ICLR 2026 Papers

High-resolution imagery is often hindered by limitations in sensor technology, atmospheric conditions, and costs. Such challenges occur in satellite remote sensing, but also with handheld cameras, such as our smartphones. Hence, super-resolution aims to enhance the image resolution algorithmically. Since single-image super-resolution requires to solve an inverse problem, such methods must exploit strong priors, e.g. learned from high-resolution training data, or be constrained by auxiliary data, e.g. by a high-resolution guide from another modality. While qualitatively pleasing, such approaches often lead to "hallucinated" structures that do not match reality. In contrast, multi-image super-resolution (MISR) aims to improve the (optical) resolution by constraining the super-resolution process with multiple views taken with sub-pixel shifts. Here, we propose SuperF, a test-time optimization approach for MISR that leverages coordinate-based neural networks, also called neural fields. Their ability to represent continuous signals with an implicit neural representation (INR) makes them an ideal fit for the MISR task. The key characteristic of our approach is to share an INR for multiple shifted low-resolution frames and to jointly optimize the frame alignment with the INR. Our approach advances related INR baselines, adopted from burst fusion for layer separation, by directly parameterizing the sub-pixel alignment as optimizable affine transformation parameters and by optimizing via a super-sampled coordinate grid that corresponds to the output resolution. Our experiments yield compelling results on simulated bursts of satellite imagery and ground-level images from handheld cameras, with upsampling factors of up to 8. A key advantage of SuperF is that this approach does not rely on any high-resolution training data.

Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretability and semantic detail. To solve this, we present CoPRS, a Multi-modal Chain-of-Thought (MCoT)–based positional perception model that bridges language reasoning to segmentation through a differentiable and interpretable positional prior instantiated as a heatmap. By making the reasoning process clear via MCoT and expressing it as a dense, differentiable heatmap, this interface enhances interpretability and diagnostic analysis and yields more concentrated evidence on the target. A learnable concentration token aggregates features of the image and reasoning text to generate this positional prior, which is decoded to precise masks through a lightweight decoder, providing a direct connection between reasoning and segmentation. Across the RefCOCO series and ReasonSeg, CoPRS matches or surpasses the best reported metrics on each standard split under comparable protocols, with performance at or above prior state of the art across both validation and test partitions. Extensive experiments reveal that the quality of the heatmap strongly influences the resulting mask quality, supporting a consistent association between the reasoning output and downstream mask generation. Collectively, these findings support the utility of this paradigm in bridging reasoning and segmentation and show advantages in concentration driven by reasoning and predicting masks more precisely. Code, checkpoints and logs will be released.

Large vision–language models (VLMs) deliver state-of-the-art results on a wide range of multimodal tasks, yet they remain prone to visual hallucinations, producing content that is not grounded in the input image. Despite progress with visual supervision, reinforcement learning, and post-hoc attention reshaping, the representational origins of hallucinations remain unclear. Our study reveals that successful grounding emerges when adjacent visual tokens exhibit coherent alignment, while hallucinations arise when key vectors scatter isotropically, weakening cross-modal attention and blurring object boundaries. Building on this insight, we propose Depth and Spatial aware Cache Refinement (DSCR), a lightweight and training-free method that augments the Transformer's key-value (KV) cache with depth cues and 2D spatial proximity. DSCR clusters vectors within objects and separates those across surfaces, guiding attention toward relevant regions without any fine-tuning. Comprehensive evaluations show that DSCR consistently reduces hallucinations, delivering up to 23\% accuracy gains across MME, POPE, RePOPE, CHAIR, and a new depth-sensitive benchmark. Our findings highlight KV-coherence as a core factor behind hallucinations and demonstrate a practical, model-agnostic solution for enhancing VLM reliability.

Visual Prompt Tuning (VPT) has proven effective for parameter-efficient adaptation of pre-trained vision models to downstream tasks by inserting task-specific learnable prompt tokens. Despite its empirical success, a comprehensive theoretical understanding of VPT remains an active area of research. Building on the recently established connection between Mixture of Experts (MoE) and prompt-based methods, wherein each attention head can be conceptualized as a composition of multiple MoE models, we reinterpret VPT as the introduction of new *prompt experts* into these MoE structures. We identify a key limitation in existing VPT frameworks: the *restricted functional expressiveness* of prompt experts, which remain static and thus limited in their adaptability. To address this, we propose **Visual Adaptive Prompt Tuning (VAPT)**, a novel method that endows prompt experts with enhanced expressiveness while preserving parameter efficiency. Empirical evaluations on VTAB-1K and FGVC demonstrate that VAPT achieves *substantial performance improvements*, surpassing fully fine-tuned baselines by **7.34%** and **1.04%**, respectively. Moreover, VAPT consistently outperforms VPT while *requiring fewer additional parameters*. Furthermore, our theoretical analysis indicates that VAPT achieves optimal sample efficiency. Collectively, these results underscore the theoretical grounding and empirical advantages of our approach.

Gaussian Splatting has emerged as a powerful representation for high-quality, real-time 3D scene rendering. While recent works extend Gaussians with learnable textures to enrich visual appearance, existing approaches allocate a fixed square texture per primitive, leading to inefficient memory usage and limited adaptability to scene variability. In this paper, we introduce adaptive anisotropic textured Gaussians (A$^2$TG), a novel representation that generalizes textured Gaussians by equipping each primitive with an anisotropic texture. Our method employs a gradient-guided adaptive rule to jointly determine texture resolution and aspect ratio, enabling non-uniform, detail-aware allocation that aligns with the anisotropic nature of Gaussian splats. This design significantly improves texture efficiency, reducing memory consumption while enhancing image quality. Experiments on multiple benchmark datasets demonstrate that A$^2$TG consistently outperforms fixed-texture Gaussian Splatting methods, achieving comparable rendering fidelity with substantially lower memory requirements.

Large language models (LLMs) often generate hallucinations---unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task, many real-world applications require identifying hallucinated spans, which is a multi-step decision making process. This naturally raises the question of whether explicit reasoning can help the complex task of detecting hallucination spans. To answer this question, we first evaluate pretrained models with and without Chain-of-Thought (CoT) reasoning, and show that CoT reasoning has the potential to generate at least one correct answer when sampled multiple times. Motivated by this, we propose RL4HS, a reinforcement learning framework that incentivizes reasoning with a span-level reward function. RL4HS builds on Group Relative Policy Optimization and introduces Class-Aware Policy Optimization to mitigate reward imbalance issue. Experiments on the RAGTruth benchmark (summarization, question answering, data-to-text) show that RL4HS surpasses pretrained reasoning models and supervised fine-tuning, demonstrating the necessity of reinforcement learning with span-level rewards for detecting hallucination spans.

Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce a desired result. Reinforcement Learning (RL) offers a promising solution, but its adoption in image editing has been severely hindered by the lack of a high-fidelity, efficient reward signal. In this work, we present a comprehensive methodology to overcome this barrier, centered on the development of a state-of-the-art, specialized reward model. We first introduce $\textbf{EditReward-Bench}$, a comprehensive benchmark to systematically evaluate reward models on editing quality. Guided by this benchmark, we develop $\textbf{EditScore}$, an efficient model to evaluate the quality of instruction-guided editing. Through meticulous data curation and filtering, EditScore effectively matches the performance of learning proprietary VLMs. Furthermore, coupled with an effective self-ensemble strategy tailored for the generative nature of EditScore, our largest variant even surpasses GPT-5 in the benchmark. We then demonstrate that a high-fidelity reward model is the key to unlocking online RL for image editing. Our experiments show that, while even the largest open-source VLMs fail to provide an effective learning signal, EditScore enables efficient and robust policy optimization. Applying our framework to a strong base model, OmniGen2, results in a final model that shows a substantial and consistent performance uplift. Overall, this work provides the first systematic path from benchmarking to reward modeling to RL training in image editing, showing that a high-fidelity, domain-specialized reward model is the key to unlocking the full potential of RL in this domain. Our code, models, and benchmark will be released publicly.

Despite recent progress in 3D Gaussian-based head avatar modeling, efficiently generating high fidelity avatars remains a challenge. Current methods typically rely on extensive multi-view capture setups or monocular videos with per-identity optimization during inference, limiting their scalability and ease of use on unseen subjects. To overcome these efficiency drawbacks, we propose FastGHA, a feed-forward method to generate high-quality Gaussian head avatars from only a few input images while supporting real-time animation. Our approach directly learns a per-pixel Gaussian representation from the input images, and aggregates multi-view information using a transformer-based encoder that fuses image features from both DINOv3 and Stable Diffusion VAE. For real-time animation, we extend the explicit Gaussian representations with per-Gaussian features and introduce a lightweight MLP-based dynamic network to predict 3D Gaussian deformations from expression codes. Furthermore, to enhance geometric smoothness of the 3D head, we employ point maps from a pre-trained large reconstruction model as geometry supervision. Experiments show that our approach significantly outperforms existing methods in both rendering quality and inference efficiency, while supporting real-time dynamic avatar animation.

This work enables everyday devices, e.g., smartphones, to dynamically capture open-ended 3D scenes with rich, expandable semantics for immersive virtual worlds. While 3DGS and foundation models hold promise for semantic scene understanding, existing solutions suffer from unscalable semantic integration, prohibitive memory costs, and cross-view inconsistency. To respond, we propose Open-Set Semantic Gaussian Splatting SLAM, a GS-SLAM system augmented by an expandable semantic feature pool that decouples condensed scene-level semantics from individual 3D Gaussians. Each Gaussian references semantics via a lightweight indexing vector, reducing memory overhead by orders of magnitude while supporting dynamic updates. Besides, we introduce a consistency-aware optimization strategy alongside a Semantic Stability Guidance mechanism to enhance long-term, cross-view semantic consistency and resolve inconsistencies. Experiments demonstrate that our system achieves high-fidelity rendering with scalable, open-set semantics across both controlled and in-the-wild environments, supporting applications like 3D localization and scene editing. These results mark an initial yet solid step towards high-quality, expressive, and accessible 3D virtual world modeling. Our code will be publicly released.

LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these challenges through the lens of agents' memory utilization along two critical dimensions: object semantics (identifying objects based on personal meaning) and user patterns (recalling sequences from behavioral routines). To assess these capabilities, we construct Memento, an end-to-end two-stage evaluation framework comprising single-memory and joint-memory tasks. Our experiments reveal that current agents can recall simple object semantics but struggle to apply sequential user patterns to planning. Through in-depth analysis, we identify two critical bottlenecks: information overload and coordination failures when handling multiple memories. Based on these findings, we explore memory architectural approaches to address these challenges. Given our observation that episodic memory provides both personalized knowledge and in-context learning benefits, we design a hierarchical knowledge graph-based user-profile memory module that separately manages personalized knowledge, achieving substantial improvements on both single and joint-memory tasks.

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in visual understanding and reasoning, but they also impose significant computational burdens due to long visual sequence inputs. Recent works address this issue by pruning unimportant visual tokens, achieving substantial computational reduction while maintaining model performance. The core of token pruning lies in determining token importance, with current approaches primarily relying on attention scores from vision encoders or Large Language Models (LLMs). In this paper, we analyze the effectiveness of attention mechanisms in both vision encoders and LLMs. We find that vision encoders suffer from attention sink, leading to poor focus on informative foreground regions, while in LLMs, although prior studies have identified attention bias toward token positions, text-to-vision attention demonstrates resistance to this bias and enables effective pruning guidance in middle layers. Based on these observations, we propose $\textbf{LearnPruner}$, a two-stage token pruning framework that first removes redundant vision tokens via a learnable pruning module after the vision encoder, then retains only task-relevant tokens in the LLM's middle layer. Experimental results show that our LearnPruner can preserve approximately 95\% of the original performance while using only 5.5\% of vision tokens, and achieve 3.2$\times$ inference acceleration, demonstrating a superior accuracy-efficiency trade-off.

Causal attention has become a foundational mechanism in autoregressive Vision-Language models (VLMs), unifying textual and visual inputs under a single generative framework. However, existing causal mask-based strategies are inherited from large language models (LLMs) where they are tailored for text-only decoding, and their adaptation to vision tokens is insufficiently addressed in the prefill stage. Strictly masking future positions for vision queries introduces overly rigid constraints, which hinder the model’s ability to leverage future context that often contains essential semantic cues for accurate inference. In this work, we empirically investigate how different causal masking strategies affect vision-language inference and then propose a family of future-aware attentions tailored for this setting. We first empirically analyze the effect of previewing future tokens for vision queries and demonstrate that rigid masking undermines the model’s capacity to capture useful contextual semantic representations. Based on these findings, we propose a lightweight attention family that aggregates future visual context into past representations via pooling, effectively preserving the autoregressive structure while enhancing cross-token dependencies. We evaluate a range of causal masks across diverse vision-language inference settings and show that selectively compressing future semantic context into past representations benefits the inference.

Understanding the negation in a sentence is an important part of compositional understanding and logic in natural language. Many practical AI applications, such as autonomous driving, include precise instruction with negations. For example, following instruction to an AI assistant ”locate a parking spot without a vehicle” requires the assistant to not confuse between presence and absence of vehicles. Al- though joint embedding-based Vision Language Models (VLMs) like CLIP have revolutionized multi-modal tasks, they struggle to interpret negation. To address this limitation, recently many works proposed to solve the problem through a data- centric approach by introducing additional datasets with hard-negative samples for both image and text data. Contrary to these approaches, we present a zero-shot approach to tackle the negation understanding problem. We probe the properties of CLIP text embeddings and show that they follow compositional arithmetic op- erations, which allow the addition or removal of semantic information directly in the embedding space. We then present a rule-based approach to extract negated text from given caption and then use it to explicitly remove corresponding se- mantic information from original embedding, improving negation understanding in VLMs. Our approach does not require expensive training process to induce negation understanding into the model, and achieves the state-of-the-art perfor- mance on popular benchmark for negation understanding. We improve baseline CLIP model performance on NegBench from 25.5% to 67.0% for MCQ and from 50.9% to 56.1% for retrieval tasks. Even NegCLIP model which is fine-tuned on negtion datasets, our approach boosts its MCQ accuracy from 54.03% to 66.22% and retrieval accuracy from 59.25% to 60.1% showing strong performance.

Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections) and diverse, high-resolution inputs. Modern text-to-image diffusion models (e.g., SD3.5, FLUX) already encode essential physical and resolution priors, yet lack a framework to unleash them without resorting to latent inversion, which often locks object poses into contextually inappropriate orientations, or brittle attention surgery. We propose SHINE, a training-free framework for Seamless, High-fidelity Insertion with Neutralized Errors. SHINE introduces manifold-steered anchor loss, leveraging pretrained customization adapters (e.g., IP-Adapter) to guide latents for faithful subject representation while preserving background integrity. Artifact-suppression guidance and adaptive background blending are proposed to further eliminate low-quality outputs and visible seams. To address the lack of rigorous benchmarks, we introduce ComplexCompo, featuring diverse resolutions and challenging conditions such as low lighting, strong illumination, intricate shadows, and reflective surfaces. Experiments on ComplexCompo and DreamEditBench show state-of-the-art performance on standard metrics (e.g., DINOv2) and human-aligned scores (e.g., DreamSim, ImageReward, VisionReward). Code and benchmark will be publicly available upon publication.

3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this case, supervising Gaussians initialized from low-frequency sparse points with high-frequency images often induces uncontrolled densification and redundant primitives, degrading both efficiency and quality. Intuitively, this issue can be mitigated with scheduling strategies, which can be categorized into two paradigms: modulating target signal frequency via densification and modulating sampling frequency via image resolution. However, previous scheduling strategies are primarily hardcoded, failing to perceive the convergence behavior of the scene frequency. To address this, we reframe scene reconstruction problem from the perspective of signal structure recovery, and propose SIG, a novel scheduler that Synchronizes Image supervision with Gaussian frequencies. Specifically, we derive the average sampling frequency and bandwidth of 3D representations, and then regulate the training image resolution and the Gaussian densification process based on scene frequency convergence. Furthermore, we introduce Sphere-Constrained Gaussians, which leverage the spatial prior of initialized point clouds to control Gaussian optimization. Our framework enables frequency-consistent, geometry-aware, and floater-free training, achieving state-of-the-art performance with a substantial margin in both efficiency and rendering quality in large-scale scenes.

We introduce $\pi^3$, a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. Previous methods often anchor their reconstructions to a designated viewpoint, an inductive bias that can lead to instability and failures if the reference is suboptimal. In contrast, $\pi^3$ employs a fully permutation-equivariant architecture to predict affine-invariant camera poses and scale-invariant local point maps without any reference frames. This design not only makes our model inherently robust to input ordering, but also leads to higher accuracy and performance. These advantages enable our simple and bias-free approach to achieve state-of-the-art performance on a wide range of tasks, including camera pose estimation, monocular/video depth estimation, and dense point map reconstruction. Code and models will be publicly available.

Multimodal Large Language Models (MLLMs) encode images into visual tokens, aligning visual and textual signals within a shared latent space to facilitate cross-modal representation learning. The CLIP model is a widely adopted foundational vision language model whose vision encoder has played a critical role in the development of MLLMs such as LLaVA. However, the CLIP vision encoder suffers from notable limitations including being constrained to only handling fixed input resolutions and a failure to produce separated embeddings for dissimilar images. Replacing the vision encoder of an existing model typically incurs substantial computational costs because such a change often necessitates retraining the entire model pipeline. In this work, we identify two factors which underlie the limitations of the CLIP vision encoder: mesoscopic bias and interpolation bias. To address these issues, we propose QLIP, a drop-in replacement for CLIP that can be seamlessly integrated with existing MLLMs with only a few lines of code and can enhance both coarse-grained and fine-grained visual understanding, without re-training. QLIP is designed around an image quadtree which replaces the standard uniform grid patches with a novel content aware patchification. Our experimental results demonstrate that QLIP improves the general visual question answering accuracy of the LLaVA-1.5 model series across various model sizes—without requiring retraining or fine-tuning of the full MLLM. Notably, QLIP boosts detailed understanding performance on the challenging $V^*$ benchmark by up to 13.6%.

Segmentation in pathology image requires handling out-of-domain tissue morphologies and new pathologies beyond training distributions, where traditional closed-set segmentation approaches fail to generalize. Reasoning segmentation enables zero-shot generalization via prompting with text queries. However, existing reasoning segmentation models face three barriers when applied to pathology: (1) the vision encoder lack pathology-specific knowledge and robustness to staining variations, (2) the large language model (LLM) backbone for reasoning fails to identify whether it has gathered sufficient semantic context to trigger the segmentation output, and (3) no reasoning segmentation benchmarks and datasets exist for pathology analysis. Consequently, we introduce PathChat-SegR1, a reasoning segmentation model built upon pathology-specific vision encoders trained with a novel stain-invariant self-distillation for robust pathology image representations. Moreover, we propose Segmentation-Optimized GRPO (SO-GRPO), a reinforcement learning method specifically for reasoning segmentation that learns to determine optimal segmentation timing based on accumulated reasoning context. Finally, we construct a pathology-specific reasoning segmentation benchmark of 118,667 triplets of pathology image, ground-truth mask, query, and reasoning chain including both public and private pathology images. Zero-shot evaluation on pathology images with out-of-domain morphologies/pathologies shows 61\% improvement over state-of-the-art segmentation models.

3D single object tracking (SOT) remains a highly challenging task due to the inherent crux in learning representations from point clouds to effectively capture both spatial shape features and temporal motion features. Most existing methods employ a category-specific optimization paradigm, training the tracking model individually for each object category to enhance tracking performance, albeit at the expense of generalizability across different categories. In this work, we propose a robust category-unified 3D SOT model, referred to as SpatioTemporal Point Relation Parsing model (*PointRePar*), which is capable of joint training across multiple categories while excelling in unified feature learning for both spatial shapes and temporal motions. Specifically, the proposed *PointRePar* captures and parses the latent point relations across both spatial and temporal domains to learn superior shape and motion characteristics for robust tracking. On the one hand, it models the multi-scale spatial point relations using a Mamba-based U-Net architecture with adaptive point-wise feature refinement. On the other hand, it captures both the point-level and box-level temporal relations to exploit the latent motion features. Extensive experiments across three benchmarks demonstrate that our *PointRePar* not only outperforms the existing category-unified 3D SOT methods significantly, but also compares favorably against the state-of-the-art category-specific methods. Codes will be released.