ICML 2025 Papers

Interactive 3D segmentation has emerged as a promising solution for generating accurate object masks in complex 3D scenes by incorporating user-provided clicks. However, two critical challenges remain underexplored: (1) effectively generalizing from sparse user clicks to produce accurate segmentations and (2) quantifying predictive uncertainty to help users identify unreliable regions. In this work, we propose \emph{NPISeg3D}, a novel probabilistic framework that builds upon Neural Processes (NPs) to address these challenges. Specifically, NPISeg3D introduces a hierarchical latent variable structure with scene-specific and object-specific latent variables to enhance few-shot generalization by capturing both global context and object-specific characteristics. Additionally, we design a probabilistic prototype modulator that adaptively modulates click prototypes with object-specific latent variables, improving the model’s ability to capture object-aware context and quantify predictive uncertainty. Experiments on four 3D point cloud datasets demonstrate that NPISeg3D achieves superior segmentation performance with fewer clicks while providing reliable uncertainty estimations.

Unsupervised anomaly detection (UAD) seeks to localize the anomaly mask of an input image with respect to normal samples. Either by reconstructing normal counterparts (reconstruction-based) or by learning an image feature embedding space (embedding-based), existing approaches fundamentally rely on image-level or feature-level matching to derive anomaly scores. Often, such a matching process is inaccurate yet overlooked, leading to sub-optimal detection. To address this issue, we introduce the concept of cost filtering, borrowed from classical matching tasks, such as depth and flow estimation, into the UAD problem. We call this approach CostFilter-AD. Specifically, we first construct a matching cost volume between the input and normal samples, comprising two spatial dimensions and one matching dimension that encodes potential matches. To refine this, we propose a cost volume filtering network, guided by the input observation as an attention query across multiple feature layers, which effectively suppresses matching noise while preserving edge structures and capturing subtle anomalies. Designed as a generic post-processing plug-in, CostFilter-AD can be integrated with either reconstruction-based or embedding-based methods. Extensive experiments on MVTec-AD and VisA benchmarks validate the generic benefits of CostFilter-AD for both single- and multi-class UAD tasks. Code and models will be released at https://github.com/ZHE-SAPI/CostFilter-AD.

Most existing 3D Gaussian Splatting (3DGS) compression schemes focus on producing compact 3DGS representation via implicit data embedding. They have long encoding and decoding times and highly customized data format, making it difficult for widespread deployment. This paper presents a new 3DGS compression framework called HybridGS, which takes advantage of both compact generation and standardized point cloud data encoding. HybridGS first generates compact and explicit 3DGS data. A dual-channel sparse representation is introduced to supervise the primitive position and feature bit depth. It then utilizes a canonical point cloud encoder to carry out further data compression and form standard output bitstreams. A simple and effective rate control scheme is proposed to pivot the interpretable data compression scheme. HybridGS does not include any modules aimed at improving 3DGS quality during generation. But experiment results show that it still provides comparable reconstruction performance against state-of-the-art methods, with evidently faster encoding and decoding speed. The code is publicly available at https://github.com/Qi-Yangsjtu/HybridGS .

Vision foundation models (FMs) like CLIP have exhibited exceptional capabilities in visual and linguistic understanding, particularly in zero-shot inference tasks. However, these models struggle with data that significantly deviates from their training samples, necessitating fine-tuning, which is often infeasible in centralized settings due to data privacy concerns. Federated learning (FL) combined with parameter-efficient fine-tuning (PEFT) offers a potential solution, yet existing methods face issues with domain-specific characteristics and out-of-domain generalization. We propose a cross-silo Federated Adapter Generalization (FedAG), a novel federated fine-tuning approach that leverages multiple fine-grained adapters to capture domain-specific knowledge while enhancing out-of-domain generalization. Our method uses quality-aware in-domain mutual learning and attention-regularized cross-domain learning to integrate domain-specific insights effectively. Experiments of the CLIP model on three domain-shifting datasets, ImageCLEF-DA, Office-Home, and DomainNet, demonstrate the superior performance of FedAG in both in-domain and out-of-domain scenarios. We envision this work as a milestone for generalizing CLIP to handle the challenge of out-of-domain knowledge under federated learning setting.

Traditional approaches to adapting multi-modal large language models (MLLMs) to new tasks have relied heavily on fine-tuning. This paper introduces Efficient Multi-Modal Long Context Learning (EMLoC), a novel training-free alternative that embeds demonstration examples directly into the model input. EMLoC offers a more efficient, flexible, and scalable solution for task adaptation. Because extremely lengthy inputs introduce prohibitive computational and memory overhead, EMLoC contributes a chunk-wise compression mechanism combined with layer-wise adaptive pruning. It condenses long-context multimodal inputs into compact, task-specific memory representations. By adaptively pruning tokens at each layer under a Jensen-Shannon divergence constraint, our method achieves a dramatic reduction in inference complexity without sacrificing performance. This approach is the first to seamlessly integrate compression and pruning techniques for multi-modal long-context learning, offering a scalable and efficient solution for real-world applications. Extensive experiments on diverse vision-language benchmarks demonstrate that EMLoC achieves performance on par with or superior to naive long-context approaches. Our results highlight the potential of EMLoC as a groundbreaking framework for efficient and flexible adaptation of multi-modal models in resource-constrained environments. Codes are publicly available at https://github.com/Zehong-Ma/EMLoC.

We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design challenging questions, yet we experimentally show that humans struggle to predict which questions are difficult for machine learning models. Our automatic approach leverages recent advances in code generation for visual question answering, using the complexity of generated code as a proxy for question difficulty. We demonstrate that this measure correlates significantly better with model performance than human estimates. To operationalize this insight, we propose an algorithm for estimating question complexity from code. It identifies fine-grained primitives that correlate with the hardest questions for any given set of models, making it easy to scale to new approaches in the future. Finally, to further illustrate the utility of our method, we extend it to automatically generate complex questions, constructing a new benchmark that is 1.9 times harder than the popular NExT-QA.

Despite their success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i.e., using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Enhanced by six key modules, Information Gathering, Self-Reflection, Task Inference, Skill Curation, Action Planning, and Memory, Cradle is able to understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning and information retrieval, so that Cradle can interact with any software and complete long-horizon complex tasks without relying on any built-in APIs. Experimental results show that Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games (Red Dead Redemption 2, Cities:Skylines, Stardew Valley and Dealer's Life 2), five software applications (Chrome, Outlook, Feishu, Meitu and CapCut), and a comprehensive benchmark, OSWorld. With a unified interface to interact with any software, Cradle greatly extends the reach of foundation agents thus paving the way for generalist agents.

Human body restoration, as a specific application of image restoration, is widely applied in practice and plays a vital role across diverse fields. However, thorough research remains difficult, particularly due to the lack of benchmark datasets. In this study, we propose a high-quality dataset automated cropping and filtering (HQ-ACF) pipeline. This pipeline leverages existing object detection datasets and other unlabeled images to automatically crop and filter high-quality human images. Using this pipeline, we constructed a person-based restoration with sophisticated objects and natural activities (*PERSONA*) dataset, which includes training, validation, and test sets. The dataset significantly surpasses other human-related datasets in both quality and content richness. Finally, we propose *OSDHuman*, a novel one-step diffusion model for human body restoration. Specifically, we propose a high-fidelity image embedder (HFIE) as the prompt generator to better guide the model with low-quality human image information, effectively avoiding misleading prompts. Experimental results show that OSDHuman outperforms existing methods in both visual quality and quantitative metrics. The dataset and code are available at: https://github.com/gobunu/OSDHuman.

As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations, including uncontrollable task complexity, extensive manual annotation, and a lack of multidimensional evaluation. In response to these challenges, we introduce OmniBench, a self-generating, graph-based benchmark with an automated pipeline for synthesizing tasks of controllable complexity through subtask composition. To evaluate the diverse capabilities of virtual agents on the graph, we further present OmniEval, a multidimensional evaluation framework that includes subtask-level evaluation, graph-based metrics, and comprehensive tests across 10 capabilities. Our synthesized dataset contains 36k graph-structured tasks across 20 scenarios, achieving a 91% human acceptance rate. Training on our graph-structured data shows that it improves generalization across environments. We conduct multidimensional evaluations for virtual agents, revealing their performance across various capabilities and paving the way for future advancements. Our project is available at https://omni-bench.github.io.

Recent advancements in computer vision have seen Implicit Neural Representations (INR) becoming a dominant representation form for data due to their compactness and expressive power. To solve various vision tasks with INR data, vision networks can either be purely INR-based, but are thereby limited by simplistic operations and performance constraints, or include raster-based methods, which then tend to lose crucial structural information of the INR during the conversion process. To address these issues, we propose DVI, a novel Derivative-based Vision network for INR, capable of handling a variety of vision tasks across various data modalities, while achieving the best performance among the existing methods by incorporating state of the art raster-based methods into a INR based architecture. DVI excels by extracting semantic information from the high order derivative map of the INR, then seamlessly fusing it into a pre-existing raster-based vision network, enhancing its performance with deeper, task-relevant semantic insights. Extensive experiments on five vision tasks across three data modalities demonstrate DVI's superiority over existing methods. Additionally, our study encompasses comprehensive ablation studies to affirm the efficacy of each element of DVI, the influence of different derivative computation techniques and the impact of derivative orders. Reproducible codes are provided in the supplementary materials.

Layout-to-Image generation aims to create complex scenes with precise control over the placement and arrangement of subjects. Existing works have demonstrated that pre-trained Text-to-Image diffusion models can achieve this goal without training on any specific data; however, they often face challenges with imprecise localization and unrealistic artifacts. Focusing on these drawbacks, we propose a novel training-free method, WinWinLay. At its core, WinWinLay presents two key strategies—Non-local Attention Energy Function and Adaptive Update—that collaboratively enhance control precision and realism. On one hand, we theoretically demonstrate that the commonly used attention energy function introduces inherent spatial distribution biases, hindering objects from being uniformly aligned with layout instructions. To overcome this issue, non-local attention prior is explored to redistribute attention scores, facilitating objects to better conform to the specified spatial conditions. On the other hand, we identify that the vanilla backpropagation update rule can cause deviations from the pre-trained domain, leading to out-of-distribution artifacts. We accordingly introduce a Langevin dynamics-based adaptive update scheme as a remedy that promotes in-domain updating while respecting layout constraints. Extensive experiments demonstrate that WinWinLay excels in controlling element placement and achieving photorealistic visual fidelity, outperforming the current state-of-the-art methods.

Text-guided image-to-image diffusion models excel in translating images based on textual prompts, allowing for precise and creative visual modifications. However, such a powerful technique can be misused for *spreading misinformation*, *infringing on copyrights*, and *evading content tracing*. This motivates us to introduce the task of origin **ID**entification for text-guided **I**mage-to-image **D**iffusion models (**ID$\mathbf{^2}$**), aiming to retrieve the original image of a given translated query. A straightforward solution to ID$^2$ involves training a specialized deep embedding model to extract and compare features from both query and reference images. However, due to *visual discrepancy* across generations produced by different diffusion models, this similarity-based approach fails when training on images from one model and testing on those from another, limiting its effectiveness in real-world applications. To solve this challenge of the proposed ID$^2$ task, we contribute the first dataset and a theoretically guaranteed method, both emphasizing generalizability. The curated dataset, **OriPID**, contains abundant **Ori**gins and guided **P**rompts, which can be used to train and test potential **ID**entification models across various diffusion models. In the method section, we first prove the *existence* of a linear transformation that minimizes the distance between the pre-trained Variational Autoencoder embeddings of generated samples and their origins. Subsequently, it is demonstrated that such a simple linear transformation can be *generalized* across different diffusion models. Experimental results show that the proposed method achieves satisfying generalization performance, significantly surpassing similarity-based methods (+31.6% mAP), even those with generalization designs. The project is available at https://id2icml.github.io.

Human vision is dynamic and continuous. However, in video understanding with multimodal large language models (LLMs), existing methods primarily rely on static features extracted from images sampled at a fixed low frame rate of frame-per-second (FPS) $\leqslant$2, leading to critical visual information loss. In this paper, we introduce F-16, the first multimodal LLM designed for high-frame-rate video understanding. By increasing the frame rate to 16 FPS and compressing visual tokens within each 1-second clip, F-16 efficiently captures dynamic visual features while preserving key semantic information. Experimental results demonstrate that higher frame rates considerably enhance video understanding across multiple benchmarks, providing a new approach to improving video LLMs beyond scaling model size or training data. F-16 achieves state-of-the-art performance among 7-billion-parameter video LLMs on both general and fine-grained video understanding benchmarks, such as Video-MME and TemporalBench. Furthermore, F-16 excels in complex spatiotemporal tasks, including high-speed sports analysis (*e.g.*, basketball, football, gymnastics, and diving), outperforming SOTA proprietary visual models like GPT-4o and Gemini-1.5-pro. Additionally, we introduce a novel decoding method for F-16 that enables highly efficient low-frame-rate inference without requiring model retraining. We will release the source code, model checkpoints, and data at [https://github.com/bytedance/F-16](https://github.com/bytedance/F-16).

Pathology image segmentation plays a pivotal role in artificial digital pathology diagnosis and treatment. Existing approaches to pathology image segmentation are hindered by labor-intensive annotation processes and limited accuracy in tail-class identification, primarily due to the long-tail distribution inherent in gigapixel pathology images. In this work, we introduce the Laplace Diffusion Model, referred to as L-Diffusion, an innovative framework tailored for efficient pathology image segmentation. L-Diffusion utilizes multiple Laplace distributions, as opposed to Gaussian distributions, to model distinct components—a methodology supported by theoretical analysis that significantly enhances the decomposition of features within the feature space. A sequence of feature maps is initially generated through a series of diffusion steps. Following this, contrastive learning is employed to refine the pixel-wise vectors derived from the feature map sequence. By utilizing these highly discriminative pixel-wise vectors, the segmentation module achieves a harmonious balance of precision and robustness with remarkable efficiency. Extensive experimental evaluations demonstrate that L-Diffusion attains improvements of up to 7.16\%, 26.74\%, 16.52\%, and 3.55\% on tissue segmentation datasets, and 20.09\%, 10.67\%, 14.42\%, and 10.41\% on cell segmentation datasets, as quantified by DICE, MPA, mIoU, and FwIoU metrics. The source are available at https://github.com/Lweihan/LDiffusion.

Foundation models pre-trained on massive unlabeled datasets have revolutionized natural language and computer vision, exhibiting remarkable generalization capabilities, thus highlighting the importance of pre-training. Yet, efforts in robotics have struggled to achieve similar success, limited by either the need for costly robotic annotations or the lack of representations that effectively model the physical world. In this paper, we introduce ARM4R, an **A**uto-regressive **R**obotic **M**odel that leverages low-level **4**D **R**epresentations learned from human video data to yield a better pre-trained robotic model. Specifically, we focus on utilizing 3D point tracking representations from videos derived by lifting 2D representations into 3D space via monocular depth estimation across time. These 4D representations maintain a shared geometric structure between the points and robot state representations up to a linear transformation, enabling efficient transfer learning from human video data to low-level robotic control. Our experiments show that ARM4R can transfer efficiently from human video data to robotics and consistently improves performance on tasks across various robot environments and configurations.

Diffusion models (DMs) are a class of generative models that allow sampling from a distribution learned over a training set. When applied to solving inverse problems, the reverse sampling steps are modified to approximately sample from a measurement-conditioned distribution. However, these modifications may be unsuitable for certain settings (e.g., presence of measurement noise) and non-linear tasks, as they often struggle to correct errors from earlier steps and generally require a large number of optimization and/or sampling steps. To address these challenges, we state three conditions for achieving measurement-consistent diffusion trajectories. Building on these conditions, we propose a new optimization-based sampling method that not only enforces standard data manifold measurement consistency and forward diffusion consistency, as seen in previous studies, but also incorporates our proposed step-wise and network-regularized backward diffusion consistency that maintains a diffusion trajectory by optimizing over the input of the pre-trained model at every sampling step. By enforcing these conditions (implicitly or explicitly), our sampler requires significantly fewer reverse steps. Therefore, we refer to our method as **S**tep-w**i**se **T**riple-**Co**nsistent Sa**m**pling (**SITCOM**). Compared to SOTA baselines, our experiments across several linear and non-linear tasks (with natural and medical images) demonstrate that SITCOM achieves competitive or superior results in terms of standard similarity metrics and run-time.

Segment Anything Model (SAM) has demonstrated remarkable zero-shot segmentation capabilities across various visual tasks. However, its performance degrades significantly when deployed in new target domains with substantial distribution shifts. While existing self-training methods based on fixed teacher-student architectures have shown improvements, they struggle to ensure that the teacher network consistently outperforms the student under severe domain shifts. To address this limitation, we propose a novel Collaborative Mutual Learning Framework for source-free SAM adaptation, leveraging dual-networks in a dynamic and cooperative manner. Unlike fixed teacher-student paradigms, our method dynamically assigns the teacher and student roles by evaluating the reliability of each collaborative network in each training iteration. Our framework incorporates a dynamic mutual learning mechanism with three key components: a direct alignment loss for knowledge transfer, a reverse distillation loss to encourage diversity, and a triplet relationship loss to refine feature representations. These components enhance the adaptation capabilities of the collaborative networks, enabling them to generalize effectively to target domains while preserving their pre-trained knowledge. Extensive experiments on diverse target domains demonstrate that our proposed framework achieves state-of-the-art adaptation performance.

Score Distillation Sampling (SDS) has emerged as a prominent method for text-to-3D generation by leveraging the strengths of 2D diffusion models. However, SDS is limited to generation tasks and lacks the capability to edit existing 3D assets. Conversely, variants of SDS that introduce editing capabilities often can not generate new 3D assets effectively. In this work, we observe that the processes of generation and editing within SDS and its variants have unified underlying gradient terms. Building on this insight, we propose Unified Distillation Sampling (UDS), a method that seamlessly integrates both the generation and editing of 3D assets. Essentially, UDS refines the gradient terms used in vanilla SDS methods, unifying them to support both tasks. Extensive experiments demonstrate that UDS not only outperforms baseline methods in generating 3D assets with richer details but also excels in editing tasks, thereby bridging the gap between 3D generation and editing.

A series of pre-trained models have demonstrated promising results in point cloud understanding tasks and are widely applied to downstream tasks through fine-tuning. However, full fine-tuning leads to the forgetting of pretrained knowledge and substantial storage costs on edge devices. To address these issues, Parameter-Efficient Transfer Learning (PETL) methods have been proposed. According to our analysis, we find that existing 3D PETL methods cannot adequately align with semantic relationships of features required by downstream tasks, resulting in suboptimal performance. To ensure parameter efficiency while introducing rich semantic cues, we propose a novel fine-tuning paradigm for 3D pre-trained models. We utilize frozen 2D pre-trained models to provide vision semantic prompts and design a new Hybrid Attention Adapter to efficiently fuse 2D semantic cues into 3D representations with minimal trainable parameters(1.8M). Extensive experiments conducted on datasets including ScanObjectNN, ModelNet40, and ShapeNetPart demonstrate the effectiveness of our proposed paradigm. In particular, our method achieves 95.6% accuracy on ModelNet40 and attains 90.09% performance on the most challenging classification split ScanObjectNN(PB-T50-RS).