating soft embeddings into the Di[M]O \citep{zhu2025di} distillation framework (denoted Soft-Di[M]O) makes one-step generators end-to-end trainable and enables straightforward application of GAN-based refinement, differentiable reward fine-tuning, and TTEO. Empirically, across multiple MDM teachers (e.g., MaskBit \citep{weber2024maskbit}, MaskGen \citep{kim2025democratizing}), Soft-Di[M]O achieves state-of-the-art one-step results: improved class-to-image performance, a one-step FID of 1.56 on ImageNet-256 with GAN-based refinement, along with higher than teacher GenEval \citep{ghosh2023geneval} and HPS \citep{wu2023human} scores on text-to-image with reward fine-tuning, and further gains from TTEO.

Computer Vision · Image and Video Generation

Guanlong Jiao, Biqing Huang, Kuan-Chieh Wang, Renjie Liao

Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are often ineffective or inapplicable to them. The straight-line, non-crossing trajectories of flow models pose challenges for diffusion-based approaches but also open avenues for novel solutions. In this paper, we introduce a predictor-corrector-based framework for inversion and editing in flow models. First, we propose Uni-Inv, an effective inversion method designed for accurate reconstruction. Building on this, we extend the concept of delayed injection to flow models and introduce Uni-Edit, a region-aware, robust image editing approach. Our methodology is tuning-free, model-agnostic, efficient, and effective, enabling diverse edits while ensuring strong preservation of edit-irrelevant regions. Extensive experiments across various generative models demonstrate the superiority and generalizability of Uni-Inv and Uni-Edit, even under low-cost settings.

Computer Vision · Image and Video Generation

Xiaofeng Tan, Wanjiang Weng, Haodong Lei, Hongsong Wang

In recent years, motion generative models have undergone significant advancement, yet pose challenges in aligning with downstream objectives. Recent studies have shown that using differentiable rewards to directly align the preference of diffusion models yields promising results. However, these methods suffer from (1) inefficient and coarse-grained optimization with (2) high memory consumption. In this work, we first theoretically and empirically identify the *key reason* of these limitations: the recursive dependence between different steps in the denoising trajectory. Inspired by this insight, we propose **EasyTune**, which fine-tunes diffusion at each denoising step rather than over the entire trajectory. This decouples the recursive dependence, allowing us to perform (1) a dense and fine-grained, and (2) memory-efficient optimization. Furthermore, the scarcity of preference motion pairs restricts the availability of motion reward model training. To this end, we further introduce a **S**elf-refinement **P**reference **L**earning (**SPL**) mechanism that dynamically identifies preference pairs and conducts preference learning. Extensive experiments demonstrate that EasyTune outperforms DRaFT-50 by 7.7% in alignment (MM-Dist) improvement while requiring only 31.16% of its additional memory overhead and achieving a **7.3$\times$** training speedup. The project page is available at this [link](https://xiaofeng-tan.github.io/projects/EasyTune/index.html).

Computer Vision · Image and Video Generation

Tianyu Chen, Yasi Zhang, Zhi Zhang, Peiyu Yu, Shu Wang, Zhendong Wang, Kevin Lin, Xiaofei Wang, Zhengyuan Yang, Linjie Li 等

Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images—resulting in limited coverage and inheriting biases from prior generative models—or (ii) rely *solely* on zero-shot vision–language models (VLMs), whose prompt-based assessments of instruction following, content consistency, and visual quality are often imprecise. To address this, we introduce **EdiVal-Agent** , an automated and fine-grained evaluation framework grounded in an object-centric perspective, designed to assess not only standard single-turn but also multi-turn instruction-based editing with precision. Given an input image, **EdiVal-Agent** first decomposes it into semantically meaningful objects, then synthesizes diverse, context-aware editing instructions while dynamically updating object pools across turns. These two stages enable two novel object-centric metrics tailored for multi-turn evaluation and one global metric of visual quality: 1) EdiVal-IF, which measures instruction following by combining open-vocabulary object detectors for symbolic checks with VLMs for semantic verification on detector-guided crops; 2) EdiVal-CC, which evaluates content consistency by calculating semantic similarity of unchanged objects and background using the evolving object pools; and 3) EdiVal-VQ, which quantifies changes in overall visual quality with human preference models. Instantiating this pipeline, we build **EdiVal-Bench**, a multi-turn editing benchmark covering 9 instruction types and 16 state-of-the-art editing models spanning in-context, flow-matching, and diffusion paradigms. Our results show that *Seedream 4.0* achieves the best overall performance, offering the strongest balance of instruction following, content consistency, and latency. *GPT-Image-1.5* clearly improves over *GPT-Image-1*, especially in content consistency across turns, while *Nano Banana 2* consistently outperforms *Nano Banana* in instruction following and overall score,. Among flow-matching models, *FLUX.2-max* is the strongest baseline, whereas *Qwen-Image-Edit* performs well on the first turn but degrades sharply in later turns, indicating strong exposure bias in multi-turn editing. We demonstrate that **EdiVal-Agent** can be used to identify existing failure modes, thereby informing the development of the next generation of editing models. Our code is available at https://github.com/TianyuCodings/EdiVal.

Computer Vision · Image and Video Generation

Shuzhou Yang, Xiaoyu Li, Xiaodong Cun, Guangzhi Wang, Lingen Li, Ying Shan, Jian Zhang

Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in lengthy production cycles and high manpower costs. To address this issue, we automate this process with generative models, called generative video compositing. This new task strives to adaptively inject identity and motion information of foreground video to the target video in an interactive manner, allowing users to customize the size, motion trajectory, and other attributes of the dynamic elements added in final video. Specifically, we designed a novel Diffusion Transformer (DiT) pipeline based on its intrinsic properties. To maintain consistency of the target video before and after editing, we revised a light-weight DiT-based background preservation branch with masked token injection. As to inherit dynamic elements from other sources, a DiT fusion block is proposed using full self-attention, along with a simple yet effective foreground augmentation for training. Besides, for fusing background and foreground videos with different layouts based on user control, we developed a novel position embedding, named Extended Rotary Position Embedding (ERoPE). Finally, we curated a dataset comprising 61K sets of videos for our new task, called VideoComp. This data includes complete dynamic elements and high-quality target videos. Experiments demonstrate that our method effectively realizes generative video compositing, outperforming existing possible solutions in fidelity and consistency. Project is available at https://gencompositor.github.io/

Applications · Neuroscience, Cognitive Science

Pinyuan Feng, Hossein Adeli, Wenxuan Guo, Fan Cheng, Ethan Hwang, Nikolaus Kriegeskorte

Recent work has demonstrated that complex visual stimuli can be decoded from human brain activity using deep generative models, offering new ways to probe how the brain represents real-world scenes. However, many existing approaches first map brain signals into intermediate image or text feature spaces before guiding the generative process, which obscures the contributions of different brain areas to the final reconstruction output. In this work, we propose NeuroAdapter, a visual decoding framework that directly conditions a latent diffusion model on brain representations, bypassing the need for intermediate feature spaces. Our method demonstrates competitive visual reconstruction quality on public fMRI datasets compared to prior work, while providing greater transparency into how brain signals drive visual reconstruction. To this end, we introduce an Image–Brain BI-directional interpretability framework (IBBI) that analyzes cross-attention patterns across diffusion denoising steps to reveal how different cortical areas influence the unfolding generative trajectory. Our work highlights the potential of end-to-end brain-to-image reconstruction and establishes a path for interpretable neural decoding.

Applications · Language, Speech and Dialog

Zengwei Yao, Wei Kang, Han Zhu, Liyong Guo, Lingxuan Ye, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Long Lin 等

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step inference that introduces considerable computational overhead. In this work, we introduce Flow2GAN, a two-stage framework that combines Flow Matching training for learning generative capabilities with GAN fine-tuning for efficient few-step inference. Specifically, given audio's unique properties, we first improve Flow Matching for audio modeling through: 1) reformulating the objective as endpoint estimation, avoiding velocity estimation difficulties when involving empty regions; 2) applying spectral energy-based loss scaling to emphasize perceptually salient quieter regions. Building on these Flow Matching adaptations, we demonstrate that a further stage of lightweight GAN fine-tuning enables us to obtain few-step (e.g., 1/2/4 steps) generators that produce high-quality audio. In addition, we develop a multi-branch network architecture that processes Fourier coefficients at different time-frequency resolutions, which improves the modeling capabilities compared to prior single-resolution designs. Experimental results indicate that our Flow2GAN delivers high-fidelity audio generation from Mel-spectrograms or discrete audio tokens, achieving highly favorable quality-efficiency trade-offs compared to existing state-of-the-art GAN-based and Flow Matching-based methods. Online demo samples are available at \url{https://flow2gan.github.io}, and the source code is released at \url{https://github.com/k2-fsa/Flow2GAN}.

Applications · Language, Speech and Dialog

Zirui Wu, Lin Zheng, Zhihui Xie, Jiacheng Ye, Jiahui Gao, Shansan Gong, Yansong Feng, Zhenguo Li, Wei BI, Guorui Zhou 等

Diffusion Language Models (DLMs) present a compelling alternative to autoregressive models, offering flexible, any-order infilling without specialized prompting design. However, their practical utility is blocked by a critical limitation: the requirement of a fixed-length masked sequence for generation. This constraint severely degrades code infilling performance when the predefined mask size mismatches the ideal completion length. To address this, we propose DreamOn, a novel diffusion framework that enables dynamic, variable-length generation. DreamOn augments the diffusion process with two length control states, allowing the model to autonomously expand or contract the output length based solely on its own predictions. We integrate this mechanism into existing DLMs with minimal modifications to the training objective and no architectural changes. Built upon Dream-Coder-7B and DiffuCoder-7B, DreamOn achieves infilling performance on par with state-of-the-art autoregressive models on HumanEval-Infilling and SantaCoder-FIM and matches oracle performance achieved with ground-truth length. Our work removes a fundamental barrier to the practical deployment of DLMs, significantly advancing their flexibility and applicability for variable-length generation. Our code is available at https://github.com/DreamLM/DreamOn.

Xinyue Ai, Yutong (Kelly) He, Albert Gu, Russ Salakhutdinov, Zico Kolter, Nicholas Boffi, Max Simchowitz

Log-likelihood evaluation enables important capabilities in generative models, including model comparison, certain fine-tuning objectives, and many downstream applications. Yet paradoxically, some of today's best generative models -- diffusion and flow-based models -- still require hundreds to thousands of neural function evaluations (NFEs) to compute a single likelihood. While recent distillation methods have successfully accelerated sampling to just a few steps, they achieve this at the cost of likelihood tractability: existing approaches either abandon likelihood computation entirely or still require expensive integration over full trajectories. We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude. Our key insight is that in continuous normalizing flows, the coupled ODEs for sampling and likelihood are computed from a shared underlying velocity field, allowing us to jointly distill both the sampling trajectory and cumulative divergence using a single flow map. F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head. Experiments demonstrate F2D2's capability of achieving accurate log-likelihood with few-step evaluations while maintaining high sample quality, solving a long-standing computational bottleneck in flow-based generative models. As an application of our approach, we propose a lightweight self-guidance method that enables a 2-step MeanFlow to outperform a 1024 step flow matching model with only a single additional backward NFE.

Deep Learning · Generative Models and Autoencoders

Dimitri von Rütte, Janis Fluri, Omead Pooladzandi, Bernhard Schölkopf, Thomas Hofmann, Antonio Orvieto

Modern LLM pre-training consumes vast amounts of compute and training data, making the scaling behavior, or scaling laws, of different models a key distinguishing factor. Discrete diffusion language models (DLMs) have been proposed as an alternative to autoregressive language models (ALMs). However, their scaling behavior has not yet been fully explored, with prior work suggesting that they require more data and compute to match the performance of ALMs. We study the scaling behavior of DLMs on different noise types by smoothly interpolating between masked and uniform diffusion while paying close attention to crucial hyperparameters such as batch size and learning rate. Our experiments reveal that the scaling behavior of DLMs strongly depends on the noise type and is considerably different from ALMs. While all noise types converge to similar loss values in compute-bound scaling, we find that uniform diffusion requires more parameters and less data for compute-efficient training compared to masked diffusion, making them a promising candidate in data-constrained training environments. We scale our uniform diffusion model up to 10B parameters trained for $10^{22}$ FLOPs, confirming the predicted scaling behavior and making it the largest publicly known uniform diffusion model to date. In the process of deriving the scaling laws, we reformulate the discrete diffusion ELBO in terms of signal-to-noise ratio, closing the gap to continuous diffusion theory and simplifying both theory and implementation. Training code and models are open-sourced: upon acceptance

Applications · Language, Speech and Dialog

Yinjie Wang, Ling Yang, Bowen Li, Ye Tian, Ke Shen, Mengdi Wang

The extension of diffusion models to language tasks has shown promising results, but their post-training methods remain largely unexplored. We highlight the importance of aligning a diffusion language model’s preference-inference trajectory with its post-training objective. To this end, we propose TraceRL, a trajectory-aware reinforcement learning framework for DLMs that incorporates information from inference trajectories into post-training and is applicable to both full-attention and block-attention diffusion models. We also introduce a diffusion-based value model that enhances training stability and naturally accommodates process rewards. We demonstrate TraceRL’s superiority in enhancing a model’s reasoning ability on complex math and coding tasks, as well as its applicability in scaling block diffusion models to larger block sizes. Employing TraceRL, we derive a series of state-of-the-art diffusion language models, namely TraDo. Although smaller than Qwen2.5-7B-Instruct, TraDo-4B-Instruct consistently outperforms it on complex math reasoning tasks. TraDo-8B-Instruct achieves 4.5% higher accuracy on MATH500 than Qwen2.5-7B-Instruct and 6.6% higher accuracy on LiveCodeBench-V2 than Llama3.1-8B-Instruct. Through curriculum learning, we also develop the first 8B-scale long-CoT diffusion language model. We open-source our code at [https://github.com/Gen-Verse/dLLM-RL](https://github.com/Gen-Verse/dLLM-RL).