ICLR 2025 论文列表

While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides reducing the training and rendering complexity, applying inverse graphics in the latent space enables a valuable interoperability with other latent-based 2D methods. The major challenge is that inverse graphics cannot be directly applied to such image latent spaces because they lack an underlying 3D geometry. In this paper, we propose an Inverse Graphics Autoencoder (IG-AE) that specifically addresses this issue. To this end, we regularize an image autoencoder with 3D-geometry by aligning its latent space with jointly trained latent 3D scenes. We utilize the trained IG-AE to bring NeRFs to the latent space with a latent NeRF training pipeline, which we implement in an open-source extension of the Nerfstudio framework, thereby unlocking latent scene learning for its supported methods. We experimentally confirm that Latent NeRFs trained with IG-AE present an improved quality compared to a standard autoencoder, all while exhibiting training and rendering accelerations with respect to NeRFs trained in the image space. Our project page can be found at https://ig-ae.github.io .

Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection approaches, such as uniform frame sampling and text-frame retrieval, fail to account for the information density variations in the videos or the complex instructions in the tasks, leading to sub-optimal performance. In this paper, we propose Frame-Voyager that learns to query informative frame combinations, based on the given textual queries in the task. To train Frame-Voyager, we introduce a new data collection and labeling pipeline, by ranking frame combinations using a pre-trained Video-LLM. Given a video of M frames, we traverse its T-frame combinations, feed them into a Video-LLM, and rank them based on Video-LLM's prediction losses. Using this ranking as supervision, we train Frame-Voyager to query the frame combinations with lower losses. In experiments, we evaluate Frame-Voyager on four Video Question Answering benchmarks by plugging it into two different Video-LLMs. The experimental results demonstrate that Frame-Voyager achieves impressive results in all settings, highlighting its potential as a plug-and-play solution for Video-LLMs.

Understanding drivers’ decision-making is crucial for road safety. Although predicting the ego-vehicle’s path is valuable for driver-assistance systems, existing methods mainly focus on external factors like other vehicles’ motions, often neglecting the driver’s attention and intent. To address this gap, we infer the ego-trajectory by integrating the driver’s gaze and the surrounding scene. We introduce RouteFormer, a novel multimodal ego-trajectory prediction network combining GPS data, environmental context, and the driver's field-of-view—comprising first-person video and gaze fixations. We also present the Path Complexity Index (PCI), a new metric for trajectory complexity that enables a more nuanced evaluation of challenging scenarios. To tackle data scarcity and enhance diversity, we introduce GEM, a comprehensive dataset of urban driving scenarios enriched with synchronized driver field-of-view and gaze data. Extensive evaluations on GEM and DR(eye)VE demonstrate that RouteFormer significantly outperforms state-of-the-art methods, achieving notable improvements in prediction accuracy across diverse conditions. Ablation studies reveal that incorporating driver field-of-view data yields significantly better average displacement error, especially in challenging scenarios with high PCI scores, underscoring the importance of modeling driver attention. All data and code are available at meakbiyik.github.io/routeformer.

Deep neural networks have achieved remarkable accomplishments in practice. The success of these networks hinges on effective initialization methods, which are vital for ensuring stable and rapid convergence during training. Recently, initialization methods that maintain identity transition within layers have shown good efficiency in network training. These techniques (e.g., Fixup) set specific weights to zero to achieve identity control. However, settings of remaining weight (e.g., Fixup uses random values to initialize non-zero weights) will affect the inductive bias that is achieved only by a zero weight, which may be harmful to training. Addressing this concern, we introduce fully identical initialization (IDInit), a novel method that preserves identity in both the main and sub-stem layers of residual networks. IDInit employs a padded identity-like matrix to overcome rank constraints in non-square weight matrices. Furthermore, we show the convergence problem of an identity matrix can be solved by stochastic gradient descent. Additionally, we enhance the universality of IDInit by processing higher-order weights and addressing dead neuron problems. IDInit is a straightforward yet effective initialization method, with improved convergence, stability, and performance across various settings, including large-scale datasets and deep models.

Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual outputs. This paper investigates the underlying mechanisms of hallucination, focusing on the unique structure of LVLMs that distinguishes them from LLMs. We identify that hallucinations often arise from the sensitivity of text decoders to vision inputs, a natural phenomenon when image encoders and text decoders are pre-trained separately. Inspired by this, we introduce Visual and Textual Intervention (VTI), a novel technique designed to reduce hallucinations by steering latent space representations during inference to enhance the stability of vision features. As a task-agnostic test-time intervention, VTI can be easily applied to any problem without additional training costs. Extensive experiments demonstrate that it can effectively reduce hallucinations and outperform baseline methods across multiple metrics, highlighting the critical role of vision feature stability in LVLMs.

Prior work has offered evidence for functional localization in the brain; different anatomical regions preferentially activate for certain types of visual input. For example, the fusiform face area preferentially activates for visual stimuli that include a face. However, the spectrum of visual semantics is extensive, and only a few semantically-tuned patches of cortex have so far been identified in the human brain. Using a multimodal (natural language and image) neural network architecture (CLIP, \cite{CLIP}, we train a highly accurate contrastive model that maps brain responses during naturalistic image viewing to CLIP embeddings. We then use a novel adaptation of the DBSCAN clustering algorithm to cluster the parameters of these participant-specific contrastive models. This reveals what we call Shared Decodable Concepts (SDCs): clusters in CLIP space that are decodable from common sets of voxels across multiple participants. Examining the images most and least associated with each SDC cluster gives us additional insight into the semantic properties of each SDC. We note SDCs for previously reported visual features (e.g. orientation tuning in early visual cortex) as well as visual semantic concepts such as faces, places and bodies. In cases where our method finds multiple clusters for a visuo-semantic concept, the least associated images allow us to dissociate between confounding factors. For example, we discovered two clusters of food images, one driven by color, the other by shape. We also uncover previously unreported areas with visuo-semantic sensitivity such as regions of extrastriate body area (EBA) tuned for legs/hands and sensitivity to numerosity in right intraparietal sulcus, sensitivity associated with visual perspective (close/far) and more. Thus, our contrastive-learning methodology better characterizes new and existing visuo-semantic representations in the brain by leveraging multimodal neural network representations and a novel adaptation of clustering algorithms.

Vocabulary adaptation, which integrates new vocabulary into pre-trained language models, enables expansion to new languages and mitigates token over-fragmentation. However, existing approaches are limited by their reliance on heuristics or external embeddings. We propose VocADT, a novel method for vocabulary adaptation using adapter modules that are trained to learn the optimal linear combination of existing embeddings while keeping the model’s weights fixed. VocADT offers a flexible and scalable solution without depending on external resources or language constraints. Across 11 languages—with diverse scripts, resource availability, and fragmentation—we demonstrate that VocADT outperforms the original Mistral model (Jiang et al., 2023) and other baselines across various multilingual tasks including natural language understanding and machine translation. We find that Latin-script languages and highly fragmented languages benefit the most from vocabulary adaptation. We further fine-tune the adapted model on the generative task of machine translation and find that vocabulary adaptation is still beneficial after fine-tuning and that VocADT is the most effective.

We address the challenge of automatically generating high-quality vector diagrams from hand-drawn sketches. Vector diagrams are essential for communicating complex ideas across various fields, offering flexibility and scalability. While recent research has progressed in generating diagrams from text descriptions, converting hand-drawn sketches into vector diagrams remains largely unexplored due to the lack of suitable datasets. To address this gap, we introduce SketikZ, a dataset comprising 3,231 pairs of hand-drawn sketches and thier corresponding TikZ codes as well as reference diagrams. Our evaluations reveal the limitations of state-of-the-art vision and language models (VLMs), positioning SketikZ as a key benchmark for future research in sketch-to-diagram conversion. Along with SketikZ, we present ImgTikZ, an image-to-TikZ model that integrates a 6.7B parameter code-specialized open-source large language model (LLM) with a pre-trained vision encoder. Despite its relatively compact size, ImgTikZ performs comparably to GPT-4o. This success is driven by using our two data augmentation techniques and a multi-candidate inference strategy. Our findings open promising directions for future research in sketch-to-diagram conversion and broader image-to-code generation tasks. SketikZ is publicly available.

We introduce MIRReS, a novel two-stage inverse rendering framework that jointly reconstructs and optimizes explicit geometry, materials, and lighting from multi-view images. Unlike previous methods that rely on implicit irradiance fields or oversimplified ray tracing, our method begins with an initial stage that extracts an explicit triangular mesh. In the second stage, we refine this representation using a physically-based inverse rendering model with multi-bounce path tracing and Monte Carlo integration. This enables our method to accurately estimate indirect illumination effects, including self-shadowing and internal reflections, leading to a more precise intrinsic decomposition of shape, material, and lighting. To address the noise issue in Monte Carlo integration, we incorporate reservoir sampling, improving convergence and enabling efficient gradient-based optimization with low sample counts. Through both qualitative and quantitative assessments across various scenarios, especially those with complex shadows, we demonstrate that our method achieves state-of-the-art decomposition performance. Furthermore, our optimized explicit geometry seamlessly integrates with modern graphics engines supporting downstream applications such as scene editing, relighting, and material editing.

Large vision-language models (LVLMs) have demonstrated remarkable image understanding and dialogue capabilities, allowing them to handle a variety of visual question answering tasks. However, their widespread availability raises concerns about unauthorized usage and copyright infringement, where users or individuals can develop their own LVLMs by fine-tuning published models. In this paper, we propose a novel method called Parameter Learning Attack (PLA) for tracking the copyright of LVLMs without modifying the original model. Specifically, we construct adversarial images through targeted attacks against the original model, enabling it to generate specific outputs. To ensure these attacks remain effective on potential fine-tuned models to trigger copyright tracking, we allow the original model to learn the trigger images by updating parameters in the opposite direction during the adversarial attack process. Notably, the proposed method can be applied after the release of the original model, thus not affecting the model’s performance and behavior. To simulate real-world applications, we fine-tune the original model using various strategies across diverse datasets, creating a range of models for copyright verification. Extensive experiments demonstrate that our method can more effectively identify the original copyright of fine-tuned models compared to baseline methods. Therefore, this work provides a powerful tool for tracking copyrights and detecting unlicensed usage of LVLMs.

In this paper, we explore a principal way to enhance the quality of widely pre-existing coarse masks, enabling them to serve as reliable training data for segmentation models to reduce the annotation cost. In contrast to prior refinement techniques that are tailored to specific models or tasks in a close-world manner, we propose SAMRefiner, a universal and efficient approach by adapting SAM to the mask refinement task. The core technique of our model is the noise-tolerant prompting scheme. Specifically, we introduce a multi-prompt excavation strategy to mine diverse input prompts for SAM (\ie, distance-guided points, context-aware elastic bounding boxes, and Gaussian-style masks) from initial coarse masks. These prompts can collaborate with each other to mitigate the effect of defects in coarse masks. In particular, considering the difficulty of SAM to handle the multi-object case in semantic segmentation, we introduce a split-then-merge (STM) pipeline. Additionally, we extend our method to SAMRefiner++ by introducing an additional IoU adaption step to further boost the performance of the generic SAMRefiner on the target dataset. This step is self-boosted and requires no additional annotation. The proposed framework is versatile and can flexibly cooperate with existing segmentation methods. We evaluate our mask framework on a wide range of benchmarks under different settings, demonstrating better accuracy and efficiency. SAMRefiner holds significant potential to expedite the evolution of refinement tools. Our code is available at https://github.com/linyq2117/SAMRefiner.

3D Gaussian Splatting (3DGS) has witnessed its rapid development in novel view synthesis, which attains high quality reconstruction and real-time rendering. At the same time, there is still a gap before implicit neural representation (INR) can become a practical compressor due to the lack of stream decoding and real-time frame reconstruction on consumer-grade hardware. It remains a question whether the fast rendering and partial parameter decoding characteristics of 3DGS are applicable to video compression. To address these challenges, we propose a Toast-like Sliding Window (TSW) orthographic projection for converting any 3D Gaussian model into a video representation model. This method efficiently represents video by leveraging temporal redundancy through a sliding window approach. Additionally, the converted model is inherently stream-decodable and offers a higher rendering frame rate compared to INR methods. Building on TSW, we introduce an end-to-end trainable video compression method, GSVC, which employs deformable Gaussian representation and optical flow guidance to capture dynamic content in videos. Experimental results demonstrate that our method effectively transforms a 3D Gaussian model into a practical video compressor. GSVC further achieves better rate-distortion performance than NeRV on the UVG dataset, while achieving higher frame reconstruction speed (+30%~40% fps) and stream decoding. Code is available at [Github](https://github.com/actcwlf/GSVC)

Large Vision-Language Models (VLMs) exhibit significant potential in multimodal tasks but often struggle with hallucinations—responses that are plausible yet visually ungrounded. In this work, we investigate the layer-wise prediction tendencies of VLMs and conduct an in-depth analysis of their decoding mechanism. We observe that VLMs tend to ``overthink'' during the final stages of decoding, making significant prediction shifts in the last few layers often favoring incorrect results, which leads to a surge in hallucinative outputs. Leveraging this localized pattern, we propose a novel decoding strategy inspired by the momentum analogy used in gradient descent-based optimizers. Our method enforces decoding consistency across layers in an adaptive manner during forward passes—an under-explored approach in existing works. This strategy significantly improves the reliability and performance of VLMs in various multimodal tasks, while introducing only negligible efficiency overhead.

The advent of Large Language Models (LLMs) has paved the way for AI search engines, e.g., SearchGPT, showcasing a new paradigm in human-internet interaction. However, most current AI search engines are limited to text-only settings, neglecting the multimodal user queries and the text-image interleaved nature of website information. Recently, Large Multimodal Models (LMMs) have made impressive strides. Yet, whether they can function as AI search engines remains under-explored, leaving the potential of LMMs in multimodal search an open question. To this end, we first design a delicate pipeline, MMSearch-Engine, to empower any LMMs with multimodal search capabilities. On top of this, we introduce MMSearch, a comprehensive evaluation benchmark to assess the multimodal search performance of LMMs. The curated dataset contains 300 manually collected instances spanning 14 subfields, which involves no overlap with the current LMMs' training data, ensuring the correct answer can only be obtained within searching. By using MMSearch-Engine, the LMMs are evaluated by performing three individual tasks (requery, rerank, and summarization), and one challenging end-to-end task with a complete searching process. We conduct extensive experiments on closed-source and open-source LMMs. Among all tested models, GPT-4o with MMSearch-Engine achieves the best results, which surpasses the commercial product, Perplexity Pro, in the end-to-end task, demonstrating the effectiveness of our proposed pipeline. We further present error analysis to unveil current LMMs still struggle to fully grasp the multimodal search tasks, and conduct ablation study to indicate the potential of scaling test-time computation for AI search engine. We hope MMSearch may provide unique insights to guide the future development of multimodal AI search engine.

The ventral, dorsal, and lateral streams in high-level human visual cortex are implicated in distinct functional processes. Yet, deep neural networks (DNNs) trained on a single task model the entire visual system surprisingly well, hinting at common computational principles across these pathways. To explore this inconsistency, we applied a novel sparse decomposition approach to identify the dominant components of visual representations within each stream. Consistent with traditional neuroscience research, we find a clear difference in component response profiles across the three visual streams—identifying components selective for faces, places, bodies, text, and food in the ventral stream; social interactions, implied motion, and hand actions in the lateral stream; and some less interpretable components in the dorsal stream. Building on this, we introduce Sparse Component Alignment (SCA), a new method for measuring representational alignment between brains and machines that better captures the latent neural tuning of these two visual systems. We find that standard visual DNNs are more aligned with ventral than either dorsal or lateral representations. SCA reveals these distinctions with greater resolution than conventional population-level geometry, offering a measure of representational alignment that is sensitive to a system’s underlying axes of neural tuning.

Image watermarking methods are not tailored to handle small watermarked areas. This restricts applications in real-world scenarios where parts of the image may come from different sources or have been edited. We introduce a deep-learning model for localized image watermarking, dubbed the Watermark Anything Model (WAM). The WAM embedder imperceptibly modifies the input image, while the extractor segments the received image into watermarked and non-watermarked areas and recovers one or several hidden messages from the areas found to be watermarked. The models are jointly trained at low resolution and without perceptual constraints, then post-trained for imperceptibility and multiple watermarks. Experiments show that WAM is competitive with state-of-the art methods in terms of imperceptibility and robustness, especially against inpainting and splicing, even on high-resolution images. Moreover, it offers new capabilities: WAM can locate watermarked areas in spliced images and extract distinct 32-bit messages with less than 1 bit error from multiple small regions -- no larger than 10\% of the image surface -- even for small $256\times 256$ images. Training and inference code and model weights are available at https://github.com/facebookresearch/watermark-anything.

To achieve realistic immersion in landscape images, fluids such as water and clouds need to move within the image while revealing new scenes from various camera perspectives. Recently, a field called dynamic scene video has emerged, which combines single image animation with 3D photography. These methods use pseudo 3D space, implicitly represented with Layered Depth Images (LDIs). LDIs separate a single image into depth-based layers, which enables elements like water and clouds to move within the image while revealing new scenes from different camera perspectives. However, as landscapes typically consist of continuous elements, including fluids, the representation of a 3D space separates a landscape image into discrete layers, and it can lead to diminished depth perception and potential distortions depending on camera movement. Furthermore, due to its implicit modeling of 3D space, the output may be limited to videos in the 2D domain, potentially reducing their versatility. In this paper, we propose representing a complete 3D space for dynamic scene video by modeling explicit representations, specifically 4D Gaussians, from a single image. The framework is focused on optimizing 3D Gaussians by generating multi-view images from a single image and creating 3D motion to optimize 4D Gaussians. The most important part of proposed framework is consistent 3D motion estimation, which estimates common motion among multi-view images to bring the motion in 3D space closer to actual motions. As far as we know, this is the first attempt that considers animation while representing a complete 3D space from a single landscape image. Our model demonstrates the ability to provide realistic immersion in various landscape images through diverse experiments and metrics. Extensive experimental results are https://cvsp-lab.github.io/ICLR2025_3D-MOM/.

Hidden State Matching is shown to improve knowledge distillation of language models by encouraging similarity between a student and its teacher's hidden states, as demonstrated by DistilBERT and its successors. This typically uses a cosine loss, which restricts the dimensionality of the student to the teacher's, severely limiting the compression ratio. We present an alternative technique using Centered Kernel Alignment (CKA) to match hidden states of different dimensionality, allowing for smaller students and higher compression ratios. We show the efficacy of our method using encoder--decoder (BART, mBART \& T5) and encoder-only (BERT) architectures across a range of tasks from classification to summarization and translation. Our technique is competitive with the current state-of-the-art distillation methods at comparable compression rates. It requires no pretrained student models, but rather can synthesize new student models from scratch through pretraining distillation. It can scale to students smaller than the current methods, is no slower in training and inference, and is considerably more flexible.

The ability to reconstruct realistic and controllable upper body avatars from casual monocular videos is critical for various applications in communication and entertainment. By equipping the most recent 3D Gaussian Splatting representation with head 3D morphable models (3DMM), existing methods manage to create head avatars with high fidelity. However, most existing methods only reconstruct a head without the body, substantially limiting their application scenarios. We found that naively applying Gaussians to model the clothed chest and shoulders tends to result in blurry reconstruction and noisy floaters under novel poses. This is because of the fundamental limitation of Gaussians and point clouds -- each Gaussian or point can only have a single directional radiance without spatial variance, therefore an unnecessarily large number of them is required to represent complicated spatially varying texture, even for simple geometry. In contrast, we propose to model the body part with a neural texture that consists of coarse and pose-dependent fine colors. To properly render the body texture for each view and pose without accurate geometry nor UV mapping, we optimize another sparse set of Gaussians as anchors that constrain the neural warping field that maps image plane coordinates to the texture space. We demonstrate that Gaussian Head & Shoulders can fit the high-frequency details on the clothed upper body with high fidelity and potentially improve the accuracy and fidelity of the head region. We evaluate our method with casual phone-captured and internet videos and show our method archives superior reconstruction quality and robustness in both self and cross reenactment tasks. To fully utilize the efficient rendering speed of Gaussian splatting, we additionally propose an accelerated inference method of our trained model without Multi-Layer Perceptron (MLP) queries and reach a stable rendering speed of around 130 FPS for any subjects.