NeurIPS 2025 Papers

Molecular synthetic space projecting is a critical technique in de novo molecular design, which aims to rectify molecules without synthesizability guarantee by converting them into synthetic postfix notations. However, the vast synthesizable chemical space and the discrete data modalities involved pose significant challenges to postfix notation conversion benchmarking. In this paper, we exploit conditional probability transitions in discrete state space and introduce MoleBridge, a deep generative model built on the Markov bridge approach for designing postfix notations of molecular synthesis pathways. MoleBridge consists of two iterative optimizations: i) Autoregressive extending of notation tokens from molecular graphs, and ii) generation of discrete reaction postfix notations through Markov bridge, where noisy token blocks are progressively denoised over multi-step iterations. For the challenging second iteration, which demands sensitivity to incorrect generative probability paths within intricate chemical spaces, we employ a thinking and denoising separation approach to denoise. Empirically, we find that MoleBridge is capable of accurately predicting synthesis pathways while exhibiting excellent performance in a variety of application scenarios.

Generating diverse, all‐atom conformational ensembles of dynamic proteins such as G‐protein‐coupled receptors (GPCRs) is critical for understanding their function, yet most generative models simplify atomic detail or ignore conformational diversity altogether. We present latent diffusion for full protein generation (LD-FPG), a framework that constructs complete all‐atom protein structures, including every side‐chain heavy atom, directly from molecular dynamics (MD) trajectories. LD-FPG employs a Chebyshev graph neural network (ChebNet) to obtain low‐dimensional latent embeddings of protein conformations, which are processed using three pooling strategies: blind, sequential and residue‐based. A diffusion model trained on these latent representations generates new samples that a decoder, optionally regularized by dihedral‐angle losses, maps back to Cartesian coordinates. Using D2R-MD, a $2\mu\text{s}$ MD trajectory (12 000 frames) of the human dopamine D$2$ receptor in a membrane environment, the sequential and residue-based pooling strategies reproduce the reference ensemble with high structural fidelity (all‐atom lDDT \~ $0.7$; $C\alpha$-lDDT \~ $0.8$) and recovers backbone and side‐chain dihedral‐angle distributions with a Jensen–Shannon divergence $<0.03$ compared to the MD data. LD-FPG thereby offers a practical route to system‐specific, all‐atom ensemble generation for large proteins, providing a promising tool for structure‐based therapeutic design on complex, dynamic targets. The D2R-MD dataset and our implementation are freely available to facilitate further research.

Diffusion models have achieved remarkable success in image generation and editing tasks. Inversion within these models aims to recover the latent noise representation for a real or generated image, enabling reconstruction, editing, and other downstream tasks. However, to date, most inversion approaches suffer from an intrinsic trade-off between reconstruction accuracy and editing flexibility. This limitation arises from the difficulty of maintaining both semantic alignment and structural consistency during the inversion process. In this work, we introduce **Dual-Conditional Inversion (DCI)**, a novel framework that jointly conditions on the source prompt and reference image to guide the inversion process. Specifically, DCI formulates the inversion process as a dual-condition fixed-point optimization problem, minimizing both the latent noise gap and the reconstruction error under the joint guidance. This design anchors the inversion trajectory in both semantic and visual space, leading to more accurate and editable latent representations. Our novel setup brings new understanding to the inversion process. Extensive experiments demonstrate that DCI achieves state-of-the-art performance across multiple editing tasks, significantly improving both reconstruction quality and editing precision. Furthermore, we also demonstrate that our method achieves strong results in reconstruction tasks, implying a degree of robustness and generalizability approaching the ultimate goal of the inversion process. Our codes are available at: [https://github.com/Lzxhh/Dual-Conditional-Inversion](https://github.com/Lzxhh/Dual-Conditional-Inversion)

The pursuit of efficient and controllable high-quality content generation stands as a pivotal challenge in artificial intelligence-generated content (AIGC). While one-step generators, refined through diffusion distillation techniques, offer excellent generation quality and computational efficiency, adapting them to new control conditions—such as structural constraints, semantic guidelines, or external inputs—poses a significant challenge. Conventional approaches often necessitate computationally expensive modifications to the base model and subsequent diffusion distillation. This paper introduces Noise Consistency Training (NCT), a novel and lightweight approach to directly integrate new control signals into pre-trained one-step generators without requiring access to original training images or retraining the base diffusion model. NCT operates by introducing an adapter module and employs a noise consistency loss in the noise space of the generator. This loss aligns the adapted model's generation behavior across noises that are conditionally dependent to varying degrees, implicitly guiding it to adhere to the new control. This training objective can be interpreted as aligning the adapted generator with the intractable conditional distribution defined by a discriminative model and the one-step generator from moment-matching perspectives. NCT is modular, data-efficient, and easily deployable, relying only on the pre-trained one-step generator and a control signal model. Extensive experiments demonstrate that NCT achieves state-of-the-art controllable generation in a single forward pass, surpassing existing multi-step and distillation-based methods in both generation quality and computational efficiency.

We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. FramePack compresses input frame contexts with frame-wise importance so that more frames can be encoded within a fixed context length, with more important frames having longer contexts. The frame importance can be measured using time proximity, feature similarity, or hybrid metrics. The packing method allows for inference with thousands of frames and training with relatively large batch sizes. We also present drift prevention methods to address observation bias (error accumulation), including early-established endpoints, adjusted sampling orders, and discrete history representation. Ablation studies validate the effectiveness of the anti-drifting methods in both single-directional video streaming and bi-directional video generation. Finally, we show that existing video diffusion models can be finetuned with FramePack, and analyze the differences between different packing schedules.

Transferring appearance to 3D assets using different representations of the appearance object - such as images or text - has garnered interest due to its wide range of applications in industries like gaming, augmented reality, and digital content creation. However, state-of-the-art methods still fail when the geometry between the input and appearance objects is significantly different. A straightforward approach is to directly apply a 3D generative model, but we show that this ultimately fails to produce appealing results. Instead, we propose a principled approach inspired by universal guidance. Given a pretrained rectified flow model conditioned on image or text, our training-free method interacts with the sampling process by periodically adding guidance. This guidance can be modeled as a differentiable loss function, and we experiment with two different types of guidance including part-aware losses for appearance and self-similarity. Our experiments show that our approach successfully transfers texture and geometric details to the input 3D asset, outperforming baselines both qualitatively and quantitatively. We also show that traditional metrics are not suitable for evaluating the task due to their inability of focusing on local details and comparing dissimilar inputs, in absence of ground truth data. We thus evaluate appearance transfer quality with a GPT-based system objectively ranking outputs, ensuring robust and human-like assessment, as further confirmed by our user study. Beyond showcased scenarios, our method is general and could be extended to different types of diffusion models and guidance functions. Project Page: *[https://sayands.github.io/guideflow3d](https://sayands.github.io/guideflow3d)*

Reinforcement learning (RL) systems, while achieving remarkable success across various domains, are vulnerable to adversarial attacks. This is especially a concern in vision-based environments where minor manipulations of high-dimensional image inputs can easily mislead the agent's behavior. To this end, various defenses have been proposed recently, with state-of-the-art approaches achieving robust performance even under large state perturbations. However, after closer investigation, we found that the effectiveness of the current defenses is due to a fundamental weakness of the existing $l_p$ norm-constrained attacks, which can barely alter the semantics of image input even under a relatively large perturbation budget. In this work, we propose SHIFT, a novel policy-agnostic diffusion-based state perturbation attack to go beyond this limitation. Our attack is able to generate perturbed states that are semantically different from the true states while remaining realistic and history-aligned to avoid detection. Evaluations show that our attack effectively breaks existing defenses, including the most sophisticated ones, significantly outperforming existing attacks while being more perceptually stealthy. The results highlight the vulnerability of RL agents to semantics-aware adversarial perturbations, indicating the importance of developing more robust policies.

Protein fitness optimization involves finding a protein sequence that maximizes desired quantitative properties in a combinatorially large design space of possible sequences. Recent advances in steering protein generative models (e.g., diffusion models and language models) with labeled data offer a promising approach. However, most previous studies have optimized surrogate rewards and/or utilized large amounts of labeled data for steering, making it unclear how well existing methods perform and compare to each other in real-world optimization campaigns where fitness is measured through low-throughput wet-lab assays. In this study, we explore fitness optimization using small amounts (hundreds) of labeled sequence-fitness pairs and comprehensively evaluate strategies such as classifier guidance and posterior sampling for guiding generation from different discrete diffusion models of protein sequences. We also demonstrate how guidance can be integrated into adaptive sequence selection akin to Thompson sampling in Bayesian optimization, showing that plug-and-play guidance strategies offer advantages over alternatives such as reinforcement learning with protein language models. Overall, we provide practical insights into how to effectively steer modern generative models for next-generation protein fitness optimization.

Text-guided 3D editing aims to locally modify 3D objects based on editing prompts, which has significant potential for applications in 3D game and film domains. Existing methods typically follow a view-agnostic paradigm: editing 2D view images indiscriminately and projecting them back into 3D space. However, the view-agnostic paradigm neglects view consistency and view-specific characteristics, resulting in spatial inconsistencies and imprecise control over edited regions. In this study, we argue that progressive view-oriented paradigm can effectively address these issues, which projects the editing information from a editing-sensitive view to other editing-insensitive views. Based on this paradigm, we design Pro3D-Editor, a new framework. Extensive experiments demonstrate that our method outperforms existing approaches in terms of editing accuracy and spatial consistency.

Paucity of medical data severely limits the generalizability of diagnostic ML models, as the full spectrum of disease variability can not be represented by a small clinical dataset. To address this, diffusion models (DMs) have been considered as a promising avenue for synthetic image generation and augmentation. However, they frequently produce _medically inaccurate_ images, deteriorating the model performance. Expert domain knowledge is critical for synthesizing images that correctly encode clinical information, especially when data is scarce and quality outweighs quantity. Existing approaches for incorporating human feedback, such as reinforcement learning (RL) and Direct Preference Optimization (DPO), rely on robust reward functions or demand labor-intensive expert evaluations. Recent progress in Multimodal Large Language Models (MLLMs) reveals their strong visual reasoning capabilities, making them adept candidates as evaluators. In this work, we propose a novel framework, coined MAGIC (**M**edically **A**ccurate **G**eneration of **I**mages through AI-Expert **C**ollaboration), that synthesizes clinically accurate skin disease images for data augmentation. Our method creatively translates expert-defined criteria into actionable feedback for image synthesis of DMs, significantly improving clinical accuracy while reducing the direct human workload. Experiments demonstrate that our method greatly improves the clinical quality of synthesized skin disease images, with outputs aligning with dermatologist assessments. Additionally, augmenting training data with these synthesized images improves diagnostic accuracy by +9.02% on a challenging 20-condition skin disease classification task, and by +13.89% in the few-shot setting. Beyond image synthesis, MAGIC illustrates a task-centric alignment paradigm: instead of adapting MLLMs to niche medical tasks, it adapts tasks to the evaluative strengths of general-purpose MLLMs by decomposing domain knowledge into attribute-level checklists. This design offers a scalable and reliable path for leveraging foundation models in specialized domains.

Part of the success of diffusion models stems from their ability to perform iterative refinement, i.e., repeatedly correcting outputs during generation. However, modern masked discrete diffusion lacks this capability: when a token is generated, it cannot be updated again, even when it introduces an error. Here, we address this limitation by introducing the remasking diffusion model (ReMDM) sampler, a method that can be applied to pretrained masked diffusion models in a principled way and that is derived from a discrete diffusion model with a custom remasking backward process. Most interestingly, ReMDM endows discrete diffusion with a form of inference-time compute scaling. By increasing the number of sampling steps, ReMDM generates natural language outputs that approach the quality of autoregressive models, whereas when the computation budget is limited, ReMDM better maintains quality. ReMDM also improves sample quality of masked diffusion models for discretized images, and in scientific domains such as molecule design, ReMDM facilitates diffusion guidance and pushes the Pareto frontier of controllability relative to classical masking and uniform noise diffusion. When applied to large pretrained diffusion language models, ReMDM boosts the model’s performance on downstream tasks requiring factual knowledge grasp and reasoning ability.

Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative models, particularly diffusion models, based approaches that directly learn the posterior may suffer from inflexibility—they require conditioning signals during training, support only a fixed number of input views, and need complete retraining for different measurements. Recent diffusion-based methods have attempted to address this by combining prior models with likelihood updates, but they rely on heuristic fixed step sizes for the likelihood update that lead to slow convergence and suboptimal reconstruction quality. We advance this line of approach by integrating our novel Forward Curvature-Matching (FCM) update method with diffusion sampling. Our method dynamically determines optimal step sizes using only forward automatic differentiation and finite-difference curvature estimates, enabling precise optimization of the likelihood update. This formulation enables high-fidelity reconstruction from both single-view and multi-view inputs, and supports various input modalities through simple operator substitution—all without retraining. Experiments on ShapeNet and CO3D datasets demonstrate that our method achieves superior reconstruction quality at matched or lower NFEs, yielding higher F-score and lower CD and EMD, validating its efficiency and adaptability for practical applications. Code is available at https://github.com/Seunghyeok0715/FCM.

Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data and struggle to generalize to the immense variability and open-set nature of real-world acoustic scenes. Inspired by the success of generative foundation models, we investigate whether pre-trained text-guided audio diffusion models can overcome these limitations. We make a surprising discovery: zero-shot source separation can be achieved purely through a pre-trained text-guided audio diffusion model under the right configuration. Our method, named ZeroSep, works by inverting the mixed audio into the diffusion model's latent space and then using text conditioning to guide the denoising process to recover individual sources. Without any task-specific training or fine-tuning, ZeroSep repurposes the generative diffusion model for a discriminative separation task and inherently supports open-set scenarios through its rich textual priors. ZeroSep is compatible with a variety of pre-trained text-guided audio diffusion backbones and delivers strong separation performance on multiple separation benchmarks, surpassing even supervised methods.

Diffusion in transformer is central to advances in high-quality multimodal generation but suffer from high inference latency due to their iterative nature. Inspired by speculative decoding's success in accelerating large language models, we propose Approximate Speculative Diffusion with Speculative Verification (ASDSV), a novel method to enhance the efficiency of diffusion models. Adapting speculative execution to diffusion processes presents unique challenges. First, the substantial computational cost of verifying numerous speculative steps for continuous, high-dimensional outputs makes traditional full verification prohibitively expensive. Second, determining the optimal number of speculative steps $K$ involves a trade-off between potential acceleration and verification success rates. To address these, ASDSV introduces two key innovations: 1) A speculative verification technique, which leverages the observed temporal correlation between draft and target model outputs, efficiently validates $K$ speculative steps by only checking the alignment of the initial and final states, significantly reducing verification overhead. 2) A multi-stage speculative strategy that adjusts $K$ according to the denoising phase—employing smaller $K$ during volatile early stages and larger $K$ during more stable later stages to optimize the balance between speed and quality. We apply ASDSV to state-of-the-art diffusion transformers, including Flux.1-dev for image generation and Wan2.1 for video generation. Extensive experiments demonstrate that ASDSV achieves up to 1.77$\times$-3.01$\times$ speedup in model inference with a minimal 0.3\%-0.4\% drop in VBench score, showcasing its effectiveness in accelerating multimodal diffusion models without significant quality degradation. The code will be publicly available once the acceptance of the paper.

Generative depth estimation methods leverage the rich visual priors stored in pretrained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic degradation in the image generation capability of the pretrained model. We introduce MERGE, a unified model for image generation and depth estimation, starting from a fixed-parameters pretrained text-to-image model. MERGE demonstrates that the pretrained text-to-image model can do more than image generation but also expand to depth estimation effortlessly. Specifically, MERGE introduces a plug-and-play framework that enables seamless switching between image generation and depth estimation modes through simple and pluggable converters. Meanwhile, we propose a Group Reuse Mechanism to encourage parameter reuse and improve the utilization of the additional learnable parameter. MERGE unleashes the powerful depth estimation capability of the pretrained text-to-image model while preserving its original image generation ability. Compared to other unified models for image generation and depth estimation, MERGE achieves state-of-the-art performance across multiple depth estimation benchmarks. The code and model will be made available.

We present Stable Part Diffusion 4D (SP4D), a framework for generating paired RGB and kinematic part videos from monocular inputs. Unlike conventional part segmentation methods that rely on appearance-based semantic cues, SP4D learns to produce kinematic parts --- structural components aligned with object articulation and consistent across views and time. SP4D adopts a dual-branch diffusion model that jointly synthesizes RGB frames and corresponding part segmentation maps. To simplify architecture and flexibly enable different part counts, we introduce a spatial color encoding scheme that maps part masks to continuous RGB-like images. This encoding allows the segmentation branch to share the latents VAE from the RGB branch, while enabling part segmentation to be recovered via straightforward post-processing. A Bidirectional Diffusion Fusion (BiDiFuse) module enhances cross-branch consistency, supported by a contrastive part consistency loss to promote spatial and temporal alignment of part predictions. We demonstrate that the generated 2D part maps can be lifted to 3D to derive skeletal structures and harmonic skinning weights with few manual adjustments. To train and evaluate SP4D, we construct KinematicParts20K, a curated dataset of over 20K rigged objects selected and processed from Objaverse XL, each paired with multi-view RGB and part video sequences. Experiments show that SP4D generalizes strongly to diverse scenarios, including real-world videos, novel generated objects, and rare articulated poses, producing kinematic-aware outputs suitable for downstream animation and motion-related tasks.

Planning with pretrained diffusion models has emerged as a promising approach for solving test-time guided control problems. Standard gradient guidance typically performs optimally under convex, differentiable reward landscapes. However, it shows substantially reduced effectiveness in real-world scenarios with non-convex objectives, non-differentiable constraints, and multi-reward structures. Furthermore, recent supervised planning approaches require task-specific training or value estimators, which limits test-time flexibility and zero-shot generalization. We propose a Tree-guided Diffusion Planner (TDP), a zero-shot test-time planning framework that balances exploration and exploitation through structured trajectory generation. We frame test-time planning as a tree search problem using a bi-level sampling process: (1) diverse parent trajectories are produced via training-free particle guidance to encourage broad exploration, and (2) sub-trajectories are refined through fast conditional denoising guided by task objectives. TDP addresses the limitations of gradient guidance by exploring diverse trajectory regions and harnessing gradient information across this expanded solution space using only pretrained models and test-time reward signals. We evaluate TDP on three diverse tasks: maze gold-picking, robot arm block manipulation, and AntMaze multi-goal exploration. TDP consistently outperforms state-of-the-art approaches on all tasks. The project page can be found at: https://tree-diffusion-planner.github.io

Text-to-Audio-Video (T2AV) generation aims to produce temporally and semantically aligned visual and auditory content from natural language descriptions. While recent progress in text-to-audio and text-to-video models has improved generation quality within each modality, jointly modeling them remains challenging due to incomplete and asymmetric correspondence: audio often reflects only a subset of the visual scene, and vice versa. Naively enforcing full alignment introduces semantic noise and temporal mismatches. To address this, we propose a novel framework that performs selective cross-modal alignment through a learnable masking mechanism, enabling the model to isolate and align only the shared latent components relevant to both modalities. This mechanism is integrated into an adaptation module that interfaces with pretrained encoders and decoders from latent video and audio diffusion models, preserving their generative capacity with reduced training overhead. Theoretically, we show that our masked objective provably recovers the minimal set of shared latent variables across modalities. Empirically, our method achieves state-of-the-art performance on standard T2AV benchmarks, demonstrating significant improvements in audiovisual synchronization and semantic consistency.

Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a key bottleneck in current diffusion LMs: the \textbf{long decoding-window problem}, where tokens generated far from the input context often become irrelevant or repetitive. Previous solutions like semi-autoregressive address this issue by splitting windows into blocks (sacrificing bidirectionality), but we find that this also leads to \textbf{time-interval expansion problem}, sacrificing the speed. Therefore, semi-AR eliminates the main advantages of diffusion models. To overcome this, we propose Convolutional decoding (\textit{Conv}), a normalization-based method that narrows the decoding window without hard segmentation, leading to better fluency and flexibility. Additionally, we introduce Rejecting Rule-based Fine-Tuning (R2FT), a post-hoc training scheme that better aligns tokens at positions far from context. Our methods achieve state-of-the-art results on open-ended generation benchmarks (e.g., AlpacaEval) among diffusion LM baselines, with significantly lower step size than previous works, demonstrating both speed and quality improvements. The code is available online (\url{https://github.com/ybseo-ac/Conv}).