论文检索

Applications · Chemistry, Physics, and Earth Sciences

Sungwon Park, Anthony Zhou, Hongjoong Kim, Amir Barati Farimani

Neural operators have emerged as a powerful paradigm for learning discretization-invariant function-to-function mappings in scientific computing. However, many practical systems are inherently stochastic, making principled uncertainty quantification essential for reliable deployment. To address this, we introduce a simple add-on, the *diffusion last layer* (DLL), a lightweight probabilistic head that can be attached to arbitrary neural operator backbones to model predictive uncertainty. Motivated by the relative smoothness and low-dimensional structure often exhibited by PDE solution distributions, DLL parameterizes the conditional output distribution directly in function space through a low-rank Karhunen-Loève expansion, enabling efficient and expressive uncertainty modeling. Across stochastic PDE operator learning benchmarks, DLL improves generalization and uncertainty-aware prediction. Moreover, even in deterministic long-horizon rollout settings, DLL enhances rollout stability and provides meaningful estimates of epistemic uncertainty for backbone neural operators.

Xinyin Ma, Julius Berner, Chao Liu, Arash Vahdat, Weili Nie, Xinchao Wang

Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models excel at global coherence and visual fidelity but suffer from slow inference, while autoregressive models offer efficient and streaming generation at the cost of long-range consistency and exposure bias. We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes. The core idea is a flexible chunking mechanism jointly defined over the temporal axis and denoising steps. This design allows the model to (1) perform flexible chunking according to different device budgets, (2) perform bidirectional inference across chunks for global structure planning, while generating frames autoregressively within each chunk for efficient and fine-grained synthesis, and (3) perform any-order, any-timestep autoregressive generation without the strict causal constraint. Extensive experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule, while offering faster inference.

Applications · Robotics

Chenyu Hui, Xiaodi Huang, Siyu Xu, Yunke Wang, Shan You, Fei Wang, Tao Huang, Chang Xu

Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain gap and limited environmental diversity, resulting in weak real-world generalization. We present an efficient video augmentation framework that converts simulated VLA videos into realistic training videos while preserving task semantics and action trajectories. Our pipeline extracts structured conditions from simulation via video semantic segmentation and video captioning, rewrites captions to diversify environments, and uses a conditional video transfer model to synthesize realistic videos. To make augmentation practical at scale, we introduce a diffusion feature-reuse mechanism that reuses video tokens across adjacent timesteps to accelerate generation, and a coreset sampling strategy that identifies a compact, non-redundant subset for augmentation under limited computation. Extensive experiments on RobotWin 2.0, LIBERO, LIBERO-Plus, and a real robotic platform demonstrate consistent improvements in both task performance and sim-to-real generalization. For example, our method improves RDT-1B by 8% on RobotWin 2.0, and boosts $\pi_0$ by 5.1% on the more challenging LIBERO-Plus benchmark. Code is released in supplementary material.

Theory · Probabilistic Methods

Zhengyan Wan, Yidong Ouyang, Qiang Yao, Liyan Xie, Fang Fang, Hongyuan Zha, Guang Cheng

Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performance compared to the discrete diffusion models. However, their convergence properties and error analysis remain largely unexplored. In this work, we develop a unified framework grounded in stochastic calculus theory to systematically investigate the theoretical properties of discrete flow models. Specifically, by leveraging a Girsanov-type theorem for the path measures of two continuous-time Markov chains (CTMCs), we present a comprehensive error analysis that accounts for both transition rate estimation error and early stopping error. In fact, the estimation error of transition rates has received little attention in existing works. Unlike discrete diffusion models, discrete flow incurs no initialization error caused by truncating the time horizon in the noising process. Building on generator matching and uniformization, we establish non-asymptotic error bounds for distribution estimation without the boundedness condition on oracle transition rates. Furthermore, we derive a faster rate of total variation convergence for the estimated distribution with the boundedness condition, yielding a nearly optimal rate in terms of sample size. Our results provide the first error analysis for discrete flow models. We also study model performance under different settings based on simulation results.

Applications · Chemistry, Physics, and Earth Sciences

Chenguang Wang, Zihan Zhou, LEI BAI, Tianshu Yu

Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches rely on rigid reaction libraries that constrain generalization. We address this gap with a key insight: atom ordering in neural representations matters. Building on this insight, we propose a structure-aware template-free framework that encodes the two-stage nature of chemical reactions as a positional inductive bias. By placing reaction center atoms at the sequence head, our method transforms implicit chemical knowledge into explicit positional patterns that the model can readily capture. The proposed RetroDiT backbone, a graph transformer with rotary position embeddings, exploits this ordering to prioritize chemically critical regions. Combined with discrete flow matching, our approach decouples training from sampling and enables generation in 20--50 steps versus 500 for prior diffusion methods. Our method achieves state-of-the-art performance on both USPTO-50k (61.2\% top-1) and the large-scale USPTO-Full (51.3\% top-1) with predicted reaction centers. With oracle centers, performance reaches 71.1\% and 63.4\% respectively, surpassing foundation models trained on 10 billion reactions while using orders of magnitude less data. Ablation studies further reveal that structural priors outperform brute-force scaling: a 280K-parameter model with proper ordering matches a 65M-parameter model without it.

Theory · Probabilistic Methods

Zhengyan Wan, Yidong Ouyang, Liyan Xie, Hongyuan Zha, Fang Fang, Guang Cheng

Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A line of recent work has studied samplers for discrete diffusion models, such as tau-leaping and Euler solver. However, these samplers require a large number of iterations to control discretization error, since the transition rates are frozen in time and evaluated at the initial state within each time interval. Moreover, theoretical results for these samplers often require boundedness conditions of the transition rate or they focus on a specific type of source distributions. To address those limitations, we establish non-asymptotic discretization error bounds for those samplers without any restriction on transition rates and source distributions, under the framework of discrete flow models. Furthermore, by analyzing a one-step lower bound of the Euler sampler, we propose two corrected samplers: \textit{time-corrected sampler} and \textit{location-corrected sampler}, which can reduce the discretization error of tau-leaping and Euler solver with almost no additional computational cost. We rigorously show that the location-corrected sampler has a lower complexity than existing parallel samplers. We validate the effectiveness of the proposed method by achieving better generation quality with reduced inference time on simulations and text-to-image generation tasks.

Applications · Chemistry, Physics, and Earth Sciences

Francisco Giral, Álvaro Sevillano, Ignacio Perez, Ricardo Vinuesa, Soledad Le Clainche

Urban wind flow reconstruction is essential for assessing air quality, heat dispersion, and pedestrian comfort, yet remains challenging when only sparse sensor data are available. We propose GenDA, a generative data assimilation framework that reconstructs high-resolution wind fields on unstructured meshes from limited observations. The model employs a multiscale graph-based diffusion architecture trained on computational fluid dynamics (CFD) simulations and interprets classifier-free guidance as a learned posterior reconstruction mechanism: the unconditional branch learns a geometry-aware flow prior, while the sensor-conditioned branch injects observational constraints during sampling. This formulation enables obstacle-aware reconstruction and generalization across unseen geometries, wind directions, and mesh resolutions without retraining. We consider both sparse fixed sensors and trajectory-based observations using the same reconstruction procedure. When evaluated against supervised graph neural network (GNN) baselines and classical reduced-order data assimilation methods, GenDA reduces the relative root-mean-square error (RRMSE) by 25-57% and increases the structural similarity index (SSIM) by 23-33% across the tested meshes. Experiments are conducted on Reynolds-averaged Navier-Stokes (RANS) simulations of a real urban neighborhood in Bristol, United Kingdom, at a characteristic Reynolds number of $\mathrm{Re}\approx2\times10^{7}$, featuring complex building geometry and irregular terrain. The proposed framework provides a scalable path toward generative, geometry-aware data assimilation for environmental monitoring in complex domains.

Deep Learning · Theory

Lev Fedorov, Michael Sander, Romuald Elie, Pierre Marion, Mathieu Lauriere

Transformers have revolutionized deep learning across various domains but understanding the precise token dynamics remains a theoretical challenge. Existing theories of deep Transformers with layer normalization typically predict that tokens cluster to a single point; however, these results rely on deterministic weight assumptions, which fail to capture the standard initialization scheme in Transformers. In this work, we show that accounting for the intrinsic stochasticity of random initialization alters this picture. More precisely, we analyze deep Transformers where noise arises from the random initialization of value matrices. Under diffusion scaling and token-wise RMS normalization, we prove that, as the number of Transformer layers goes to infinity, the discrete token dynamics converge to an interacting-particle system on the sphere where tokens are driven by a \emph{common} matrix-valued Brownian noise. In this limit, we show that initialization noise prevents the collapse to a single cluster predicted by deterministic models. For two tokens, we prove a phase transition governed by the interaction strength and the token dimension: unlike deterministic attention flows, antipodal configurations become attracting with positive probability. Numerical experiments confirm the predicted transition, reveal that antipodal formations persist for more than two tokens, and demonstrate that suppressing the intrinsic noise degrades accuracy.

Deep Learning · Other Representation Learning

FANGZHENG WU, Brian Summa

Attention sinks (tokens that receive disproportionate attention mass) are often assumed to be functionally important in autoregressive language models. Whether such sinks are necessary in diffusion transformers remains unclear. We present a causal analysis of attention sinks in text-to-image diffusion models, dynamically identifying dominant attention recipients based on incoming attention mass. Using paired, training-free interventions along the score and value paths, we test sink necessity across layers, denoising phases, and architectures. Across large-scale evaluations on 553 GenEval prompts with Stable Diffusion~3 and corroborating experiments on SDXL, we find that removing \textbf{these sinks} does not degrade text-image alignment or preference proxies under standard settings ($k{=}1$), with a metric-dependent boundary on HPS-v2 emerging only under stronger interventions ($k \geq 10$). We additionally quantify perceptual and distributional shifts relative to baseline outputs, showing that suppressing dominant recipients can alter appearance without affecting alignment or preference scores. Together, these results clarify that attention sinks are not functionally necessary for \emph{semantic alignment} in diffusion transformers, while revealing a metric-dependent boundary: preference proxies show sink-specific degradation under stronger interventions ($k \geq 10$), whereas alignment (CLIP-T) remains robust across all tested conditions.

Deep Learning · Large Language Models

Ruishu Zhu, Zhihao Huang, Jiacheng Sun, Ping Luo, Hongyuan Zhang, Xuelong Li

Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce \textbf{ViewMask-1-to-3}, formulating multi-view synthesis as a discrete sequence modeling problem where each viewpoint is represented as visual tokens from MAGVIT-v2. Through \textbf{masked token prediction}, our approach \textbf{enables progressive multi-view generation via iterative token unmasking}, unifying language and vision in a shared token space. Importantly, simple random masking combined with self-attention naturally encourages cross-view consistency without specialized architectures or 3D geometric priors. Our method outperforms the baseline on the GSO and 3D-FUTURE benchmarks, ranking first on average across standard image metrics and improving IoU by 10.6\% on 3D-FUTURE. This validates discrete diffusion as a promising candidate for multi-view generation.

Deep Learning · Large Language Models

Zhiwei Zhang, Yudi Lin, Linlin Wu, Fali Wang, Yi Xin, Xiaomin Li, Minhua Lin, Xianfeng Tang, Qi He, Suhang Wang

Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, enabling parallel sequence generation and flexible token generation orders. Machine unlearning plays a critical role in mitigating legal and ethical risks by removing the influence of specific training examples from trained models. While unlearning has been extensively studied for autoregressive language models, its applicability to DLMs remains unexplored. The architectural differences of DLMs raise new challenges for effective and robust unlearning that are not addressed by existing methods. In this paper, we present the first comprehensive study of unlearning for DLMs. Through systematic empirical analysis, we show that unlearning performance in DLMs is highly sensitive to generation hyperparameters, highlighting the need for evaluation across diverse generation settings. We further observe that DLMs tend to reproduce unlearned information when target inputs are embedded within informative contexts, due to their ability to incorporate both prefix and suffix conditioning, which increases vulnerability to elicitation attacks and weakens the robustness of existing unlearning methods. To design a robust unlearning method, we propose an adversarial reinforcement learning framework, where a context generator adversarially produces informative contexts to elicit unlearned knowledge, while the DLM is optimized to suppress undesired recall. We further introduce novel components to address credit assignment and stability issues in this adversarial learning setup. Extensive experiments demonstrate that our method significantly improves unlearning effectiveness while preserving model utility. Our code is available at: https://anonymous.4open.science/r/dllm_unlearning-771D/

Deep Learning · Large Language Models

Joshua Ong, Yu Zhao, Mihaela C. Stoian, Wenda Li, Shay Cohen, Eleonora Giunchiglia

While plan-and-infill decoding in Masked Diffusion Models (MDMs) shows promise for mathematical and code reasoning, performance remains highly sensitive to slot infilling order, often yielding substantial output variance. We introduce DiffuSearch, a framework that formulates slot selection as decision making and optimises infilling orders through Monte Carlo Tree Search (MCTS). DiffuSearch uses look-ahead simulations to evaluate partial completions before commitment, systematically exploring the combinatorial space of generation orders. Experiments show an average improvement of 3.2% over autoregressive baselines and 8.0% over baseline plan-and-infill, with notable gains of 19.5% on MBPP and 4.9% on MATH500. Our analysis reveals that while DiffuSearch predominantly follows sequential ordering, incorporating non-sequential generation is essential for maximising performance. We observe that larger exploration constants, rather than increased simulations, are necessary to overcome model confidence biases and discover effective orderings. These findings establish MCTS-based planning as an effective approach for enhancing generation quality in MDMs.

Deep Learning · Generative Models and Autoencoders

Hongzhou Zhu, Min Zhao, Guande He, Hang Su, Chongxuan Li, Jun Zhu

To achieve real-time video generation, current approaches distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models. This process involves an *architectural gap*, as it converts full attention into causal attention. In this paper, we demonstrate that existing methods fail to bridge this gap theoretically, leading to suboptimal performance. Specifically, these methods employ ODE distillation to initialize the AR student, where a key requirement is *injectivity*. We figure out that for an AR student, *frame-level injectivity* must hold: each noisy frame must map to a unique clean frame under the PF-ODE of the *AR teacher*. We theoretically prove that existing methods, which distill an AR student from a bidirectional teacher, violate this frame-level injectivity. Consequently, the student fails to recover the teacher's flow map and instead learns a conditional expectation, resulting in subpar performance. To address this issue, we propose *Causal Forcing*, which employs an AR teacher for ODE initialization, thereby effectively bridging the architectural gap. Empirical results show that our method outperforms all baselines across all metrics, surpassing the SOTA Self-Forcing by 19.3\% in Dynamic Degree, 8.7\% in VisionReward, and 16.7\% in Instruction Following.

Social Aspects · Privacy

Yanhao Wei, Xiaokang Zhao, Boheng Li, Yang Zhang, Run Wang

Text-to-Image diffusion models have achieved remarkable success in image generation and are increasingly fine-tuned for personalized use cases. However, many personalized models may incorporate unauthorized data (e.g., copyrighted materials) during the fine-tuning process, raising growing concerns about potential copyright infringements. Existing methods either require intrusive modifications to the images to be protected, which not only fail to safeguard previously released images but may also degrade image quality, or rely on the availability of the pre-fine-tuned model, thereby limiting their applicability. To bridge this gap, in this paper, we propose the first non-intrusive copyright authentication framework without pre-fine-tuned model. We reveal that if a model is fine-tuned on a specific image, it learns the denoising trajectory of that image across varying noise levels, allowing it to stably reconstruct the image even under noise perturbations. Based on this insight, we propose Reliable dEteCtion Of unauthorized data usage via inVErsion Robustness (RECOVER), an effective non-intrusive detection method without pre-fine-tuned model. Unlike existing methods that rely on external watermarks or discrepancies between the suspect and pre-fine-tuned models, RECOVER directly leverages the robustness observed during the inversion–reconstruction process of the suspect model to determine whether an image was used for fine-tuning. Extensive experiments demonstrate that RECOVER is effective across a wide range of scenarios, consistently outperforming existing methods.

Reinforcement Learning · Multi-agent

Hao Xiang Li, Michael Amir, Amanda Prorok

The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performance, promising to fundamentally reshape how we deploy multi-agent systems in domains such as warehouse logistics and windfarm management. However, current co-design methods collapse under high dimensional environment design spaces and suffer from sample inefficiency when addressing moving targets inherent to joint optimisation. We address this by developing **Diffusion Co-Design** (DiCoDe), a scalable and sample-efficient co-design framework incorporating two core innovations. We introduce Projected Universal Guidance (PUG), enabling exploration of constraint-satisfying reward-maximising environments, and devise a critic distillation mechanism to transfer knowledge from the reinforcement learning loop to a guided diffuision model. Together, these improvements lead to superior environment-policy pairs when validated on challenging multi-agent co-design benchmarks, for example, exceeding state-of-the art in a warehouse setting with 39% higher rewards and 66% fewer simulation steps.

Deep Learning · Large Language Models

Kevin Zhai, Sabbir Mollah, Zhenyi Wang, Mubarak Shah

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade effects where initial inconsistencies misguide the remaining generation. Existing revision strategies attempt to mitigate this by relying on static confidence scores, but these signals are inherently myopic; inconsistent tokens frequently appear confident to the model itself. To address this, we propose Context-Robust Remasking (CoRe), a training-free framework for inference-time revision. We introduce a new selection paradigm: rather than trusting static token probabilities, we identify *context-brittle* tokens by probing their sensitivity to adversarial perturbations. We formalize revision as a robust optimization problem targeting worst-case context shifts. CoRe efficiently approximates this objective to expose unstable tokens, prioritizing them for revision. On LLaDA-8B-Base, CoRe delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and boosting performance on code generation (MBPP) by up to $+9.2\\%$.

Deep Learning · Generative Models and Autoencoders

Haofei Xu, Rundi Wu, Philipp Henzler, Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Marc Pollefeys, Andreas Geiger, Federico Tombari, Michael Niemeyer

State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures or necessitate compressing geometry into latent spaces to leverage pre-trained latent diffusion models. In this work, we demonstrate that such architectural overhead is unnecessary. We introduce a minimalist pixel-space Diffusion Transformer built on a plain ViT, which operates directly on raw point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion-based approaches, we train our diffusion backbone entirely from scratch, eliminating the need for point map tokenizers. We show that this streamlined approach yields results superior to complex latent-based diffusion models while remaining significantly simpler than hybrid alternatives. Notably, our model produces sharper geometric structures and achieves significantly better results on highly ambiguous regions, such as transparent objects.

Applications · Health / Medicine

Ziquan Wei, Tingting Dan, Guorong Wu

Despite the central role of sensor-derived measurements such as imaging traits and plasma biomarkers in biomedical research and clinical practice, existing generative models for disease prediction largely depend on event-level representations from hospital and registry data. Given the multi-factorial nature of human disease, the absence of human-environment interaction modeling limits the capacity for personalized disease modeling and clinical decision support. To address this limitation, we propose a generative model with human-environment interaction for \textit{in silico} modeling of disease reasoning, a conditioned latent diffusion framework that establishes the connection between multi-organ sensor data with tokenized healthcare events. Specifically, we introduce a novel geometric diffusion model to characterize the temporal evolution of complex data representation such as brain networks (region-to-region connectivity encoded in a graph), in parallel with diffusion models for tabular data from other organ systems. Together, we integrate the generative model with digitalized human-environment interaction (coined DiffDT) for simulated intervention and reasoning of future disease trajectories. We conduct extensive experiments on the UK Biobank (UKB) dataset, which contains organ-specific imaging traits, including brain (44,834), heart (23,987), liver (28,722), and kidney (32,155), along with nearly 500k medical history sequences (age range: 25$\sim$89 years). Our DiffDT achieves significant improvements over state-of-the-art human disease autoregressive models and imaging trait generative baselines.

Deep Learning · Large Language Models

Wenzheng Song, Pei Chen, Yichen Tan, Zejian Li, Lingyun Sun

Multi-modal Diffusion Language Models (MDLMs) have emerged as a powerful alternative to autoregressive models in vision-language understanding, offering advantages in bidirectional context modeling and parallel decoding. However, existing MDLMs suffer from severe visual hallucinations due to the static nature of visual perception. Unlike autoregressive models, MDLMs lack the sequential dependency required to dynamically interact with visual content. Therefore, MDLMs rely on fixed visual features encoded at initialization, causing the denoising process to drift toward language priors and lose its anchor to visual evidence. In this paper, we propose VGR (Visual-Guided Refinement), a framework that enables MDLMs to revisit visual details by exploiting diffusion dynamics. Our key insight is that the temporal trajectory of confidence during denoising reveals intrinsic uncertainty: while grounded tokens converge smoothly, hallucinated ones exhibit pronounced confidence fluctuation. VGR utilizes this fluctuation signal to detect uncertain spans and corrects them through targeted visual evidence extraction and in-place remasking. Extensive experiments on image captioning and hallucination evaluation benchmarks demonstrate that our method significantly reduces hallucinations and recalls more details, achieving state-of-the-art performance among MDLMs.

Deep Learning · Large Language Models

Liang Zheng, Bowen Shi, Yitao Hu, Jiawei Zhang, Ruofan Li, Guotao Yang, Zhixin Zhao, Zhengchao Wang, Sheng Chen, Wenxin Li 等

Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive models, leveraging simultaneous denoising to enable global planning and iterative refinement. These properties make dLLMs particularly attractive for long-context generation. However, deploying dLLMs faces a prohibitive memory capacity barrier, as existing inference systems are inefficient for the diffusion paradigm. We observe that current inference systems are misaligned with dLLMs. Unlike autoregressive models, whose memory footprint is dominated by the cumulative KV-Cache, dLLMs are bottlenecked by transient activations rematerialized per step. Moreover, generic memory reuse mechanisms lack the global visibility to handle dynamic memory peaks of dLLMs, which alternate between logits and feed-forward networks. To address these challenges, we present Mosaic, a memory-efficient inference system that shifts dLLM execution from local, static memory management to a global, dynamic paradigm. Mosaic integrates (i) a mask-only logits kernel eliminating redundant activation materialization, (ii) a lazy chunking optimizer using online heuristics to adaptively tame dynamic memory peaks, and (iii) a global memory manager leveraging virtual addressing to mitigate memory fragmentation. Extensive evaluations show that Mosaic reduces the memory peak-to-average ratio by 2.71$\times$ on average and increases the maximum supportable inference sequence length on identical hardware by 15.30--32.34$\times$. Crucially, Mosaic is training-free and preserves exact model outputs, while simultaneously reducing end-to-end latency by 2.5\%--55.4\%.