paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ECCV 2026

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model

Youngwan Lee, Soojin Jang, Yoorhim Cho, Seunghwan Lee, Yong-Ju Lee, Sung Ju Hwang

Spatial reasoning is foundational for Vision-Language Mod-els (VLMs), particularly when deployed as Vision-Language-Action (VLA)agents in physical environments. However, existing benchmarks predomi-nantly focus on elementary, single-hop relations, neglecting the multi-hopcompositional reasoning and precise visual grounding essential for real-world scenarios. To address this, we introduce MultihopSpatial, o!er-ing three key contributions: (1) A comprehensive benchmark designedfor multi-hop and compositional spatial reasoning, featuring 1- to 3-hopcomplex queries across diverse spatial perspectives. (2) Acc@50IoU,a complementary metric that simultaneously evaluates reasoning andvisual grounding by requiring both answer selection and precise bound-ing box prediction—capabilities vital for robust VLA deployment. (3)MultihopSpatial-Train, a dedicated large-scale training corpus to fos-ter spatial intelligence. Extensive evaluation of 37 state-of-the-art VLMsyields eight key insights, revealing that compositional spatial reasoningremains a formidable challenge. Finally, we demonstrate that reinforce-ment learning post-training on our corpus enhances both intrinsic VLMspatial reasoning and downstream embodied manipulation performance.

ECCV 2026

MoE-KD: Your Teacher Model is Worth Mixture-of-Experts for Knowledge Distillation

Kuo Shi, Wenjie Zhu, Bo Peng

Knowledge distillation (KD) aims to transfer useful informa-tion from a large-scale model (teacher) to a lightweight model (student).Classical KD focuses on leveraging the teacher’s predictions as soft labelsto regularize student training. However, the exact match of predictionsin Kullback-Leibler (KL) divergence could be somewhat in conflict withthe classification objective, given that the distribution discrepancies be-tween teacher-generated predictions and ground-truth annotations tendto be fairly severe. In this paper, we rethink the role of teacher predic-tions from a Mixture-of-Experts (MoE) perspective and transfer knowl-edge by introducing teacher predictions as latent variables to reformulatethe classification objective. This MoE strategy results in breaking downthe vanilla classification task into a mixture of easier subtasks with theteacher classifier as a gating function to weigh the importance of sub-tasks. Each subtask is efficiently conquered by distinct experts that areeffectively implemented by resorting to multi-level teacher outputs. Wefurther develop a theoretical framework to formulate our method, termedMoE-KD, as an Expectation-Maximization (EM) algorithm and provideproof of the convergence. Extensive experiments manifest that MoE-KDoutperforms advanced knowledge distillers on mainstream benchmarks.

ECCV 2026

MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models

Alejandro Lozano, Ryan D&amp, #x27, Cunha, Daniel Jarquin, Min Sun, Josiah Aklilu, James Burgess, Yuhui Zhang, Paola Robayo, Jin Ye, Ming Hu, Zhongying Deng, Junjun He, Xin Chen, Yue Yao, Robert Tibshirani, Jeffrey Nirschl, Xiaoxiao Sun, Serena Yeung-Levy

Vision and language models (VLMs) hold immense promiseto transform biomedical imaging workflows, from detecting lesions inchest X-rays to profiling cellular features in microscopy. Realizing this po-tential, however, requires robust and fine-grained visual perception. Mod-els need to correctly interpret subtle features in images, and they mustdo so across diverse biomedical modalities, scales, and contexts. Never-theless, current benchmarks remain limited. To address these gaps, weintroduce the Massive Multimodal Biomedical Understanding (MMBU)benchmark. It is the largest biomedical vision and language benchmarkto date, covering 35 submodalities with rich structured metadata. Itincludes both open and closed versions of ungrounded classification,grounded classification, and object detection, enabling systematic evalu-ation of model performance across biological scales, clinical settings, andimaging modalities. Evaluating 15 open-weight and 2 frontier VLMs, wefind that while medical adaptation provides measurable gains for somemodels, the high accuracy often reported on established benchmarks canmask deficiencies in visual perception and domain generalization.

ECCV 2026

MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

Sijun Dai, Qiang Huang, Xiaoxing You, Jun Yu

Retrieval-Augmented Generation (RAG) mitigates halluci-nations in Multimodal Large Language Models (MLLMs), yet existingsystems struggle with complex cross-modal reasoning. Flat vector retrievaloften ignores structural dependencies, while current graph-based methodsrely on costly “translation-to-text” pipelines that discard fine-grainedvisual information. To address these limitations, we propose MG2 -RAG,a lightweight Multi-Granularity Graph RAG framework that jointlyimproves graph construction, modality fusion, and cross-modal retrieval.MG2 -RAG constructs a hierarchical multimodal knowledge graph bycombining lightweight textual parsing with entity-driven visual ground-ing, enabling textual entities and visual regions to be fused into unifiedmultimodal nodes that preserve atomic evidence. Building on this repre-sentation, we introduce a multi-granularity graph retrieval mechanismthat aggregates dense similarities and propagates relevance across thegraph to support structured multi-hop reasoning. Extensive experimentsacross four representative multimodal tasks (i.e., retrieval, knowledge-based VQA, reasoning, and classification) demonstrate that MG2 -RAGconsistently achieves state-of-the-art performance while reducing graphconstruction overhead with an average 43.3× speedup and 23.9× costreduction compared with advanced graph-based frameworks. The sourcecode is publicly available at https://github.com/Daboolu/MG2-RAG.

ECCV 2026

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

Chunzheng Zhu, Jiaqi Zeng, Junyu Jiang, Jianxin Lin, Yijun Wang

High-precision medical diagnosis relies not only on staticimaging features but also on the implicit diagnostic memory experts in-stantly invoke during image interpretation. We pinpoint a fundamentalcognitive misalignment in medical VLMs caused by discrete tokeniza-tion, leading to quantization loss, long-range information dissipation,and missing case-adaptive expertise. To bridge this gap, we proposeMedSynapse-V, a framework for latent diagnostic memory evolution thatsimulates the experiential invocation of clinicians by dynamically synthe-sizing implicit diagnostic memories within the model’s hidden stream.Specifically, it begins with a Meta Query for Prior Memorizationmechanism, where learnable probes retrieve structured priors from ananatomical prior encoder to generate condensed implicit memories. Toensure clinical fidelity, we introduce Causal Counterfactual Refine-ment (CCR) which leverages reinforcement learning and counterfactualrewards derived from region-level feature masking to quantify the causalcontribution of each memory, thereby pruning redundancies and aligninglatent representations with diagnostic logic. This evolutionary processculminates in Intrinsic Memory Transition (IMT), a privileged-autonomous dual-branch paradigm that internalizes teacher-branch di-agnostic patterns into the student-branch via full-vocabulary divergencealignment. Comprehensive empirical evaluations across multiple datasetsdemonstrate that MedSynapse-V, by transferring external expertise intoendogenous parameters, significantly outperforms existing state-of-the-art methods, particularly Chain-of-Thought (CoT) paradigms, in diag-nostic accuracy and multi-dataset generalization without compromisingthe inference efficiency of standard VLMs.

ECCV 2026

Manifold-Aware Spectral Compaction: A Graph Signal Processing Perspective on Online Gaussian Reduction for 3DGS SLAM

Jiayi Tian, Jiaze Wang, Tian Xia, Wenzhe Zhao, Pengju Ren

3D Gaussian Splatting (3DGS) has established itself as apremier technique for high-fidelity radiance field rendering. However, itsapplication in SLAM tasks is frequently hindered by the explosive growthof redundant Gaussian primitives, which imposes prohibitive memoryand rendering overhead. Existing compaction strategies predominantlyrely on heuristic pruning based on importance scores; such methods oftenfail to provide global fidelity guarantees and can disrupt the optimizationcontinuity required for online tracking. To address these challenges, weintroduce Manifold-Aware Spectral Compaction (MASC), a frameworkthat reformulates map reduction as a continuous signal reconstructiontask mapped onto a Riemannian manifold. We first construct a topology-aware graph representation using Symmetrized Kullback-Leibler diver-gence to precisely capture the statistical connectivity between primi-tives. To ensure real-time efficiency, we implement an incremental Nys-tröm spectral embedding strategy to project the Gaussian map onto alow-dimensional spectral subspace. We further derive a mathematicallyrigorous, closed-form solution for primitive aggregation leveraging Bures-Wasserstein barycenters, which theoretically ensures the conservation oflocal radiance field moments. Extensive evaluations on the Replica andTUM RGB-D datasets demonstrate that MASC achieves a 2.8× reduc-tion in GPU memory and a 2.4× speedup in rendering throughput.Remarkably, our method maintains or even enhances tracking accuracywhile eliminating approximately 60% of redundant primitives, achiev-ing an ATE of 0.98 cm on the TUM dataset. These results substantiatethat MASC provides an efficient and principled plug-and-play pathwayfor scalable, long-term neural rendering SLAM.

ECCV 2026

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

Qi Li, Yanzhe Zhao, Yongxin Zhou, Yameng Wang, Yandong Yang, Yuanjia Zhou, Jinxiang Liu

Multimodal Large Language Models (MLLMs) have shownimmense promise in universal multimodal retrieval, which aims to findrelevant items of various modalities for a given query. However, theirpractical application is often hindered by the substantial computationalcost incurred from processing a large number of tokens from visual inputs.In this paper, we propose Magic-MM-Embedding, a series of novel modelsthat achieve both high efficiency and state-of-the-art performance inuniversal multimodal embedding. Our approach is built on two synergisticpillars: (1) a highly efficient MLLM architecture incorporating visualtoken compression to drastically reduce inference latency and trainingtime, and (2) a multi-stage progressive training strategy designed tonot only recover but significantly boost performance. This coarse-to-finetraining paradigm begins with extensive continued training to restoremultimodal understanding and generation capabilities, progresses tolarge-scale contrastive pretraining and hard negative mining to enhancediscriminative power, and culminates in a task-aware fine-tuning stageguided by an MLLM-as-a-Judge for precise data curation. Comprehensiveexperiments show that our model outperforms existing methods by alarge margin while being more inference-efficient.

ECCV 2026

Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Stephan Alaniz, Marco Grangetto

Sparse autoencoders (SAEs) have recently been proposed asinterpretable tools for concept-level manipulation, under the assumptionthat isolated features can serve as controllable intervention points. In thiswork, we systematically evaluate this assumption in the context of ob-ject erasure and steering in diffusion models. We show that while SAEsreliably detect and localize semantic concepts within diffusion modelactivations, direct intervention in their latent space frequently inducesout-of-distribution activations, resulting in severe visual artifacts. To dis-entangle detection from intervention, we use SAE activations purely assemantic detectors to identify image regions containing the target object,and replace those patch embeddings with the ones that do not containit. This detection-based replacement preserves the diffusion model’s ac-tivation statistics and produces significantly cleaner erasure results thanlatent steering. Our findings reveal a fundamental gap between conceptdetection and concept intervention in diffusion models: monosemanticor sparse features are not inherently suitable as control knobs for steer-ing. These results position SAEs as powerful interpretability tools foranalyzing generative models, but highlight important limitations whenused for direct manipulation, such as unlearning. We release the code athttps://eidoslab.github.io/PER/.

ECCV 2026

Lifting Ego World Models for Planning and Control

Alex Wang, Trevor Darrell, Pavel Izmailov, Yutong Bai, Amir Bar

World models of embodied agents predict future observationsconditioned on an action taken by the agent. For complex embodiments,action spaces are high-dimensional and difficult to specify: for example,precisely controlling a human agent requires specifying the motion ofeach joint. This makes the world model hard to control and expensiveto plan with as search-based methods like CEM scale poorly with actiondimensionality. To address this issue, we train a lightweight policy thatmaps high-level actions to sequences of low-level joint actions. Composingthis policy with the frozen world model produces a lifted world model thatpredicts a sequence of future observations from a single high-level action.We instantiate this framework for a human-like embodiment, defining thehigh-level action space as a small set of 2D waypoints annotated on thecurrent observation frame, each specifying a near-term goal position for aleaf joint (pelvis, head, hands). Waypoints are low-dimensional, visuallyinterpretable, and easy to specify manually or to search over. We showthat the lifted world model substantially outperforms searching directlyin low-level joint space (3.8× lower mean joint error to the goal pose),while remaining more compute-efficient and generalizing to environmentsunseen by the policy.

ECCV 2026

Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision

Dominick Reilly, Manish Govind, Le Xue, Srijan Das

Vision Language Models (VLMs) have achieved strong per-formance across diverse video understanding tasks. However, their view-point invariant training limits their ability to understand egocentricproperties (e.g., human-object interactions) from exocentric video ob-servations. This limitation is critical for applications such as Activi-ties of Daily Living (ADL) monitoring, where understanding egocen-tric properties is essential yet egocentric cameras are impractical to de-ploy, making it impossible to simply collect egocentric data at test time.To address this challenge, we propose Ego2ExoVLM, a VLM frame-work that learns to infer egocentric properties from exocentric videos.Our key insight is that time-synchronized ego-exo video pairs can beleveraged during training, where the egocentric viewpoint provides priv-ileged supervision (rich egocentric signal available only at training time).Ego2ExoVLM achieves this through two components: Ego2Exo Se-quence Distillation, which transfers egocentric reasoning through alanguage-level sequence distillation objective, and Ego Adaptive Vi-sual Tokens, which encourages the model to surface relevant interac-tion cues within exocentric video representations. To measure this ca-pability, we introduce Ego-in-Exo Perception, a benchmark designedto evaluate the understanding of egocentric properties from exocentricvideos. Ego2ExoVLM is evaluated on 10 tasks across Ego-in-Exo Per-ception and existing ADL benchmarks, achieving state-of-the-art resultson the ADL-X benchmark suite and outperforming strong baselines onour proposed benchmark. Code, models, and data will be released athttps://github.com/dominickrei/EgoExo4ADL.

ECCV 2026

ICLAgent: Integrated Circuit Footprint Geometry Labeling via LMM-empowered Multi-Agent Framework

Yida Wang, Yixin Liu, Taiting Lu, Lanqing Yang, Dian Ding, Juntao Zhou, Yifan Yang, Yi-Chao Chen, Mahanth Gowda

Integrated circuit (IC) footprint geometry labeling refers tothe process of converting pin diagrams in IC datasheets into machine-readable geometric parameters. This task is critical in printed circuitboard (PCB) design and component assembly, as accurate labeling en-sures proper IC placement and reliable connectivity. The process is chal-lenged by unstructured annotations, complex footprint arrangements,and abstract geometric diagrams, making fully automated labeling meth-ods inadequate. Traditional EDA tools require heavy manual input. Ex-isting automation methods, such as OCR or object detection, fail tocapture the implicit geometric relationships in IC diagrams, leaving thelabeling task incomplete. Recent work has shown that end-to-end largemultimodal models (LMMs) can perform IC geometry labeling. How-ever, by treating the task as a black box, it is prone to shortcut learningand lack interpretability. In this work, we introduce ICLAgent, thefirst multi-agent framework for fully automated IC footprint geometrylabeling that explicitly models the workflow of expert engineers to pro-duce more interpretable and reliable labeling outcomes. Furthermore, wepresent ICAgent-Instruct, the first dynamic planning and reasoningdataset tailored for IC footprint geometry labeling. Extensive experi-ments show that ICLAgent improves overall accuracy by 10.3% com-pared to the previous SOTA method and by 79.5% compared to man-ual annotation. Despite using only simple supervised fine-tuning on a7B model (Qwen2-VL-7B), ICLAgent surpasses general-purpose LMMssuch as GPT-5 (by 94.6%) and Gemini-3 Pro (by 15.2%).

ECCV 2026

Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation

Peixin Chen, Guoxi Zhang, Jianwei Ma, Qing Li

Embodied agents must explore partially observed environ-ments while maintaining reliable long-horizon memory. Existing graph-based navigation systems improve scalability, but they often treat un-explored regions as semantically unknown, leading to inefficient frontiersearch. Although vision-language models (VLMs) can predict frontiersemantics, erroneous predictions may be embedded into memory andpropagate through downstream inferences, causing structural error ac-cumulation that confidence attenuation alone cannot resolve. These ob-servations call for a framework that can leverage semantic predictionsfor directed exploration while systematically retracting errors once newevidence contradicts them. We propose Hypothesis Graph Refinement(HGR), a framework that represents frontier predictions as revisable hy-pothesis nodes in a dependency-aware graph memory. HGR introduces(1) semantic hypothesis module, which estimates context-conditioned se-mantic distributions over frontiers and ranks exploration targets by goalrelevance, travel cost, and uncertainty, and (2) verification-driven cas-cade correction, which compares on-site observations against predictedsemantics and, upon mismatch, retracts the refuted node together withall its downstream dependents. Unlike additive map-building, this allowsthe graph to contract by pruning erroneous subgraphs, keeping mem-ory reliable throughout long episodes. We evaluate HGR on multimodallifelong navigation (GOAT-Bench) and embodied question answering (A-EQA, EM-EQA). HGR achieves 72.41% success rate and 56.22% SPL onGOAT-Bench, and shows consistent improvements on both QA bench-marks. Diagnostic analysis reveals that cascade correction eliminates ap-proximately 20% of structurally redundant hypothesis nodes and reducesrevisits to erroneous regions by 4.5×, with specular and transparent sur-faces accounting for 67% of corrected prediction errors.

ECCV 2026

HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding

Wenhui Liao, Hongliang Li, Pengyu Xie, Xinyu Cai, Yufan Shen, Yi Xin, Qi Qin, Shenglong Ye, Tianbin Li, Ming Hu, Junjun He, Yihao Liu, Wenhai Wang, Min Dou, Bin Fu, Botian Shi, Yu Qiao, Lianwen Jin

Document parsing is a fundamental task in multimodal understanding, supporting a wide range of downstream applications such as information extraction and intelligent document analysis. Benefiting from strong semantic modeling and robust generalization, VLM-based end-to-end approaches have emerged as the mainstream paradigm in recent years. However, these models often suffer from substantial inference latency, as they must autoregressively generate long, full-page sequences when processing long-form documents. While recent hybrid methods mitigate this issue via region-level parallel decoding with VLMs, independent region decoding loses full-page context and might weaken global coherence. To address this issue, we propose Hierarchical Speculative Decoding (HSD), a two-stage local-to-global framework for document parsing. HSD first employs a lightweight pipeline drafter to predict region partitions and generate coarse drafts for each region. The first stage verifies the generated region-level drafts in parallel for efficiency, while the second stage further performs page-level verification on these refined outputs to preserve full-page coherence. Experimental results show that our HSD achieves a near-lossless 2.78× speedup with HunyuanOCR on OmniDocBench v1.5 and up to 7.04× speedup on long-document parsing tasks, demonstrating the effectiveness of our proposed method. The code is available at https://github.com/whlscut/HSD.

ECCV 2026

Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges

Hongyang He, Xinyuan Song, Yan Zhong, Daizong Liu, Yanbin Li, Yangfan He, Wenqiao Zhang

Real-world semi-supervised learning (SSL) often encounterssignificant challenges with long-tailed label distributions and noisy pseudo-labels, which hinder generalization and amplify confirmation bias. In thiswork, we introduce a novel framework, Gaussian Bridge Consistency(GBC), to address these challenges by constructing semantic interpo-lation paths between unlabeled samples and high-quality class anchors.Our method maintains a dynamic Prototype Atlas that stores a diverseand evolving set of labeled and pseudo-labeled exemplars per class. Foreach unlabeled instance, GBC forms a class-conditional Gaussian Fea-ture Bridge in the latent space, enabling the student model to traversea smooth trajectory from uncertain predictions to reliable class proto-types. A bridge consistency loss is applied along this path to enforcealignment with a geometrically interpolated target distribution. Further-more, we propose BridgeMix, a confidence-aware feature mixing strategythat interpolates both sample and anchor pairs to amplify cross-samplegeneralization. Extensive experiments on CIFAR10-LT and ImageNet-LT (USB benchmarks) validate the robustness and effectiveness of GBCunder realistic long-tailed SSL settings, consistently improving long tail-class performance without sacrificing scalability.

ECCV 2026

From Masks to Pixels and Meaning: A New Taxonomy, Benchmark and Metrics for VLM Image Tampering

Xinyi Shang, Yi Tang, Jiacheng Cui, Ahmed Elhagry, Salwa Al Khatib, Sondos Bsharat, Jiacheng Liu, Xiaohan Zhao, Jing-Hao Xue, Hao Li, Salman Khan, Zhiqiang Shen

Existing tampering benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are untouched or only trivially modified, while subtle yet consequential edits outside the mask are treated as natural. We reformulate VLM image tampering from coarse region labels to a pixel-grounded, meaning and language-aware task. First, we introduce a taxonomy spanning edit primitives (replace/remove/splice/inpaint/attribute/colorization, etc.) and their semantic class of tampered object, linking low-level changes to high-level understanding. Second, we release a new benchmark with perpixel tamper maps and paired category supervision to evaluate detection and classification within a unified protocol. Third, we propose a training framework and evaluation metrics that quantify pixel-level correctness with localization to assess confidence or prediction on true edit intensity, and further measure tamper meaning understanding via semantics-aware classification and natural language descriptions for the predicted regions. We also re-evaluate the existing strong segmentation/localization baselines on recent strong tamper detectors and reveal substantial overand underscoring using mask-only metrics, and expose failure modes on micro-edits and off-mask changes. Our framework advances the field from masks to pixels, meanings and language descriptions, establishing a rigorous standard for tamper localization, semantic classification and description. Code and data are available at https://github.com/VILA-Lab/PIXAR.

ECCV 2026

FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection

Md Redwanul Haque, Manzur Murshed, Manoranjan Paul, Tsz-Kwan Lee

Generalization remains a critical bottleneck in AI-generatedimage detection. Because many modern generators are proprietary oradversarially modified, existing detectors overfit to the low-level tex-tural patterns of accessible training data, resulting in severe failureson unseen domains. Conventional regularization techniques (e.g., L1 /L2norms, Dropout) apply indiscriminate parametric constraints and fail toprovide the domain-invariant structure necessary for cross-generator ro-bustness. To address this, we propose Feature-Augmented Implicit Reg-ularization (FAIR). FAIR introduces an orthogonal, macro-structuralprior, specifically, Scene Composition Structure (SCS), during train-ing to geometrically constrain the model’s optimization trajectory. Byaugmenting the primary feature space with domain-invariant SCS fea-tures, FAIR explicitly penalizes texture-biased shortcut learning. Cru-cially, this structural prior is entirely discarded at inference, yielding asmoothed, generalized decision boundary with zero architectural or com-putational overhead. Extensive evaluations across five massive bench-marks demonstrate that integrating FAIR into state-of-the-art detectorssignificantly improves cross-generator generalization, boosting accuracyby up to 8.04% and establishing new state-of-the-art robustness in zero-shot transfer scenarios.

ECCV 2026

Exploring Efficient Reasoning Segmentation with Small Language Models

Changsong Wen, Zelin Peng, Yu Huang, Xiaokang Yang, Wei Shen

Reasoning segmentation is a challenging vision–language taskthat performs pixel-level segmentation guided by language reasoning overimplicit textual descriptions. Existing methods typically employ largelanguage models (LLMs) to achieve such reasoning capability, yet theirsubstantial computational and memory demands limit practical deploy-ment. To overcome this, we present LReSeg, the first attempt to tacklereasoning segmentation with a small language model (SLM), achievingstrong performance with substantially reduced model size and computa-tional cost. To address the challenges of scaling reasoning segmentationto SLMs, we propose two key designs: First, unlike LLMs, SLMs havelimited capacity to provide sufficient spatial instruction cues for mask de-coding. We introduce register tokens that aggregate text-conditioned spa-tial features via the SLM’s self-attention and inject them into the visualtoken stream to enrich the mask decoder’s inputs. Second, we adopt aunified encoder architecture to eliminate the redundant visual backboneof conventional dual-encoder designs, naturally ensuring feature consis-tency between reasoning and mask decoding. LReSeg surpasses modelsof similar scale with superior efficiency, while being nearly 10× smaller(800M vs. ∼8B) and 3.3× faster than conventional 7B-scale LLM-basedmethods. Code is available at https://github.com/downdric/LReSeg.

ECCV 2026

EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation

Nan Wang, Zhiyi Xia, Yiming Li, Shi Tang, Zoe Fan, Xi Fang, Haoyi Tao, Zhang Siyuan, Guolin Ke, Yanhui Hong

Quantitative microstructural characterization is fundamen-tal to materials science, and electron micrographs (EMs) provide indis-pensable high-resolution insights. However, progress in deep learning-based analysis of EMs has been hampered by the scarcity of large-scale,expert-annotated public datasets. To address this issue, we introduceEM3M, a large-scale and multimodal dataset for instance-level under-standing of EMs. EM3M comprises 5,091 high-quality EMs, approxi-mately 3 million instance segmentation annotations, and image-leveltextual descriptions with disentangled attributes. The dataset is con-structed through a rigorous multi-stage curation and validation pipeline,with comprehensive statistical analyses to ensure reliability and repro-ducibility. Building upon these curated image-text pairs, we further pro-vide a text-to-image diffusion model that serves as a controllable dataaugmentation engine, demonstrating that synthetic augmentation con-sistently improves downstream segmentation performance. To establish asystematic benchmark, we evaluate representative instance segmentationmethods on EM3M. Our results reveal that conventional detection-basedand query-based methods struggle with the extreme instance densitiesand textural complexities inherent in EMs. We additionally provide anoptimized flow-based baseline to facilitate fair comparison and future re-search. EM3M1 , the generative engine2 , and an online demo3 are publiclyavailable to support future research in automated materials analysis.

ECCV 2026

Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement

Chujie Qin, Zilong Zhang, Zewei Chang, Chun-Le Guo, Ruixing Wang, Tao Hu, Ming-Ming Cheng, Chongyi Li

Image retouching is commonly formulated as enhancing over-all visual quality through color adjustment, but in practice, it also servesto emphasize visual focus by guiding viewers’ attention toward a specificsubject or region. Achieving such focus-oriented retouching is inherentlychallenging, as it requires well-coordinated global and local adjustmentsto manipulate perceptual saliency while maintaining visual naturalness.This intricate process typically demands substantial professional exper-tise. In this study, we propose EyeControl, a multi-modal large lan-guage model (MLLM)-driven agent with a diffusion-based retouchingexecutor that enables visual focus enhancement under weak user intent.With only a few clicks or coarse strokes, EyeControl directs visual at-tention to the intended region, effectively “dotting the eye” of the image.The core idea is to explicitly link the weak user intention with the tar-get editing region and the corresponding tonal adjustment operationsduring retouching. To achieve this, the system first interprets the in-tent and image content to infer the visual focus and generate structuredintent guidance for the retouching executor. Second, the retouching ex-ecutor is encouraged to respond more strongly to the target region, ex-plicitly aligning its attention map with a designed pseudo-intent map.We also introduce an operation-consistency constraint to improve coor-dination between global and local adjustments, achieving more naturaland coherent retouching. Additionally, we contribute ControlArt-Bench,a high-quality evaluation dataset for visual focus enhancement. Exten-sive evaluations demonstrate that EyeControl yields perceptually ap-pealing results with stronger intent alignment. Code will be released athttps://github.com/DragonisCV/EyeControl.

ECCV 2026

CURE: Contextual Debiasing and Unbiased Refinement for Training-Free Open-Vocabulary Semantic Segmentation

Jiean Wang, Sanqing Qu, Fan Lu, Huanhuan Bao, Wei Tian, Bo Jin, Jiangtong Li, Junqiao Zhao, Guang Chen

Recent advances in large-scale vision–language models (VLMs)have greatly advanced open-vocabulary semantic segmentation (OVSS),enabling segmentation beyond predefined category constraints. However,due to the image-level pre-training objectives of VLMs, existing training-free OVSS methods often suffer from global contextual artifacts, degrad-ing their ability to capture fine-grained and spatially localized semantics.In this work, we propose a novel framework, termed CURE (Contextualdebiasing and Unbiased REfinement), to address these limitations bymitigating both explicit and implicit global biases. Technically, CUREemploys a reject-and-reconstruction module to identify explicit outliertokens and reconstruct them using local neighborhood information. Aglobal contextual debiasing module is further introduced to suppressresidual implicit bias. Finally, a spatial correlation refinement moduleis designed to enhance spatial coherence by leveraging mid-level simi-larity patterns. Extensive experiments on five datasets demonstrate thatCURE consistently improves segmentation quality. When integrated intosix baseline methods, it yields average mIoU gains of 2.8% and 7.7% withViT-B/16 and ViT-L/14 backbones, respectively.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.