ICLR 2025 Papers

Current volumetric biomedical foundation models struggle to generalize as public 3D datasets are small and do not cover the broad diversity of medical procedures, conditions, anatomical regions, and imaging protocols. We address this by creating a representation learning method that instead anticipates strong domain shifts at training time itself. We first propose a data engine that synthesizes highly variable training samples that would enable generalization to new biomedical contexts. To then train a single 3D network for any voxel-level task, we develop a contrastive learning method that pretrains the network to be stable against nuisance imaging variation simulated by the data engine, a key inductive bias for generalization. This network's features can be used as robust representations of input images for downstream tasks and its weights provide a strong, _dataset-agnostic_ initialization for finetuning on new datasets. As a result, we set new standards across _both_ multimodality registration and few-shot segmentation, a first for any 3D biomedical vision model, all without (pre-)training on any existing dataset of real images.

Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become outdated over time, preventing LLMs from correctly invoking tools. Existing research primarily focuses on static environments and overlooks this issue, limiting the adaptability of LLMs in real-world applications. In this paper, we propose ToolEVO, a novel framework designed to enhance the adaptive and reflective capabilities of LLMs against tool variability. By leveraging Monte Carlo Tree Search, ToolEVO facilitates active exploration and interaction of LLMs within dynamic environments, allowing for autonomous self-reflection and self-updating of tool usage based on environmental feedback. Additionally, we introduce ToolQA-D, a benchmark specifically designed to evaluate the impact of tool variability. Extensive experiments demonstrate the effectiveness and stability of our approach, highlighting the importance of adaptability to tool variability for effective tool learning.

Multiview Structure from Motion is a fundamental and challenging computer vision problem. A recent deep-based approach utilized matrix equivariant architectures for simultaneous recovery of camera pose and 3D scene structure from large image collections. That work, however, made the unrealistic assumption that the point tracks given as input are almost clean of outliers. Here, we propose an architecture suited to dealing with outliers by adding a multiview inlier/outlier classification module that respects the model equivariance and by utilizing a robust bundle adjustment step. Experiments demonstrate that our method can be applied successfully in realistic settings that include large image collections and point tracks extracted with common heuristics that include many outliers, achieving state-of-the-art accuracies in almost all runs, superior to existing deep-based methods and on-par with leading classical (non-deep) sequential and global methods.

In the primate neocortex, neurons with similar function are often found to be spatially close. Kohonen's self-organizing map (SOM) has been one of the most influential approaches for simulating brain-like topographical organization in artificial neural network models. However, integrating these maps into deep neural networks with multitude of layers has been challenging, with self-organized deep neural networks suffering from substantially diminished capacity to perform visual recognition. We identified a key factor leading to the performance degradation in self-organized topographical neural network models: the discord between predominantly bottom-up learning updates in the self-organizing maps, and those derived from top-down, credit-based learning approaches. To address this, we propose an alternative self organization algorithm, tailored to align with the top-down learning processes in deep neural networks. This model not only emulates critical aspects of cortical topography but also significantly narrows the performance gap between non-topographical and topographical models. This advancement underscores the substantial importance of top-down assigned credits in shaping topographical organization. Our findings are a step in reconciling topographical modeling with the functional efficacy of neural network models, paving the way for more brain-like neural architectures.

Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, creating a procedural material given an input image requires professional knowledge and significant effort. In this work, we leverage the ability to convert procedural materials into standard Python programs and fine-tune a large pre-trained vision-language model (VLM) to generate such programs from input images. To enable effective fine-tuning, we also contribute an open-source procedural material dataset and propose to perform program-level augmentation by prompting another pre-trained large language model (LLM). Through extensive evaluation, we show that our method outperforms previous methods on both synthetic and real-world examples.

With the explosive growth of video data, finding videos that meet detailed requirements in large datasets has become a challenge. To address this, the composed video retrieval task has been introduced, enabling users to retrieve videos using complex queries that involve both visual and textual information. However, the inherent heterogeneity between the modalities poses significant challenges. Textual data are highly abstract, while video content contains substantial redundancy. The modality gap in information representation makes existing methods struggle with the modality fusion and alignment required for fine-grained composed retrieval. To overcome these challenges, we first introduce FineCVR-1M, a fine-grained composed video retrieval dataset containing 1,010,071 video-text triplets with detailed textual descriptions. This dataset is constructed through an automated process that identifies key concept changes between video pairs to generate textual descriptions for both static and action concepts. For fine-grained retrieval methods, the key challenge lies in understanding the detailed requirements. Text description serves as clear expressions of intent, but it requires models to distinguish subtle differences in the description of video semantics. Therefore, we propose a textual Feature Disentanglement and Cross-modal Alignment framework (FDCA) that disentangles features at both the sentence and token levels. At the sequence level, we separate text features into retained and injected features. At the token level, an Auxiliary Token Disentangling mechanism is proposed to disentangle texts into retained, injected, and excluded tokens. The disentanglement at both levels extracts fine-grained features, which are aligned and fused with the reference video to extract global representations for video retrieval. Experiments on FineCVR-1M dataset demonstrate the superior performance of FDCA. Our code and dataset are available at: https://may2333.github.io/FineCVR/.

Recently, mixture of experts (MoE) has become a popular paradigm for achieving the trade-off between modal capacity and efficiency of multimodal large language models (MLLMs). Different from previous efforts, we are dedicated to exploring the dynamic experts in existing MLLMs and showing that a standard MLLM can also be a mixture of experts. However, achieving this target is still notoriously challenging. The well-trained MLLMs are more accustomed to the fixed pathway and a drastic change in its inference manner also greatly impedes its performance. To address these issues, we propose a novel dynamic expert routing method for existing MLLMs, termed Routing Experts (RoE), which can achieve example-dependent optimal path routing without obvious structure tweaks. Meanwhile, a new structure sparsity regularization is also introduced to force the well-trained MLLMs to learn more short-cut pathways. In addition, we also address the alignment of the training and inference of MLLMs in terms of network routing. To validate RoE, we apply it to a set of existing MLLMs, including LLaVA-1.5, LLaVA-HR and VILA, and conduct extensive experiments on a bunch of VL benchmarks. The experiment results not only show the effectiveness of our RoE in improving MLLMs' efficiency, but also yield obvious advantages over MoE-LLaVA in both performance and speed, e.g., an average performance gain of 3.3% on 5 benchmarks while being 1.61 times faster. Our code is anonymously released at https://github.com/DoubtedSteam/RoE

Using extensive training data from SA-1B, the Segment Anything Model (SAM) has demonstrated exceptional generalization and zero-shot capabilities, attracting widespread attention in areas such as medical image segmentation and remote sensing image segmentation. However, its performance in the field of image manipulation detection remains largely unexplored and unconfirmed. There are two main challenges in applying SAM to image manipulation detection: a) reliance on manual prompts, and b) the difficulty of single-view information in supporting cross-dataset generalization. To address these challenges, we develops a cross-view prompt learning paradigm called IMDPrompter based on SAM. Benefiting from the design of automated prompts, IMDPrompter no longer relies on manual guidance, enabling automated detection and localization. Additionally, we propose components such as Cross-view Feature Perception, Optimal Prompt Selection, and Cross-View Prompt Consistency, which facilitate cross-view perceptual learning and guide SAM to generate accurate masks. Extensive experimental results from five datasets (CASIA, Columbia, Coverage, IMD2020, and NIST16) validate the effectiveness of our proposed method.

In the realm of high-resolution (HR), fine-grained image segmentation, the primary challenge is balancing broad contextual awareness with the precision required for detailed object delineation, capturing intricate details and the finest edges of objects. Diffusion models, trained on vast datasets comprising billions of image-text pairs, such as SD V2.1, have revolutionized text-to-image synthesis by delivering exceptional quality, fine detail resolution, and strong contextual awareness, making them an attractive solution for high-resolution image segmentation. To this end, we propose DiffDIS, a diffusion-driven segmentation model that taps into the potential of the pre-trained U-Net within diffusion models, specifically designed for high-resolution, fine-grained object segmentation. By leveraging the robust generalization capabilities and rich, versatile image representation prior of the SD models, coupled with a task-specific stable one-step denoising approach, we significantly reduce the inference time while preserving high-fidelity, detailed generation. Additionally, we introduce an auxiliary edge generation task to not only enhance the preservation of fine details of the object boundaries, but reconcile the probabilistic nature of diffusion with the deterministic demands of segmentation. With these refined strategies in place, DiffDIS serves as a rapid object mask generation model, specifically optimized for generating detailed binary maps at high resolutions, while demonstrating impressive accuracy and swift processing. Experiments on the DIS5K dataset demonstrate the superiority of DiffDIS, achieving state-of-the-art results through a streamlined inference process. The source code will be publicly available at \href{https://github.com/qianyu-dlut/DiffDIS}{DiffDIS}.

Visual navigation is an essential skill for home-assistance robots, providing the object-searching ability to accomplish long-horizon daily tasks. Many recent approaches use Large Language Models (LLMs) for commonsense inference to improve exploration efficiency. However, the planning process of LLMs is limited within texts and it is difficult to represent the spatial occupancy and geometry layout only by texts. Both are important for making rational navigation decisions. In this work, we seek to unleash the spatial perception and planning ability of Vision-Language Models (VLMs), and explore whether the VLM, with only on-board camera captured RGB/RGB-D stream inputs, can efficiently finish the visual navigation tasks in a mapless manner. We achieve this by developing the imagination-powered navigation framework ImagineNav, which imagines the future observation images at valuable robot views and translates the complex navigation planning process into a rather simple best-view image selection problem for VLM. To generate appropriate candidate robot views for imagination, we introduce the Where2Imagine module, which is distilled to align with human navigation habits. Finally, to reach the VLM preferred views, an off-the-shelf point-goal navigation policy is utilized. Empirical experiments on the challenging open-vocabulary object navigation benchmarks demonstrates the superiority of our proposed system.

Latent 3D reconstruction has shown great promise in empowering 3D semantic understanding and 3D generation by distilling 2D features into the 3D space. However, existing approaches struggle with the domain gap between 2D feature space and 3D representations, resulting in degraded rendering performance. To address this challenge, we propose a novel framework that integrates 3D awareness into the 2D latent space. The framework consists of three stages: (1) a correspondence-aware autoencoding method that enhances the 3D consistency of 2D latent representations, (2) a latent radiance field (LRF) that lifts these 3D-aware 2D representations into 3D space, and (3) a VAE-Radiance Field (VAE-RF) alignment strategy that improves image decoding from the rendered 2D representations. Extensive experiments demonstrate that our method outperforms the state-of-the-art latent 3D reconstruction approaches in terms of synthesis performance and cross-dataset generalizability across diverse indoor and outdoor scenes. To our knowledge, this is the first work showing the radiance field representations constructed from 2D latent representations can yield photorealistic 3D reconstruction performance.

As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in real-world scenarios, necessitating the integration of visual context or common sense for accurate interpretation. However, even highly intelligent large models exhibit observable performance limitations on ambiguous instructions, where weak reasoning abilities of disambiguation can lead to catastrophic errors. To address this issue, this paper proposes Visual-O1, a multi-modal multi-turn chain-of-thought reasoning framework. It simulates human multi-modal multi-turn reasoning, providing instantial experience for highly intelligent models or empirical experience for generally intelligent models to understand ambiguous instructions. Unlike traditional methods that require models to possess high intelligence to understand long texts or perform lengthy complex reasoning, our framework does not notably increase computational overhead and is more general and effective, even for generally intelligent models. Experiments show that our method not only enhances the performance of models of different intelligence levels on ambiguous instructions but also improves their performance on general datasets. Our work highlights the potential of artificial intelligence to work like humans in real-world scenarios with uncertainty and ambiguity. We release our data and code at https://github.com/kodenii/Visual-O1.

Neural radiance fields have recently revolutionized novel-view synthesis and achieved high-fidelity renderings. However, these methods sacrifice the geometry for the rendering quality, limiting their further applications including relighting and deformation. How to synthesize photo-realistic rendering while reconstructing accurate geometry remains an unsolved problem. In this work, we present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction. Different from previous neural surfaces, our fused-granularity geometry structure balances the overall structures and fine geometric details, producing accurate geometry reconstruction. To disambiguate geometry from reflective appearance, we introduce blended radiance fields to model diffuse and specularity following the anisotropic spherical Gaussian encoding, a physics-based rendering pipeline. With these designs, AniSDF can reconstruct objects with complex structures and produce high-quality renderings. Furthermore, our method is a unified model that does not require complex hyperparameter tuning for specific objects. Extensive experiments demonstrate that our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.

We propose FlowDec, a neural full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel conditional flow matching method. Compared to the prior work ScoreDec which is based on score matching, we generalize from speech to general audio and move from 24 kbit/s to as low as 4 kbit/s, while improving output quality and reducing the required postfilter DNN evaluations from 60 to 6 without any fine-tuning or distillation techniques. We provide theoretical insights and geometric intuitions for our approach in comparison to ScoreDec as well as another recent work that uses flow matching, and conduct ablation studies on our proposed components. We show that FlowDec is a competitive alternative to the recent GAN-dominated stream of neural codecs, achieving FAD scores better than those of the established GAN-based codec DAC and listening test scores that are on par, and producing qualitatively more natural reconstructions for speech and harmonic structures in music.

Learning high-quality multi-modal entity representations is an important goal of multi-modal knowledge graph (MMKG) representation learning, which can en- hance reasoning tasks within the MMKGs, such as MMKG completion (MMKGC). The main challenge is to collaboratively model the structural information concealed in massive triples and the multi-modal features of the entities. Existing methods focus on crafting elegant entity-wise multi-modal fusion strategies, yet they over- look the utilization of multi-perspective features concealed within the modalities under diverse relational contexts. To address this issue, we introduce a novel framework with Mixture of Modality Knowledge experts (MOMOK for short) to learn adaptive multi-modal entity representations for better MMKGC. We design relation-guided modality knowledge experts to acquire relation-aware modality embeddings and integrate the predictions from multi-modalities to achieve joint decisions. Additionally, we disentangle the experts by minimizing their mutual information. Experiments on four public MMKG benchmarks demonstrate the outstanding performance of MOMOK under complex scenarios. Our code and data are available at https://github.com/zjukg/MoMoK.

We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models ($s$-MLLM) distilling knowledge from large-scale MLLM ($l$-MLLM). Our approach tackles two fundamental challenges in MLLM distillation. First, we optimize the network structure of $s$-MLLM by integrating a sparse Mixture of Experts (MoE) architecture into the language model, striking a balance between computational efficiency and model expressiveness. Second, we propose a progressive knowledge transfer strategy for comprehensive knowledge transfer. This strategy begins with mimic distillation, where we minimize the Kullback-Leibler (KL) divergence between output distributions to enable $s$-MLLM to emulate $s$-MLLM's understanding. Following this, we introduce preference distillation via Preference Optimization (PO), where the key lies in treating $l$-MLLM as the reference model. During this phase, the $s$-MLLM's ability to discriminate between superior and inferior examples is significantly enhanced beyond $l$-MLLM, leading to a better $s$-MLLM that surpasses $l$-MLLM, particularly in hallucination benchmarks. Extensive experiments demonstrate that LLaVA-MoD surpasses existing works across various benchmarks while maintaining a minimal activated parameters and low computational costs. Remarkably, LLaVA-MoD-2B surpasses Qwen-VL-Chat-7B with an average gain of 8.8\%, using merely $0.3\%$ of the training data and 23\% trainable parameters. The results underscore LLaVA-MoD's ability to effectively distill comprehensive knowledge from its teacher model, paving the way for developing efficient MLLMs.

Histopathology Whole-Slide Images (WSIs) provide an important tool to assess cancer prognosis in computational pathology (CPATH). While existing survival analysis (SA) approaches have made exciting progress, they are generally limited to adopting highly-expressive network architectures and only coarse-grained patient-level labels to learn visual prognostic representations from gigapixel WSIs. Such learning paradigm suffers from critical performance bottlenecks, when facing present scarce training data and standard multi-instance learning (MIL) framework in CPATH. To overcome it, this paper, for the first time, proposes a new Vision-Language-based SA (**VLSA**) paradigm. Concretely, (1) VLSA is driven by pathology VL foundation models. It no longer relies on high-capability networks and shows the advantage of *data efficiency*. (2) In vision-end, VLSA encodes textual prognostic prior and then employs it as *auxiliary signals* to guide the aggregating of visual prognostic features at instance level, thereby compensating for the weak supervision in MIL. Moreover, given the characteristics of SA, we propose i) *ordinal survival prompt learning* to transform continuous survival labels into textual prompts; and ii) *ordinal incidence function* as prediction target to make SA compatible with VL-based prediction. Notably, VLSA's predictions can be interpreted intuitively by our Shapley values-based method. The extensive experiments on five datasets confirm the effectiveness of our scheme. Our VLSA could pave a new way for SA in CPATH by offering weakly-supervised MIL an effective means to learn valuable prognostic clues from gigapixel WSIs. Our source code is available at https://github.com/liupei101/VLSA.

This work does not introduce a new method. Instead, we present an interesting finding that questions the necessity of the inductive bias of locality in modern computer vision architectures. Concretely, we find that vanilla Transformers can operate by directly treating each individual pixel as a token and achieve highly performant results. This is substantially different from the popular design in Vision Transformer, which maintains the inductive bias from ConvNets towards local neighborhoods (e.g., by treating each 16x16 patch as a token). We showcase the effectiveness of pixels-as-tokens across three well-studied computer vision tasks: supervised learning for classification and regression, self-supervised learning via masked autoencoding, and image generation with diffusion models. Although it's computationally less practical to directly operate on individual pixels, we believe the community must be made aware of this surprising piece of knowledge when devising the next generation of neural network architectures for computer vision.

The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing importance, the security of VLMs, particularly against backdoor attacks, is under explored. Moreover, prior works often assume attackers have access to the original training data, which is often unrealistic. In this paper, we address a more practical and challenging scenario where attackers must rely solely on Out-Of-Distribution (OOD) data. We introduce VLOOD (Backdoor Vision-Language Models using Out-of-Distribution Data), a novel approach with two key contributions: (1) demonstrating backdoor attacks on VLMs in complex image-to-text tasks while minimizing degradation of the original semantics under poisoned inputs, and (2) proposing innovative techniques for backdoor injection without requiring any access to the original training data. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of VLOOD, revealing a critical security vulnerability in VLMs and laying the foundation for future research on securing multimodal models against sophisticated threats.