ICML 2025 Papers

CLIP has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, it has been widely adopted as the vision backbone of multimodal large language models (MLLMs). The success of CLIP relies on aligning web-crawled noisy text annotations at image levels. However, such criteria may be insufficient for downstream tasks in need of fine-grained vision representations, especially when understanding region-level is demanding for MLLMs. We improve the localization capability of CLIP with several advances. Our proposed pre-training method, Contrastive Localized Language-Image Pre-training (CLOC), complements CLIP with region-text contrastive loss and modules. We formulate a new concept, promptable embeddings, of which the encoder produces image embeddings easy to transform into region representations given spatial hints. To support large-scale pre-training, we design a visually-enriched and spatially-localized captioning framework to effectively generate region-text labels. By scaling up to billions of annotated images, CLOC enables high-quality regional embeddings for recognition and retrieval tasks, and can be a drop-in replacement of CLIP to enhance MLLMs, especially on referring and grounding tasks.

Visual localization aims to predict the absolute camera pose for a single query image. However, predominant methods focus on single-camera images and scenes with limited appearance variations, limiting their applicability to cross-domain scenes commonly encountered in real-world applications. Furthermore, the long-tail distribution of cross-domain datasets poses additional challenges for visual localization. In this work, we propose a novel cross-domain data generation method to enhance visual localization methods. To achieve this, we first construct a cross-domain 3DGS to accurately model photometric variations and mitigate the interference of dynamic objects in large-scale scenes. We introduce a text-guided image editing model to enhance data diversity for addressing the long-tail distribution problem and design an effective fine-tuning strategy for it. Then, we develop an anchor-based method to generate high-quality datasets for visual localization. Finally, we introduce positional attention to address data ambiguities in cross-camera images. Extensive experiments show that our method achieves state-of-the-art accuracy, outperforming existing cross-domain visual localization methods by an average of 59\% across all domains. Project page: https://yzwang-sjtu.github.io/CDG-Loc.

Fine-grained hashing has become a powerful solution for rapid and efficient image retrieval, particularly in scenarios requiring high discrimination between visually similar categories. To enable each hash bit to correspond to specific visual attributes, we propose a novel method that harnesses learnable queries for attribute-aware hash code learning. This method deploys a tailored set of queries to capture and represent nuanced attribute-level information within the hashing process, thereby enhancing both the interpretability and relevance of each hash bit. Building on this query-based optimization framework, we incorporate an auxiliary branch to help alleviate the challenges of complex landscape optimization often encountered with low-bit hash codes. This auxiliary branch models high-order attribute interactions, reinforcing the robustness and specificity of the generated hash codes. Experimental results on benchmark datasets demonstrate that our method generates attribute-aware hash codes and consistently outperforms state-of-the-art techniques in retrieval accuracy and robustness, especially for low-bit hash codes, underscoring its potential in fine-grained image hashing tasks.

Commonly used image tokenizers produce a 2D grid of spatially arranged tokens. In contrast, so-called *1D* image tokenizers represent images as highly compressed one-dimensional sequences of as few as 32 discrete tokens. We find that the high degree of compression achieved by a 1D tokenizer with vector quantization enables image editing and generative capabilities through heuristic manipulation of tokens, demonstrating that even very crude manipulations -- such as copying and replacing tokens between latent representations of images -- enable fine-grained image editing by transferring appearance and semantic attributes. Motivated by the expressivity of the 1D tokenizer's latent space, we construct an image generation pipeline leveraging gradient-based test-time optimization of tokens with plug-and-play loss functions such as reconstruction or CLIP similarity. Our approach is demonstrated for inpainting and text-guided image editing use cases, and can generate diverse and realistic samples without requiring training of any generative model.

Motion transfer is to transfer pose in driving video to object of source image, so that object of source image moves. Although great progress has been made recently in unsupervised motion transfer, many unsupervised methods still struggle to accurately model large displacement motions when large motion differences occur between source and driving images. To solve the problem, we propose an unsupervised anytime interpolation based large displacement motion transfer method, which can generate a series of anytime interpolated images between source and driving images. By decomposing large displacement motion into many small displacement motions, difficulty of large displacement motion estimation is reduced. In the process, we design a selector that can select optimal interpolated image from generated interpolated images for downstream tasks. Since there are no real images as labels in the interpolation process, we propose a bidirectional training strategy. Some constraints are added to optimal interpolated image to generate a reasonable interpolated image. To encourage network to generate high-quality images, a pre-trained Vision Transformer model is used to design constraint losses. Finally, experiments show that compared with the large displacement motion between source and driving images, small displacement motion between interpolated and driving images is easier to realize motion transfer. Compared with existing state-of-art methods, our method has significant improvements in motion-related metrics.

Fluorescence microscopy is ubiquitously used in cell biology research to characterize the cellular role of a protein. To help elucidate the relationship between the amino acid sequence of a protein and its cellular function, we introduce CELL-Diff, a unified diffusion model facilitating bidirectional transformations between protein sequences and their corresponding microscopy images. Utilizing reference cell morphology images and a protein sequence, CELL-Diff efficiently generates corresponding protein images. Conversely, given a protein image, the model outputs protein sequences. CELL-Diff integrates continuous and diffusion models within a unified framework and is implemented using a transformer-based network. We train CELL-Diff on the Human Protein Atlas (HPA) dataset and fine-tune it on the OpenCell dataset. Experimental results demonstrate that CELL-Diff outperforms existing methods in generating high-fidelity protein images, making it a practical tool for investigating subcellular protein localization and interactions.

Medical AI models excel at tumor detection and segmentation. However, their latent representations often lack explicit ties to clinical semantics, producing outputs less trusted in clinical practice. Most of the existing models generate either segmentation masks/labels (localizing where without why) or textual justifications (explaining why without where), failing to ground clinical concepts in spatially localized evidence. To bridge this gap, we propose to develop models that can justify the segmentation or detection using clinically relevant terms and point to visual evidence. We address two core challenges: First, we curate a rationale dataset to tackle the lack of paired images, annotations, and textual rationales for training. The dataset includes 180K image-mask-rationale triples with quality evaluated by expert radiologists. Second, we design rationale-informed optimization that disentangles and localizes fine-grained clinical concepts in a self-supervised manner without requiring pixel-level concept annotations. Experiments across medical benchmarks show our model demonstrates superior performance in segmentation, detection, and beyond. The anonymous link to our code.

Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key factors that contribute to both performance and efficiency. Based on the improvements observed during this exploration, we develop our model, referred to as \textbf{eMIGM}. Empirically, eMIGM demonstrates strong performance on ImageNet generation, as measured by Fréchet Inception Distance (FID). In particular, on ImageNet $256\times256$, with similar number of function evaluations (NFEs) and model parameters, eMIGM outperforms the seminal VAR. Moreover, as NFE and model parameters increase, eMIGM achieves performance comparable to the state-of-the-art continuous diffusion model REPA while requiring less than 45\% of the NFE. Additionally, on ImageNet $512\times512$, eMIGM outperforms the strong continuous diffusion model EDM2. Code is available at \url{https://github.com/ML-GSAI/eMIGM}.

The autoregressive decoding for text generation in large language models (LLMs), while widely used, is inherently suboptimal due to the lack of a built-in mechanism to perform refinement and/or correction of the generated content. In this paper, we consider optimality in terms of the joint probability over the generated response, when jointly considering all tokens at the same time. We theoretically characterize the potential deviation of the autoregressively generated response from its globally optimal counterpart that is of the same length. Our analysis suggests that we need to be cautious when noticeable uncertainty arises during text generation, which may signal the sub-optimality of the generation history. To address the pitfall of autoregressive decoding for text generation, we propose an approach that incorporates a sliding reflection window and a pausing criterion, such that refinement and generation can be carried out interchangeably as the decoding proceeds. Our selective refinement framework strikes a balance between efficiency and optimality, and our extensive experimental results demonstrate the effectiveness of our approach.

We continue to study the learning-theoretic foundations of generation by extending the results from Kleinberg and Mullainathan [2024] and Li et al. [2024] to account for noisy example streams. In the noiseless setting of Kleinberg and Mullainathan [2024] and Li et al. [2024], an adversary picks a hypothesis from a binary hypothesis class and provides a generator with a sequence of its positive examples. The goal of the generator is to eventually output new, unseen positive examples. In the noisy setting, an adversary still picks a hypothesis and a sequence of its positive examples. But, before presenting the stream to the generator, the adversary inserts a finite number of negative examples. Unaware of which examples are noisy, the goal of the generator is to still eventually output new, unseen positive examples. In this paper, we provide necessary and sufficient conditions for when a binary hypothesis class can be noisily generatable. We provide such conditions with respect to various constraints on the number of distinct examples that need to be seen before perfect generation of positive examples. Interestingly, for finite and countable classes we show that generatability is largely unaffected by the presence of a finite number of noisy examples.

The improved semantic understanding of vision-language pretrained (VLP) models has made it increasingly difficult to protect publicly posted images from being exploited by search engines and other similar tools. In this context, this paper seeks to protect users' privacy by implementing defenses at the image compression stage to prevent exploitation. Specifically, we propose a flexible coding method, termed Privacy-Shielded Image Compression (PSIC), that can produce bitstreams with multiple decoding options. By default, the bitstream is decoded to preserve satisfactory perceptual quality while preventing interpretation by VLP models. Our method also retains the original image compression functionality. With a customizable input condition, the proposed scheme can reconstruct the image that preserves its full semantic information. A Conditional Latent Trigger Generation (CLTG) module is proposed to produce bias information based on customizable conditions to guide the decoding process into different reconstructed versions, and an Uncertainty-Aware Encryption-Oriented (UAEO) optimization function is designed to leverage the soft labels inferred from the target VLP model's uncertainty on the training data. This paper further incorporates an adaptive multi-objective optimization strategy to obtain improved encrypting performance and perceptual quality simultaneously within a unified training process. The proposed scheme is plug-and-play and can be seamlessly integrated into most existing Learned Image Compression (LIC) models. Extensive experiments across multiple downstream tasks have demonstrated the effectiveness of our design.

Recent advances have highlighted the benefits of scaling language models to enhance performance across a wide range of NLP tasks. However, these approaches still face limitations in effectiveness and efficiency when applied to domain-specific tasks, particularly for small edge-side models. We propose the LoRA-Gen framework, which utilizes a large cloud-side model to generate LoRA parameters for edge-side models based on task descriptions. By employing the reparameterization technique, we merge the LoRA parameters into the edge-side model to achieve flexible specialization. Our method facilitates knowledge transfer between models while significantly improving the inference efficiency of the specialized model by reducing the input context length. Without specialized training, LoRA-Gen outperforms conventional LoRA fine-tuning, which achieves competitive accuracy and a 2.1x speedup with TinyLLaMA-1.1B in reasoning tasks. Besides, our method delivers a compress ratio of 10.1x with Gemma-2B on intelligent agent tasks.

In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for high-quality generation. Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input. In this work, we offer a new perspective by proposing denoising as decoding, shifting from single-step reconstruction to iterative refinement. Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image, guided by the latents provided by the encoder. We evaluate our approach by assessing both reconstruction (rFID) and generation quality (FID), comparing it to state-of-the-art autoencoding approaches. By adopting iterative reconstruction through diffusion, our autoencoder, namely Epsilon-VAE, achieves high reconstruction quality, which in turn enhances downstream generation quality by 22% at the same compression rates or provides 2.3x inference speedup through increasing compression rates. We hope this work offers new insights into integrating iterative generation and autoencoding for improved compression and generation.

We show that deep neural networks can achieve dimension-independent rates of convergence for learning structured densities typical of image, audio, video, and text data. For example, in images, where each pixel becomes independent of the rest of the image when conditioned on pixels at most $t$ steps away, a simple $L^2$-minimizing neural network can attain a rate of $n^{-1/((t+1)^2+4)}$, where $t$ is independent of the ambient dimension $d$, i.e. the total number of pixels. We further provide empirical evidence that, in real-world applications, $t$ is often a small constant, thus effectively circumventing the curse of dimensionality. Moreover, for sequential data (e.g., audio or text) exhibiting a similar local dependence structure, our analysis shows a rate of $n^{-1/(t+5)}$, offering further evidence of dimension independence in practical scenarios.

Motion synthesis for diverse object categories holds great potential for 3D content creation but remains underexplored due to two key challenges: (1) the lack of comprehensive motion datasets that include a wide range of high-quality motions and annotations, and (2) the absence of methods capable of handling heterogeneous skeletal templates from diverse objects. To address these challenges, we contribute the following: First, we augment the Truebones Zoo dataset—a high-quality animal motion dataset covering over 70 species—by annotating it with detailed text descriptions, making it suitable for text-based motion synthesis. Second, we introduce rig augmentation techniques that generate diverse motion data while preserving consistent dynamics, enabling models to adapt to various skeletal configurations. Finally, we redesign existing motion diffusion models to dynamically adapt to arbitrary skeletal templates, enabling motion synthesis for a diverse range of objects with varying structures. Experiments show that our method learns to generate high-fidelity motions from textual descriptions for diverse and even unseen objects, setting a strong foundation for motion synthesis across diverse object categories and skeletal templates. Qualitative results are available on this [link](https://t2m4lvo.github.io).

Damage to imaging systems and complex external environments often introduce corruption, which can impair the performance of deep learning models pretrained on high-quality image data. Previous methods have focused on restoring degraded images or fine-tuning models to adapt to out-of-distribution data. However, these approaches struggle with complex, unknown corruptions and often reduce model accuracy on high-quality data. Inspired by the use of warning colors and camouflage in the real world, we propose designing a robust appearance that can enhance model recognition of low-quality image data. Furthermore, we demonstrate that certain universal features in radiance fields can be applied across objects of the same class with different geometries. We also examine the impact of different proxy models on the transferability of robust appearances. Extensive experiments demonstrate the effectiveness of our proposed method, which outperforms existing image restoration and model fine-tuning approaches across different experimental settings, and retains effectiveness when transferred to models with different architectures. Code will be available at https://github.com/SilverRAN/YARM.

Text-to-image (T2I) generation has made remarkable progress in producing high-quality images, but a fundamental challenge remains: creating backgrounds that naturally accommodate text placement without compromising image quality. This capability is non-trivial for real-world applications like graphic design, where clear visual hierarchy between content and text is essential. Prior work has primarily focused on arranging layouts within existing static images, leaving unexplored the potential of T2I models for generating text-friendly backgrounds. We present TextCenGen, a training-free approach that actively relocates objects before optimizing text regions, rather than directly reducing cross-attention which degrades image quality. Our method introduces: (1) a force-directed graph approach that detects conflicting objects and guides them relocation using cross-attention maps, and (2) a spatial attention constraint that ensures smooth background generation in text regions. Our method is plug-and-play, requiring no additional training while well balancing both semantic fidelity and visual quality. Evaluated on our proposed text-friendly T2I benchmark of 27,000 images across three seed datasets, TextCenGen outperforms existing methods by achieving 23\% lower saliency overlap in text regions while maintaining 98\% of the original semantic fidelity measured by CLIP score and our proposed Visual-Textual Concordance Metric (VTCM).

Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining precision, we propose SageAttention2, which utilizes significantly faster 4-bit matrix multiplication (Matmul) alongside additional precision-enhancing techniques. First, we propose to quantize matrixes $(Q, K)$ to INT4 in a hardware-friendly thread-level granularity and quantize matrixes $(\widetilde P, V)$ to FP8. Second, we propose a method to smooth $Q$, enhancing the accuracy of INT4 $QK^\top$. Third, we propose a two-level accumulation strategy for $\widetilde PV$ to enhance the accuracy of FP8 $\widetilde PV$. The operations per second (OPS) of SageAttention2 surpass FlashAttention2 and xformers by about **3x** and **4.5x**, respectively. Moreover, SageAttention2 matches the speed of FlashAttention3(fp8) on the Hopper GPUs, while delivering much higher accuracy. Comprehensive experiments confirm that our approach incurs negligible end-to-end metrics loss across diverse models, including those for language, image, and video generation.

State-of-the-art image reconstruction often relies on complex, abundantly parameterized deep architectures. We propose an alternative: a data-driven reconstruction method inspired by the classic Tikhonov regularization. Our approach iteratively refines intermediate reconstructions by solving a sequence of quadratic problems. These updates have two key components: (i) learned filters to extract salient image features; and (ii) an attention mechanism that locally adjusts the penalty of the filter responses. Our method matches leading plug-and-play and learned regularizer approaches in performance while offering interpretability, robustness, and convergent behavior. In effect, we bridge traditional regularization and deep learning with a principled reconstruction approach.