ICLR 2026 论文列表

Recently, visualization-of-thought (VoT) has unlocked new opportunities for complex spatial reasoning in multimodal large language models (MLLMs) by complementing verbal reasoning with visual thinking. However, the autoregressive accumulation of lengthy and redundant tokens substantially increases computation and memory costs. In this paper, we present a new efficient framework for multimodal spatial reasoning, named *DARE*, designed to adaptively prune multimodal tokens across different network depths, reasoning hops, and modalities. First, *DARE* devises an intra- and inter-hop-aware differentiable retention mechanism to dynamically estimate token importance both within each reasoning step and across successive hops. Recognizing that deeper network layers encode visual cues into verbal streams, *DARE* introduces an asymmetric compression strategy that prunes tokens according to modality-specific redundancy and semantic importance. Furthermore, *DARE* incorporates a progressive KV-cache retention policy aligned with cross-modal fusion dynamics, further reducing memory overhead during autoregressive reasoning. Our method delivers substantial reductions in computation and memory footprint, averaging a 40.37\% reduction in FLOPs and 46.07\% reduction in KV caches usage, while consistently preserving or even improving reasoning performance across seven multimodal spatial reasoning benchmarks, and further generalizing to broader multimodal reasoning tasks, establishing a scalable and robust recipe for efficient multimodal reasoning.

Bridge diffusion models have shown great promise in image restoration by constructing a direct path from degraded to clean images. However, they often rely on predefined, high-action trajectories, which limits both sampling efficiency and final restoration quality. To address this, we propose a Consistency Geodesic Bridge (CGB) framework to construct a lower-action, geodesic trajectory. We achieve this by designing a novel bridge process that evolves over a shorter time horizon and makes the reverse process start from an entropy-regularized point that mixes the degraded image and Gaussian noise, which theoretically reduces the required trajectory action. To ensure this path approximates a geodesic on the data manifold, we innovatively leverage a pretrained denoiser as a dynamic geodesic guidance field. To solve this process efficiently, we draw inspiration from consistency models to learn a single-step mapping function, optimized via a continuous-time consistency objective tailored for our trajectory, so as to analytically map any state on the path to the target image. Notably, the path length in our framework becomes a tunable task-adaptive knob, allowing the model to adaptively balance information preservation against generative power for tasks of varying degradation, such as denoising versus super-resolution. Extensive experiments demonstrate that CGB achieves state-of-the-art performance across various image restoration tasks, while enabling high-quality recovery with a single or fewer sampling steps. Our project page is \url{https://cgbridge.github.io/}.

We consider the inverse problem of reconstructing the spatial layout of a place, a home floorplan for example, from a user’s movements inside that layout. Direct inversion is ill-posed since many floorplans can explain the same movement trajectories. We adopt a diffusion-based posterior sampler to generate layouts consistent with the measurements. While active research is in progress on generative inverse solvers, we find that the forward operator in our problem poses new challenges. The path planning process inside a floorplan is a non-invertible, non-differentiable function, and causes instability while optimizing using the likelihood score. We break-away from existing approaches and reformulate the likelihood score in a smoother embedding space. The embedding space is trained with a contrastive loss which brings compatible floorplans and trajectories close to each other, while pushing mismatched pairs far apart. We show that a surrogate form of the likelihood score in this embedding space is a valid approximation of the true likelihood score, making it possible to steer the denoising process towards the posterior. Across extensive experiments, our model CoGuide produces more consistent floorplans from trajectories, and is more robust than differentiable-planner baselines and guided-diffusion methods.

Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creates a critical memory bottleneck that fundamentally limits deployment scalability. While existing KV cache compression methods focus on retaining high-importance KV pairs to minimize storage, they often overlook the modality-specific semantic redundancy patterns that emerge distinctively in multi-modal KV caches. In this work, we first analyze how, beyond simple importance, the KV cache in LVLMs exhibits varying levels of redundancy across attention heads. We show that relying solely on importance can only cover a subset of the full KV cache information distribution, leading to potential loss of semantic coverage. To address this, we propose MixKV, a novel method that mixes importance with diversity for optimized KV cache compression in LVLMs. MixKV adapts to head-wise semantic redundancy, selectively balancing diversity and importance when compressing KV pairs. Extensive experiments demonstrate that MixKV consistently enhances existing methods across multiple LVLMs. Under extreme compression (budget=64), MixKV improves baseline methods by an average of 5.1% across five multi-modal understanding benchmarks and achieves remarkable gains of 8.0% and 9.0% for SnapKV and AdaKV on GUI grounding tasks, all while maintaining comparable inference efficiency. Furthermore, MixKV extends seamlessly to LLMs with comparable performance gains.

The growing demand for high-quality 3D mesh models has fueled the need for efficient 3D mesh compression techniques. However, existing methods often exhibit suboptimal compression performance due to the inefficient representation of mesh data. To address this issue, we propose a novel neural mesh compression method based on Sparse Implicit Representation (SIR). Specifically, SIR records signed distance field (SDF) values only on regular grids near the surface, enabling high-resolution structured representation of arbitrary geometric data with a significantly lower memory cost, while still supporting precise surface recovery. Building on this representation, we construct a lightweight Sparse Neural Compression (SNC) network to extract compact embedded features from the SIR and encode them into a bitstream. Extensive experiments and ablation studies demonstrate that our method outperforms state-of-the-art mesh and point cloud compression approaches in both compression performance and computational efficiency across a variety of mesh models. The source code is available at https://github.com/yydlmzyz1/SIR-SNC.

Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing a unified tokenizer. However, existing tokenizers face a significant performance trade-off between understanding and generation, stemming from the inherent conflict between high-level semantic abstraction and low-level pixel reconstruction. To tackle this challenge, we propose a generic and unified tokenizer, namely $\textbf{UniFlow}$, by flexibly adapting any visual encoder with a concise reconstruction decoder. Specifically, we introduce $\textit{layer-wise adaptive self-distillation}$ applied to the well-pretrained visual encoders, which enables UniFlow to simultaneously inherit the strong semantic features for visual understanding and flexibly adapt to model fine-grained details for visual generation. Moreover, we propose a lightweight $\textit{patch-wise pixel flow decoder}$, which efficiently achieves high-fidelity pixel reconstruction by modeling a conditional flow from the noisy state back to the patch-wise pixel domain. By leveraging the semantic features as visual conditions for the decoder, we effectively alleviate the training conflicts between understanding and generation. Furthermore, the patch-wise learning strategy simplifies the data distribution, thereby improving training efficiency. For instance, our 7B UniFlow-XL not only surpasses the 14B TokenFlow-XL by 6.05\% on average understanding benchmarks, but also achieves a competitive results in both visual reconstruction and generation, surpassing UniTok by 0.15 in rFID and 0.09 in gFID (without guidance), respectively.

Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are often ineffective or inapplicable to them. The straight-line, non-crossing trajectories of flow models pose challenges for diffusion-based approaches but also open avenues for novel solutions. In this paper, we introduce a predictor-corrector-based framework for inversion and editing in flow models. First, we propose Uni-Inv, an effective inversion method designed for accurate reconstruction. Building on this, we extend the concept of delayed injection to flow models and introduce Uni-Edit, a region-aware, robust image editing approach. Our methodology is tuning-free, model-agnostic, efficient, and effective, enabling diverse edits while ensuring strong preservation of edit-irrelevant regions. Extensive experiments across various generative models demonstrate the superiority and generalizability of Uni-Inv and Uni-Edit, even under low-cost settings.

Feature lifting has emerged as a crucial component in 3D scene understanding, enabling the attachment of rich image feature descriptors (e.g., DINO, CLIP) onto splat-based 3D representations. The core challenge lies in optimally assigning rich general attributes to 3D primitives while addressing the inconsistency issues from multi-view images. We present a unified, kernel- and feature-agnostic formulation of the feature lifting problem as a sparse linear inverse problem, which can be solved efficiently in closed form. Our approach admits a provable upper bound on the global optimal error under convex losses for delivering high quality lifted features. To address inconsistencies and noise in multi-view observations, we introduce two complementary regularization strategies to stabilize the solution and enhance semantic fidelity. Tikhonov Guidance enforces numerical stability through soft diagonal dominance, while Post-Lifting Aggregation filters noisy inputs via feature clustering. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on open-vocabulary 3D segmentation benchmarks, outperforming training-based, grouping-based, and heuristic-forward baselines while producing the lifted features in minutes. Demo Video, \textbf{Code} and \textbf{demo website} are all inside the supplementary.

Multimodal learning requires integrating heterogeneous modalities, such as structured records, visual imagery, and temporal signals. It has been revealed that this heterogeneity causes modality encoders to converge at different rates, making the multimodal learning imbalanced. We empirically observe that such an imbalance is related to the sharpness of the solution. Modality encoders that converge faster could be dragged into sharp regions due to inter-modal interference, degrading the generalization capability of unimodal features learned. Sharpness-Aware Minimization is effective in improving generalization via finding solutions in flat regions. However, its application in multimodal scenarios is challenging: 1) SAM pays excessive attention to the dominant modality, exacerbating modality imbalance, and 2) the perturbation gradient calculation is affected by interference from other modalities. To address these issues, we propose Multimodal Adaptive Sharpness-Aware Minimization (MASAM), which optimizes different modalities based on their dominance. We design an Adaptive Perturbation Score (APS) using convergence speed and gradient alignment to identify dominant modalities for SAM application. Our Modality-Decoupled Perturbation Scaling (MDPS) then reduces inter-modal interference during optimization, better aligning each modality with shared information. Extensive empirical evaluations on five multimodal datasets and six downstream tasks demonstrate that MASAM consistently attains flatter solutions, achieves balanced multimodal learning, and subsequently surpasses state-of-the-art methods across diverse datasets and tasks.

While current high-resolution depth estimation methods achieve strong results, they often suffer from computational inefficiencies due to reliance on heavyweight models and multiple inference steps, increasing inference time. To address this, we introduce PatchRefiner V2 (PRV2), which replaces heavy refiner models with lightweight encoders. This reduces model size and inference time but introduces noisy features. To overcome this, we propose a Coarse-to-Fine (C2F) module with a Guided Denoising Unit for refining and denoising the refiner features and a Noisy Pretraining strategy to pretrain the refiner branch to fully exploit the potential of the lightweight refiner branch. Additionally, we propose to adopt the Scale-and-Shift Invariant Gradient Matching (SSIGM) loss within local windows to enhance synthetic-to-real domain transfer. PRV2 outperforms state-of-the-art depth estimation methods on UnrealStereo4K in both accuracy and speed, using fewer parameters and faster inference. It also shows improved depth boundary delineation on real-world datasets like CityScapes, demonstrating its effectiveness.

Driven by the growing need for Oriented Object Detection (OOD), learning from point annotations under a weakly-supervised framework has emerged as a promising alternative to costly and laborious manual labeling. In this paper, we discuss two deficiencies in existing point-supervised methods: inefficient utilization and poor quality of pseudo labels. Therefore, we present Point2RBox-v3. At the core are two principles: $\textbf{1) Progressive Label Assignment (PLA)}$. It dynamically estimates instance sizes in a coarse yet intelligent manner at different stages of the training process, enabling the use of label assignment methods. $\textbf{2) Prior-Guided Dynamic Mask Loss (PGDM-Loss)}$. It is an enhancement of the Voronoi Watershed Loss from Point2RBox-v2, which overcomes the shortcomings of Watershed in its poor performance in sparse scenes and SAM's poor performance in dense scenes. To our knowledge, Point2RBox-v3 is the first model to employ dynamic pseudo labels for label assignment, and it creatively complements the advantages of SAM model with the watershed algorithm, which achieves excellent performance in both sparse and dense scenes. Our solution gives competitive performance, especially in scenarios with large variations in object size or sparse object occurrences: 66.09\%/56.86\%/41.28\%/46.40\%/19.60\%/45.96\% on DOTA-v1.0/DOTA-v1.5/DOTA-v2.0/DIOR/STAR/RSAR.

Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing approaches reduce dataset size by discarding samples, they often ignore the significant redundancy within each image -- particularly in the color space. To address this, we propose Dataset Color Quantization (DCQ), a unified framework that compresses visual datasets by reducing color-space redundancy while preserving information crucial for model training. DCQ achieves this by enforcing consistent palette representations across similar images, selectively retaining semantically important colors guided by model perception, and maintaining structural details necessary for effective feature learning. Extensive experiments across CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-1K show that DCQ significantly improves training performance under aggressive compression, offering a scalable and robust solution for dataset-level storage reduction. Code is available at \href{https://github.com/he-y/Dataset-Color-Quantization}{https://github.com/he-y/Dataset-Color-Quantization}.

Dense semantic segmentation in dynamic environments is fundamentally limited by the low-frame-rate (LFR) nature of standard cameras, which creates critical perceptual gaps between frames. To solve this, we introduce *Anytime Interframe Semantic Segmentation*: a new task for predicting segmentation at any arbitrary time using only a single past RGB frame and a stream of asynchronous event data. This task presents a core challenge: how to robustly propagate dense semantic features using a motion field derived from sparse and often noisy event data, all while mitigating feature degradation in highly dynamic scenes. We propose LiFR-Seg, a novel framework that directly addresses these challenges by propagating deep semantic features through time. The core of our method is an *uncertainty-aware warping process*, guided by an event-driven motion field and its learned, explicit confidence. A *temporal memory attention* module further ensures coherence in dynamic scenarios. We validate our method on the DSEC dataset and a new high-frequency synthetic benchmark (SHF-DSEC) we contribute. Remarkably, our LFR system achieves performance (73.82\% mIoU on DSEC) that is statistically indistinguishable from an HFR upper-bound (within 0.09\%) that has full access to the target frame. % We further demonstrate superior robustness in *highly dynamic* (M3ED-Drone \& Quadruped) and *low-light* (DSEC-Night) scenarios, where our method can even surpass the HFR baseline. We further demonstrate superior robustness across extreme scenarios: in highly dynamic (M3ED) tests, our method closely matches the HFR baseline's performance, while in the low-light (DSEC-Night) evaluation, it even surpasses it. This work presents a new, efficient paradigm for achieving robust, high-frame-rate perception with low-frame-rate hardware.

We present CogniMap3D, a bioinspired framework for dynamic 3D scene understanding and reconstruction that emulates human cognitive processes. Our approach maintains a persistent memory bank of static scenes, enabling efficient spatial knowledge storage and rapid retrieval. CogniMap3D integrates three core capabilities: a multi-stage motion cue framework for identifying dynamic objects, a cognitive mapping system for storing, recalling, and updating static scenes across multiple visits, and a factor graph optimization strategy for refining camera poses. Given an image stream, our model identifies dynamic regions through motion cues with depth and camera pose priors, then matches static elements against its memory bank. When revisiting familiar locations, CogniMap3D retrieves stored scenes, relocates cameras, and updates memory with new observations. Evaluations on video depth estimation, camera pose reconstruction, and 3D mapping tasks demonstrate its state-of-the-art performance, while effectively supporting continuous scene understanding across extended sequences and multiple visits.

We introduce Mono4DGS-HDR, the first system for reconstructing renderable 4D high dynamic range (HDR) scenes from unposed monocular low dynamic range (LDR) videos captured with alternating exposures. To tackle such a challenging problem, we present a unified framework with two-stage optimization approach based on Gaussian Splatting. The first stage learns a video HDR Gaussian representation in orthographic camera coordinate space, eliminating the need for camera poses and enabling robust initial HDR video reconstruction. The second stage transforms video Gaussians into world space and jointly refines the world Gaussians with camera poses. Furthermore, we propose a temporal luminance regularization strategy to enhance the temporal consistency of the HDR appearance. Since our task has not been studied before, we construct a new evaluation benchmark using publicly available datasets for HDR video reconstruction. Extensive experiments demostrate that Mono4DGS-HDR significantly outperforms alternative solutions adapted from state-of-the-art methods in both rendering quality and speed. The project page for this paper is available at https://liujf1226.github.io/Mono4DGS-HDR.

Audio inpainting seeks to restore missing segments in degraded recordings. Previous diffusion-based methods exhibit impaired performance when the missing region is large. We introduce the first approach that applies discrete diffusion over tokenized music representations from a pre-trained audio tokenizer, enabling stable and semantically coherent restoration of long gaps. Our method further incorporates two training approaches: a derivative-based regularization loss that enforces smooth temporal dynamics, and a span-based absorbing transition that provides structured corruption during diffusion. Experiments on the MusicNet and MAESTRO datasets with gaps up to 750ms show that our approach consistently outperforms strong baselines across range of gap lengths, for gaps of 150ms and above. This work advances musical audio restoration and introduces new directions for discrete diffusion model training. Visit our project page for examples and code.

The rapid growth of high-resolution, meticulously crafted AI-generated images poses a significant challenge to existing detection methods, which are often trained and evaluated on low-resolution, automatically generated datasets that do not align with the complexities of high-resolution scenarios. A common practice is to resize or center-crop high-resolution images to fit standard network inputs. However, without full coverage of all pixels, such strategies risk either obscuring subtle, high-frequency artifacts or discarding information from uncovered regions, leading to input information loss. In this paper, we introduce the **H**igh-Resolution **D**etail-**A**ggregation Network (**HiDA-Net**), a novel framework that ensures no pixel is left behind. We use the Feature Aggregation Module (FAM), which fuses features from multiple full-resolution local tiles with a down-sampled global view of the image. These local features are aggregated and fused with global representations for final prediction, ensuring that native-resolution details are preserved and utilized for detection. To enhance robustness against challenges such as localized AI manipulations and compression, we introduce Token-wise Forgery Localization (TFL) module for fine-grained spatial sensitivity and JPEG Quality Factor Estimation (QFE) module to disentangle generative artifacts from compression noise explicitly. Furthermore, to facilitate future research, we introduce **HiRes-50K**, a new challenging benchmark consisting of **50,568** images with up to **64 megapixels**. Extensive experiments show that HiDA-Net achieves state-of-the-art, increasing accuracy by over **13%** on the challenging Chameleon dataset and **8%** on our HiRes-50K.

Collaborative perception emphasizes enhancing environmental understanding by enabling multiple agents to share visual information with limited bandwidth resources. While prior work has explored the empirical trade-off between task performance and communication volume, a significant gap remains in the theoretical foundation. To fill this gap, we draw on information theory and introduce a pragmatic rate-distortion theory for multi-agent collaboration, specifically formulated to analyze performance-communication trade-off in goal-oriented multi-agent systems. This theory concretizes two key conditions for designing optimal communication strategies: supplying pragmatically relevant information and transmitting redundancy-less messages. Guided by these two conditions, we propose RDcomm, a communication-efficient collaborative perception framework that introduces two key innovations: i) task entropy discrete coding, which assigns features with task-relevant codeword-lengths to maximize the efficiency in supplying pragmatic information; ii) mutual-information-driven message selection, which utilizes mutual information neural estimation to approach the optimal redundancy-less condition. Experiments on 3D detection and BEV segmentation show that RDcomm achieves state-of-the-art accuracy on datasets DAIR-V2X, OPV2V, V2XSeq, and V2V4Real, while reducing communication volume by up to 108×. The code will be released.

Anticipating traffic accidents in real time is critical for intelligent transportation systems, yet remains challenging under edge-device constraints. We propose a lightweight spatio-temporal framework that introduces a temporally shifted distillation strategy, enabling a student model to acquire predictive temporal dynamics from a frozen image-based teacher without requiring a video pre-trained teacher. The student combines a RepMixer spatial encoding with a RWKV-inspired recurrent module for efficient long-range temporal reasoning. To enhance robustness under partial observability, we design a masking memory strategy that leverages memory retention to reconstruct missing visual tokens, effectively simulating occlusions and future events. In addition, multi-modal vision-language supervision enriches semantic grounding. Our framework achieves state-of-the-art performance on multiple real-world dashcam benchmarks while sustaining real-time inference on resource-limited platforms such as the NVIDIA Jetson Orin Nano. Remarkably, it is 3-7$\times$ smaller than leading approaches yet delivers superior accuracy and earlier anticipation, underscoring its practicality for deployment in intelligent vehicles.