ICLR 2026 Papers

While Large Vision-Language Models (LVLMs) achieve strong performance in multimodal tasks, hallucinations continue to affect their reliability. Among the three categories of hallucinations, which include object, attribute, and relation, relation hallucinations account for the largest proportion but have received the least attention. To address this challenge, we propose \textbf{ChainMPQ} (\textbf{M}ulti-\textbf{P}erspective \textbf{Q}uestions guided Interleaved Text-image Reasoning \textbf{Chain}), a training-free method that improves relational inference in LVLMs by utilizing accumulated textual and visual memories. ChainMPQ first extracts subject and object keywords from the question to enhance the corresponding image regions. It then constructs multi-perspective questions that focus on the three core components of a relationship: the subject, the object, and the relation that links them. These questions are sequentially input to the model, with textual and visual memories from earlier steps providing supporting context for subsequent ones, thereby forming an interleaved chain of image and text that guides progressive relational reasoning. Experiments on multiple LVLMs and benchmarks show that ChainMPQ substantially reduces relation hallucinations, while ablation studies further validate the effectiveness of its three core modules.

Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While several distillation-based approaches have exhibited the potential of one-step image restoration, extending existing approaches to VR remains challenging and underexplored, particularly when dealing with high-resolution video in real-world settings. In this work, we propose a one-step diffusion-based VR model, termed as SeedVR2, which performs adversarial VR training against real data. To handle the challenging high-resolution VR within a single step, we introduce several enhancements to both model architecture and training procedures. Specifically, an adaptive window attention mechanism is proposed, where the window size is dynamically adjusted to fit the output resolutions, avoiding window inconsistency observed under high-resolution VR using window attention with a predefined window size. To stabilize and improve the adversarial post-training towards VR, we further verify the effectiveness of a series of losses, including a proposed feature matching loss without significantly sacrificing training efficiency. Extensive experiments show that SeedVR2 can achieve comparable or even better performance compared with existing VR approaches in a single step.

The minimum-cost bipartite matching between two sets of points $R$ and $S$ in a metric space has a wide range of applications in machine learning, computer vision, and logistics. For instance, it can be used to estimate the $1$-Wasserstein distance between continuous probability distributions and for efficiently matching requests to servers while minimizing cost. However, the computational cost of determining the minimum-cost matching for general metrics spaces, poses a significant challenge, particularly in dynamic settings where points arrive over time and each update requires re-executing the algorithm. In this paper, given a fixed set $S$, we describe a deterministic algorithm that maintains, after $i$ additions to $R$, an $O(1/\delta^{0.631})$-approximate minimum-cost matching of cardinality $i$ between sets $R$ and $S$ in any metric space, with an amortized insertion time of $\widetilde{O}(n^{1+\delta})$ for adding points in $R$. To the best of our knowledge, this is the first algorithm for incremental minimum-cost matching that applies to arbitrary metric spaces. Interestingly, an important subroutine of our algorithm lends itself to efficient parallelization. We provide both a CPU implementation and a GPU implementation that leverages parallelism. Extensive experiments on both synthetic and real world datasets showcase that our algorithm either matches or outperforms all benchmarks in terms of speed while significantly improving upon the accuracy.

Egocentric vision is essential for both human and machine visual understanding, particularly in capturing the detailed hand-object interactions needed for manipulation tasks. Translating third-person views into first-person views significantly benefits augmented reality (AR), virtual reality (VR) and robotics applications. However, current exocentric-to-egocentric translation methods are limited by their dependence on 2D cues, synchronized multi-view settings, and unrealistic assumptions such as the necessity of an initial egocentric frame and relative camera poses during inference. To overcome these challenges, we introduce *EgoWorld*, a novel two-stage framework that reconstructs an egocentric view from rich exocentric observations, including projected point clouds, 3D hand poses, and textual descriptions. Our approach reconstructs a point cloud from estimated exocentric depth maps, reprojects it into the egocentric perspective, and then applies diffusion-based inpainting to produce dense, semantically coherent egocentric images. Evaluated on 4 datasets (i.e., H2O, TACO, Assembly101, and Ego-Exo4D), *EgoWorld* achieves state-of-the-art performance and demonstrates robust generalization to new objects, actions, scenes, and subjects. Moreover, *EgoWorld* exhibits robustness on in-the-wild examples, underscoring its practical applicability.

Traditional super-resolution (SR) methods assume an "ideal'' downscaling SR-kernel (e.g., bicubic downscaling) between the high-resolution (HR) image and the low-resolution (LR) image. Such methods fail once the LR images are generated differently. Current blind-SR methods aim to remove this assumption, but are still fundamentally restricted to rather simplistic downscaling SR-kernels (e.g., anisotropic Gaussian kernels), and fail on more complex (out of distribution) downscaling degradations. However, using the correct SR-kernel is often more important than using a sophisticated SR algorithm. In "KernelFusion'' we introduce a zero-shot diffusion-based method that uses an unrestricted kernel. Our method recovers the unique image-specific SR-kernel directly from the LR input image, while simultaneously recovering its corresponding HR image. KernelFusion exploits the principle that the correct SR-kernel is the one that maximizes patch similarity across different scales of the LR image. We first train an image-specific patch-based diffusion model on the single LR input image, capturing its unique internal patch statistics. We then reconstruct a larger HR image with the same learned patch distribution, while simultaneously recovering the correct downscaling SR-kernel that maintains this cross-scale relation between the HR and LR images. Empirical results demonstrate that KernelFusion handles complex downscaling degradations where existing Blind-SR methods fail, achieving robust kernel recovery and superior SR quality. By breaking free from predefined kernel assumptions and training distributions, KernelFusion establishes a new paradigm of zero-shot Blind-SR that can handle unrestricted, image-specific kernels previously thought impossible.

Although recent research applying text-to-image (T2I) diffusion models to real-world super-resolution (SR) has achieved remarkable progress, the misalignment of their targets leads to a suboptimal trade-off between inference speed and detail fidelity. Specifically, the T2I task requires multiple inference steps to synthesize images matching to prompts and reduces the latent dimension to lower generating difficulty. Contrariwise, SR can restore high-frequency details in fewer inference steps, but it necessitates a more reliable variational auto-encoder (VAE) to preserve input information. However, most diffusion-based SRs are multistep and use 4-channel VAEs, while existing models with 16-channel VAEs are overqualified diffusion transformers, e.g., FLUX (12B). To align the target, we present a one-step diffusion model for generative detail restoration, GenDR, distilled from a tailored diffusion model with a larger latent space. In detail, we train a new SD2.1-VAE16 (0.9B) via representation alignment to expand the latent space without increasing the model size. Regarding step distillation, we propose consistent score identity distillation (CiD) that incorporates SR task-specific loss into score distillation to leverage more SR priors and align the training target. Furthermore, we extend CiD with adversarial learning and representation alignment (CiDA) to enhance perceptual quality and accelerate training. We also polish the pipeline to achieve a more efficient inference. Experimental results demonstrate that GenDR achieves state-of-the-art performance in both quantitative metrics and visual fidelity.

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-quality rendering across a wide range of applications. However, its high computational demands and large storage costs pose significant challenges for deployment on mobile devices. In this work, we propose a mobile-tailored real-time Gaussian Splatting method, dubbed Mobile-GS, enabling efficient inference of Gaussian Splatting on edge devices. Specifically, we first identify alpha blending as the primary computational bottleneck, since it relies on the time-consuming Gaussian depth sorting process. To solve this issue, we propose a depth-aware order-independent rendering scheme that eliminates the need for sorting, thereby substantially accelerating rendering. Although this order-independent rendering improves rendering speed, it may introduce transparency artifacts in regions with overlapping geometry due to the scarcity of rendering order. To address this problem, we propose a neural view-dependent enhancement strategy, enabling more accurate modeling of view-dependent effects conditioned on viewing direction, 3D Gaussian geometry, and appearance attributes. In this way, Mobile-GS can achieve both high-quality and real-time rendering. Furthermore, to facilitate deployment on memory-constrained mobile platforms, we propose first-degree spherical harmonics distillation, a neural vector quantization technique, and a contribution-based pruning strategy to reduce the number of Gaussian primitives and compress the 3D Gaussian representation with the assistance of neural networks. Extensive experiments demonstrate that our proposed Mobile-GS achieves real-time rendering and compact model size while preserving high visual quality, making it well-suited for mobile applications.

Temporal grounding in long, untrimmed videos is critical for real-world video understanding, yet it remains a challenging task owing to complex temporal structures and pervasive visual redundancy. Existing methods rely heavily on supervised training with task-specific annotations, which inherently limits their scalability and adaptability due to the substantial cost of data collection and model retraining. Although a few recent works have explored training-free or zero-shot grounding, they seldom address the unique challenges posed by long videos. In this paper, we propose HiTeA (Hierarchical Temporal Alignment), a novel, training-free framework explicitly designed for long-video temporal grounding. HiTeA introduces a hierarchical temporal decomposition mechanism that structures videos into events, scenes, and actions, thereby aligning natural language queries with the most appropriate temporal granularity. Candidate segments are then matched with queries by leveraging pre-trained vision–language models (VLMs) to directly compute segment–text similarity, thereby obviating the need for any task-specific training or fine-tuning. Extensive experiments on both short- and long-video benchmarks show that HiTeA not only substantially outperforms all existing training-free methods (e.g., achieving 44.94% R\@0.1 on TACoS, representing an absolute gain of 12.4%) but also achieves competitive performance against state-of-the-art supervised baselines under stricter metrics. The code is available at https://anonymous.4open.science/r/HiTeA_code.

Radiance fields have emerged as a predominant representation for modeling 3D scene appearance. Neural formulations such as Neural Radiance Fields provide high expressivity but require costly ray marching for rendering, whereas primitive-based methods such as 3D Gaussian Splatting offer real-time efficiency through splatting, yet at the expense of representational power. Inspired by advances in both these directions, we introduce splattable neural primitives, a new volumetric representation that reconciles the expressivity of neural models with the efficiency of primitive-based splatting. Each primitive encodes a bounded neural density field parameterized by a shallow neural network. Our formulation admits an exact analytical solution for line integrals, enabling efficient computation of perspectively accurate splatting kernels. As a result, our representation supports integration along view rays without the need for costly ray marching. The primitives flexibly adapt to scene geometry and, being larger than prior analytic primitives, reduce the number required per scene. On novel-view synthesis benchmarks, our approach matches the quality and speed of 3D Gaussian Splatting while using 10x fewer primitives and 6x fewer parameters. These advantages arise directly from the representation itself, without reliance on complex control or adaptation frameworks.

We propose a method for inferring an egocentric dense depth map from an RGB image and a sparse point cloud. The crux of our method lies in modeling the 3D scene implicitly within the latent space and learning an inductive bias in an unsupervised manner through principles of Structure-from-Motion. To force the learning of this inductive bias, we propose to optimize for an ill-posed objective: predicting latent features that are not observed in the input view, but exists in the 3D scene. This is facilitated by means of rigid warping of latent features from the input view to a nearby or adjacent (co-visible) view of the same 3D scene. "Empty" regions in the latent space that correspond to regions occluded from the input view are completed by a Contextual eXtrapolation mechanism based on features visible in input view. Once learned, the inductive bias can be transferred to modulate the features of the input view to improve fidelity. We term our method "Occluded Region Completion as Supervision" or ORCaS. We evaluate ORCaS on VOID1500 and NYUv2 benchmark datasets, where we improve over the best existing method by 8.91% across all metrics. ORCaS also improves generalization from VOID1500 to ScanNet and NYUv2 by 15.7% and robustness to low density inputs by 31.2%. Code will be released.

Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and inefficient representations. The Gray-Wyner network, a classical concept from information theory, offers a principled framework for separating common and task-specific information. Inspired by this idea, we develop a learnable three-channel codec that disentangles shared information from task-specific details across multiple vision tasks. We characterize the limits of this approach through the notion of lossy common information, and propose an optimization objective that balances inherent tradeoffs in learning such representations. Through comparisons of three codec architectures on two-task scenarios spanning six vision benchmarks, we demonstrate that our approach substantially reduces redundancy and consistently outperforms independent coding. These results highlight the practical value of revisiting Gray-Wyner theory in modern machine learning contexts, bridging classic information theory with task-driven representation learning.

The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations of existing methods: supervised fine-tuning (SFT) often compromises general capabilities, while reinforcement fine-tuning (RFT) prioritizes textual reasoning over visual perception. To bridge this gap, we propose a novel two-stage task that structures visual perception learning as a coarse-to-fine progressive process. Based on this task formulation, we develop ViPER, a self-bootstrapping framework specifically designed to enable iterative evolution through self-critiquing and self-prediction. By synergistically integrating image-level and instance-level reconstruction with a two-stage reinforcement learning strategy, ViPER establishes a closed-loop training paradigm, where internally synthesized data directly fuel the enhancement of perceptual ability. Applied to the Qwen2.5-VL family, ViPER produces the Qwen-Viper series. With an average gain of 1.7\% on seven comprehensive benchmarks spanning various tasks and up to 6.0\% on fine-grained perception, Qwen-Viper consistently demonstrates superior performance across different vision-language scenarios while maintaining generalizability. Beyond enabling self-improvement in perceptual capabilities, ViPER provides concrete evidence for the reciprocal relationship between generation and understanding, a breakthrough to developing more autonomous and capable VLMs.

Hand motion plays a central role in human interaction, yet modeling realistic 4D hand motion (*i.e.*, 3D hand pose sequences over time) remains challenging. Research in this area is typically divided into two tasks: (1) Estimation approaches reconstruct precise motion from visual observations, but often fail under hand occlusion or absence; (2) Generation approaches focus on synthesizing hand poses by exploiting generative priors under multi-modal structured inputs and infilling motion from incomplete sequences. However, this separation not only limits the effective use of heterogeneous condition signals that frequently arise in practice, but also prevents knowledge transfer between the two tasks. We present **UniHand**, a unified diffusion-based framework that formulates both estimation and generation as conditional motion synthesis. UniHand integrates heterogeneous inputs by embedding structured signals into a shared latent space through a joint variational autoencoder, which aligns conditions such as MANO parameters and 2D skeletons. Visual observations are encoded with a frozen vision backbone, while a dedicated hand perceptron extracts hand-specific cues directly from image features, removing the need for complex detection and cropping pipelines. A latent diffusion model then synthesizes consistent motion sequences from these diverse conditions. Extensive experiments across multiple benchmarks demonstrate that UniHand delivers robust and accurate hand motion modeling, maintaining performance under severe occlusions and temporally incomplete inputs.

Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equivariance in the context of reconstruction networks, and show that the combination of self-supervised splitting losses and equivariant reconstruction networks results in unbiased estimates of the supervised loss. Through a series of experiments on image inpainting, accelerated magnetic resonance imaging, sparse-view computed tomography, and compressive sensing, we demonstrate that the proposed loss achieves state-of-the-art performance in settings with highly rank-deficient forward models.

Speech emotion recognition (SER) hinges on front-ends that expose informative time-frequency (TF) structure from raw speech. Classical short-time Fourier and wavelet transforms impose fixed resolution trade-offs, while prior "superlet" variants rely on integer orders and hand-tuned hyperparameters. We revisit TF analysis from first principles and formulate a learnable continuum of superlet transforms. Starting from DC-corrected analytic Morlet wavelets, we define superlets as multiplicative ensembles of wavelet responses and realize learnable fractional orders via softmax-normalized weights over discrete orders, computed as a log-domain geometric mean. We establish admissibility (zero mean) and continuity in order and frequency, and characterize approximate analyticity by bounding negative-frequency leakage as a function of an effective cycle parameter. Building on these results, we introduce the Learnable Fractional Superlet Transform (LFST), a fully differentiable front-end that jointly optimizes (i) a monotone, log-spaced frequency grid, (ii) frequency-dependent base cycles, and (iii) learnable fractional-order weights, all trained end-to-end. LFST further includes a learnable asymmetric hard-thresholding (LAHT) module that promotes sparse, denoised TF activations while preserving transients; we provide sufficient conditions for boundedness and stability under mild cycle and grid constraints. To exploit LFST for SER, we design the Spectro-Temporal Emotion Encoder (STEE), which consumes two-channel TF maps, magnitude $S$ and phase-congruency $\kappa$, through a compact multi-scale stack with residual temporal and depthwise-frequency blocks, Adaptive FiLM gating, axial (time-axis) self-attention, global attentive pooling, and a lightweight classifier. The full LFST+STEE system is trained in a standard train-validate-test regime using focal loss with optional class rebalancing, and is validated on IEMOCAP, EMO-DB, and the private NSPL-CRISE dataset under standard protocols. By unifying a principled, learnable TF transform with a compact encoder, LFST+STEE replaces ad hoc front-ends with a mathematically grounded alternative that is differentiable, stable, and adaptable to data, enabling systematic ablations over frequency grids, cycle schedules, and fractional orders within a single end-to-end model. The source code for this paper is shared in this anonymous repository: https://anonymous.4open.science/r/LFST-for-SER-C5D2.

Many black-box techniques for quantifying the uncertainty of large language models (LLMs) rely on repeated LLM sampling, which can be computationally expensive. Therefore, practical applicability demands reliable estimation from few samples. Semantic entropy (SE) is a popular sample-based uncertainty estimator with a discrete formulation attractive for the black-box setting. Recent extensions of SE exhibit improved LLM hallucination detection, but do so with less interpretable methods that admit additional hyperparameters. For this reason, we revisit the canonical discrete semantic entropy (DSE) estimator, finding that it underestimates the ``true'' semantic entropy, as expected from theory. We propose a modified semantic alphabet size estimator, and illustrate that using it to adjust DSE for sample coverage results in more accurate SE estimation in our setting of interest. Furthermore, we find that two semantic alphabet size estimators, including our proposed, flag incorrect LLM responses as well or better than many top-performing alternatives, with the added benefit of remaining highly interpretable.

Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall short on new tasks not covered in the training data. When finetuned on limited demonstrations of a new task, these policies often overfit to the specific demonstrations---not only losing their prior abilities to solve a wide variety of generalist tasks but also failing to generalize within the new task itself. In this work, we aim to develop a method that preserves the generalization capabilities of the generalist policy during finetuning, allowing a single policy to robustly incorporate a new skill into its repertoire. Our goal is a single policy that both learns to generalize to variations of the new task and retains the broad competencies gained from pretraining. We show that this can be achieved through a simple yet effective strategy: interpolating the weights of a finetuned model with that of the pretrained model. We show, across extensive simulated and real-world experiments, that such model merging produces a single model that inherits the generalist abilities of the base model and learns to solve the new task robustly, outperforming both the pretrained and finetuned model on out-of-distribution variations of the new task. Moreover, we show that model merging enables continual acquisition of new skills in a lifelong learning setting, without sacrificing previously learned generalist abilities.

Recent years have witnessed remarkable progress in multimodal learning within computational pathology. Existing models primarily rely on vision and language modalities; however, language alone lacks molecular specificity and offers limited pathological supervision, leading to representational bottlenecks. In this paper, we propose STAMP, a Spatial Transcriptomics-Augmented Multimodal Pathology representation learning framework that integrates spatially-resolved gene expression profiles to enable molecule-guided joint embedding of pathology images and transcriptomic data. Our study shows that self-supervised, gene-guided training provides a robust and task-agnostic signal for learning pathology image representations. Incorporating spatial context and multi-scale information further enhances model performance and generalizability. To support this, we constructed SpaVis-6M, the largest Visium-based spatial transcriptomics dataset to date, and trained a spatially-aware gene encoder on this resource. Leveraging hierarchical multi-scale contrastive alignment and cross-scale patch localization mechanisms, STAMP effectively aligns spatial transcriptomics with pathology images, capturing spatial structure and molecular variation. We validate STAMP across six datasets and four downstream tasks, where it consistently achieves strong performance. These results highlight the value and necessity of integrating spatially resolved molecular supervision for advancing multimodal learning in computational pathology. The code is included in the supplementary materials. The pretrained weights and SpaVis-6M will be released for community development after reviewing the manuscript.

While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios---particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose $\textbf{Follow-Your-Shape}$, a training- and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a $\textbf{Trajectory Divergence Map (TDM)}$ by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a $\textbf{Scheduled KV Injection}$ mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce $\textit{\textbf{ReShapeBench}}$, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement.