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

DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning

Jiajian Huang, Dongliang Zhu, Zitong Yu, Hui Ma, Jiayu Zhang, Chunmei Zhu, Xiaochun Cao

Multimodal deception detection aims to identify deceptivebehavior by analyzing audiovisual cues for forensics and security. Inthese high-stakes settings, investigators need verifiable evidence con-necting audiovisual cues to final decisions, along with reliable general-ization across domains and cultural contexts. However, existing bench-marks provide only binary labels without intermediate reasoning cues.Datasets are also small with limited scenario coverage, leading to short-cut learning. We address these issues through three contributions. First,we construct reasoning datasets by augmenting existing benchmarks withstructured cue-level descriptions and reasoning chains, enabling modelsto output auditable reports. Second, we release T4-Deception, a mul-ticultural dataset based on the unified “To Tell the Truth” televisionformat implemented across four countries. With 1695 samples, it is thelargest non-laboratory deception detection dataset. Third, we proposetwo modules for robust learning under small-data conditions. StabilizedIndividuality-Commonality Synergy (SICS) refines multimodal represen-tations by combining learnable global priors with sample-adaptive resid-uals and applying polarity-aware recalibration. Distilled Modality Con-sistency (DMC) aligns modality-specific predictions with the fused mul-timodal predictions via knowledge distillation to prevent unimodal short-cut learning. Experiments on three established benchmarks and our noveldataset demonstrate that our method achieves state-of-the-art perfor-mance in both in-domain and cross-domain scenarios, while exhibitingsuperior transferability across diverse cultural contexts. The datasets andcode are available at this link.

ECCV 2026

CogniCred: A Dataset and Benchmark for Cognitive Credential Forgery Detection

Junchi Li, Jiasheng Sun, Weizhi Chen, Ziwei Wang, Sheng Zhou, Jiajun Bu, Chenfan Qu, Bohan Yu, Jian Liu, Weiqiang Wang

Credentials, such as corporate qualifications and personalidentification, serve as common forms of evidentiary materials. The forgeryof such credentials poses significant risks to security, making its detectiona long-standing area of widespread concern. With the advancement of AI-Generated Content technologies, forgery techniques can now largely pre-serve visual characteristics, making purely vision-based detection meth-ods insufficient to meet practical demands. Instead, a growing number offorgeries necessitate cognitive reasoning for detection. While the devel-opment of Multimodal Large Language Models (MLLMs) presents newopportunities for complex credential forgery detection, the scarcity ofdatasets and benchmarks severely impedes progress in this critical do-main. To bridge this gap, we introduce CogniCred — the first large-scale,multimodal dataset built upon complex, real-world credentials with care-fully crafted cognitive-level forgeries. Along with this dataset, we proposea dedicated benchmark, namely CogniCredBench, that evaluates modelperformance across five distinct types of cognitive forgeries. We conductcomprehensive evaluations across 21 mainstream MLLMs, revealing sub-stantial performance disparities and a strong bias toward text-based rea-soning, highlighting that current models still fall short in balanced multi-modal reasoning for cognitive forgery detection. Our datasets are publiclyavailable at https://huggingface.co/datasets/sjs0606/CogniCred.

ECCV 2026

ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation

Kerui Chen, Jianrong Zhang, Ming Li, Zhonglong Zheng, Hehe Fan

Existing stylized motion generation models have shown theirremarkable ability to understand specific style information from the stylemotion, and insert it into the content motion. However, capturing intra-style diversity, where a single style should correspond to diverse motionvariations, remains a significant challenge. In this paper, we propose aclustering-based framework, ClusterStyle, to address this limitation.Instead of learning an unstructured embedding from each style motion,we leverage a set of prototypes to effectively model diverse style pat-terns across motions belonging to the same style category. We considertwo types of style diversity: global-level diversity among style motionsof the same category, and local-level diversity within the temporal dy-namics of motion sequences. These components jointly shape two struc-tured style embedding spaces, i.e., global and local, optimized via align-ment with non-learnable prototype anchors. Furthermore, we augmentthe pretrained text-to-motion generation model with the Stylistic Mod-ulation Adapter (SMA) to integrate the style features. Extensive ex-periments demonstrate that our approach outperforms existing state-of-the-art models in stylized motion generation and motion style transfer.Project page: https://1233chen.github.io/ClusterStyle/.

ECCV 2026

Bayesian Self-Attention with Local Pixel Correlations for Lightweight Denoising Transformers

Runyang He, Zuowei Shen, Hui Ji

Transformer architectures have achieved strong performancein image denoising, but their computational and memory costs remainhigh. We revisit self-attention (SA) from a Bayesian perspective and showthat standard SA mainly exploits first-order inter-patch statistics, resem-bling a learnable non-local averaging scheme. However, this formulationneglects second-order intra-patch statistics, which are important for cap-turing local pixel dependencies. To address this, we introduce a BayesianSA formulation that jointly models first-order inter-patch and second-order intra-patch statistics. This leads to a lightweight denoising Trans-former, termed NLformer, featuring a dual-branch attention design andan efficient feed-forward module. Experiments on several benchmarksshow that NLformer outperforms existing lightweight denoising networksand substantially narrows the gap to full-size Transformer-based denois-ers while maintaining low model complexity.

ECCV 2026

AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning

Kyuan Oh, Bumsoo Kim

Large vision-language models incur substantial inference costsbecause high-resolution inputs introduce thousands of visual tokens, manyof which are redundant for a given query. Existing pruning methods of-ten combine query relevance and token diversity, yet these objectivescan conflict under aggressive compression: relevance-driven selection mayoverconcentrate the budget on correlated local evidence, while diversity-driven selection may suppress indispensable tokens or retain distinctbut uninformative regions. We introduce AnchorPrune, a training-freeframework that first constructs a protected relevance anchor and thenexpands it with complementary visual context. AnchorPrune adaptivelydetermines the anchor size from the novelty profile of relevance-rankedtokens, preserving a compact set of query-critical evidence, and allocatesthe remaining budget through importance-weighted novelty to recover in-formative, non-redundant context relative to the anchor. This ordered de-sign prevents contextual expansion from displacing indispensable querycues while improving overall visual coverage. AnchorPrune is lightweight,architecture-aware, and requires neither retraining nor model modifica-tion. Across image and video vision-language models and benchmarks, itconsistently improves the accuracy–efficiency trade-off over training-freebaselines, particularly under severe compression. On LLaVA-NeXT-7B,AnchorPrune preserves 97.6% of full-token performance using only 160of 2,880 visual tokens. These results establish relevance-anchored contex-tual expansion as an effective principle for efficient multimodal inference.Code is available at https://github.com/MULTI-cau/AnchorPrune.

ECCV 2026

AnaPFL: When Closed-Form Solutions Meet Generalizationand Personalization in Personalized Federated Learning

Kejia Fan, Jianheng Tang, Zhirui Yang, Feijiang Han, Yajiang Huang, Run He, Jiaxu Li, Songning Lai, Anfeng Liu, Houbing Herbert Song, Yunhuai Liu, Huiping Zhuang

Personalized Federated Learning (PFL) has emerged as aprevalent paradigm to deliver personalized models to individual clientsthrough collaborative training. Existing PFL methods often suffer fromthe issue of Non-IID data, due to their reliance on gradient-based up-dates. Recently, Analytic Learning (AL) has exhibited great potential toaddress this issue via analytical (i.e., closed-form) solutions in a gradient-free manner. However, there remains a significant gap in introducingAL into PFL, owing to the encountered generalization-personalizationdilemma. In this paper, to bridge this gap and address the associatedchallenges, we propose an Analytic Personalized Federated Learningapproach, named AnaPFL, for addressing the Non-IID issue in PFL byintroducing and advancing AL. In AnaPFL, we develop dual-stream an-alytic models with closed-form solutions, including (1) a shared primarystream for global generalization across all clients, and (2) a dedicated re-finement stream for local personalization of each client. Experimentally,we give comprehensive results to show AnaPFL’s superior performancewith over 99% efficiency advantages against gradient-based methods.

ECCV 2026

Amplify, Aggregate, and Adjust: VideoMAE-based Holistic-Subtle Aggregation for Micro-Action Recognition

Yan Zhang, Nan Pu, Wenjing Li, Zhun Zhong, Meng Wang

Micro-Action Recognition (MAR) aims to identify transient and subtle bodily movements that occur during interpersonal communication. Existing MAR methods attempt to emphasize low-amplitude motion by injecting skeletal priors and have achieved certain progress. However, they (1) rely on additional modalities and costly pose annotations, and (2) employ coarse joint graphs that fail to capture sub-joint micro-movements and fine-grained appearance cues (e.g., finger tremors). In contrast, raw RGB videos preserve such subtle cues, and pretrained VideoMAE provides strong spatiotemporal priors without requiring additional supervision. Motivated by this, we first establish a strong MAR baseline by task-adaptively fine-tuning VideoMAE. To further enhance its capacity to perceive subtle motion cues, we propose A3-MAE, a VideoMAE-based holistic-subtle collaborative framework that integrates Amplification, Aggregation, and Adjustment in a unified design. Specifically, 1) we design a Temporal Gradient Local Amplification (TGLA) module to amplify subtle-motion regions directly from RGB inputs, forming a subtle-motion branch that complements the holistic-motion counterpart; 2) we develop a Holistic-Subtle Motion Aggregation (HSMA) module with dual cross-attention, enabling reciprocal conditioning between holistic and subtle branches while maintaining their complementarity; and 3) we introduce a Confidence-Aware Dynamic Adjustment (CADA) module to adaptively calibrate aggregation mismatch between the two branches in an instance-aware manner. Together, these components establish a unified amplify-aggregate-adjust paradigm for comprehensive micro-action understanding. Extensive experiments demonstrate that A3-MAE achieves new state-of-the-art performance on both MA-52 and iMiGUE benchmarks. Code is available at https://github.com/zy-hfut/A3MAE.

ECCV 2026

AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution

Jiangang Wang, Shangquan Sun, Aiping Zhang, Yuning Cui, Wenqi Ren

Despite their remarkable performance in real-world imagesuper-resolution, diffusion models remain challenged by the perception–distortion trade-off between structural fidelity and perceptual realism.Existing methods typically rely on a globally predefined restoration tra-jectory, applying spatially uniform noise and a fixed temporal schedule.Such rigid trajectories often lead to a dilemma: reliable structures may bedistorted, while severely degraded textures may become over-smoothed.To address this, we propose AdaBridge-SR, built upon a novel spatio-temporal adaptive bridge matching (ST-ABM) formulation that castsrestoration as a controlled bridge between degraded and clean imagedistributions. ST-ABM decouples the bridge stochasticity into spatialand temporal controls, adaptively determining where to inject stochas-ticity and when to allocate generative capacity conditioned on the inputdegradation. We instantiate these controls with a lightweight AdaptiveBridge Controller that predicts a spatial stochasticity map and a timereparameterization. Consequently, AdaBridge-SR unifies deterministicrestoration and stochastic exploration within a single model. Extensiveexperiments demonstrate that it achieves a superior perception–distortionbalance, supporting efficient deterministic one-step inference and high-quality stochastic few-step bridge refinement. Our code and models areavailable at https://github.com/W-JG/AdaBridge-SR.

ECCV 2026

A Simple Baseline with Placement Prior for Point-Supervised Oriented Object Detection

Runxiang Liu, Kaikai Xie, Qianxi Cao, Yuming Fang, Jiebin Yan, Junjie Chen

Oriented object detection for aerial images has attractedgrowing attention due to the increasing demand in extensive applica-tions. However, the oriented box annotation is relatively expensive, andthus point-supervised oriented object detection has emerged as a practi-cal paradigm. Owing to the lack of size and angle annotations, existingmethods leverage various complementary information, but usually sufferfrom extra training stages or multiplied computational overhead. In thispaper, we propose three simple yet effective loss terms, and set a simplebaseline with the placement prior. In particular, the placement prior in-dicates that objects in aerial images are placed in a context, rather thanexhibiting arbitrary distribution. Therefore, we propose the angle priorloss, considering that the angles of objects are usually aligned in a neigh-borhood. Furthermore, we propose the size prior loss, considering thatthe sizes of objects are usually proportional for each class in an image.Besides, we propose to derive oriented boxes from the Voronoi Water-shed regions without training, which can jointly regularize the estimatedangles and sizes. By employing only loss terms, our baseline is not onlysimple and easy to extend but also readily transferable to other methods.We conduct extensive experiments on representative UAV datasets andremote sensing datasets, which indicates the effectiveness of our method.

ECCV 2026

Weight Feedback Computes the Exact Jacobian Transpose in Modern Deep Networks

Junlong Shen, Xingyu Li

Predictive Coding (PC) offers a biologically motivated al-ternative to backpropagation via local weight updates, yet routing er-ror between layers still relies on an autograd Jacobian-transpose (J⊤ )product—the last non-local operation in PC. We show that this depen-dency is largely avoidable. For any layer f (x)=Act(Norm(L(x))) withfrozen normalization statistics, the exact J⊤ factors into three locallyavailable terms, J⊤ v = L⊤ (s ⊙ σ ′ (pre-act) ⊙ v), where σ ′ is the activationderivative and s=γ/σrun is the normalization gain. Prior weight-feedbackmethods omitted both corrections; restoring them closes the transportgap for this layer class. Note that locality here holds up to three as-sumptions, which we state upfront—weight symmetry (L⊤ mirrors theforward operator, as assumed by all PC), a soft spectral-norm controlthat is not synapse-local, and a nearest-neighbour approximation forMaxPool. Substituting the identity into PC yields WF-Act-PC, whichremoves the autograd backward pass from error transport. On CIFAR-10/100 (50 epochs, 5 seeds), WF-Act-PC is the only PC method whoseaccuracy improves with depth, surpassing iPC—the strongest classicalPC baseline—by 2.7–22.3 pp on CIFAR-10. With both methods tunedper architecture, it matches or exceeds a comparably-tuned backpropa-gation baseline on the deeper CIFAR-10 architectures (VGG-9: 93.57%vs. 92.43%; ResNet-18: 92.76% vs. 91.54%) and on the harder Tiny-ImageNet benchmark, while trailing tuned BP on the deeper CIFAR-100VGG cells. Our WF-Act-PC implementation is publicly available athttps://github.com/jlshen025/pcax.

ECCV 2026

WALL-EVE: World Alignment with Rule Learning in Visual Environments

SiYu Zhou, Tianyi Zhou, Yijun Yang, Deheng Ye, Chengqi Zhang, Jing Jiang, Guodong Long

Constructing world models for AI agents in visual environ-ments has long been a significant challenge, chiefly due to the di!cultyof achieving precise alignment of the dynamics between the world modeland the environment, given noisy pixel-level observations. Existing worldmodels solely rely on video or image generation, which are exceedinglycomplex and expensive to train, yet still su"er from hallucinations andviolations of basic rules due to misalignment. In this paper, we show thata few rules su!ce to convert a pretrained large language model (LLM)to an accurate world model for a specific visual environment. We pro-pose a training-free approach to e!ciently learn these complementaryrules from multimodal agent trajectories collected in the visual environ-ment. In particular, we convert the multimodal input into structuredtext and extract symbolic rules using an LLM by comparing agents’ truetrajectories with world model predictions if they have conflicts. We usethis neurosymbolic approach to induce, update, and prune rules dur-ing exploration, resulting in a precise world model. It allows us to builda novel model-predictive control (MPC) agent, “WALL-EVE”, with-out training any policy. Before taking each action, WALL-EVE utilizesan LLM as a look-ahead optimizer to determine the next k-step actionsthrough interactions with our world model. On challenging tasks in ALF-World and Minecraft, WALL-EVE achieves higher success rates thanexisting methods, while reducing inference times and the number of to-kens required for reasoning. In ALFWorld, WALL-EVE surpasses thestate-of-the-art method RAFA with only 17% of RAFA’s token usage.In Minecraft, WALL-EVE outperforms baselines by 8-30% in successrate but costs 8–20 fewer replanning rounds and only 60–85% tokens.Code is available here.

ECCV 2026

VVSim: A Large-Scale Aerial-Ground Dataset and Benchmark for Cooperative Perception

Zengle Zhu, Zhen Li, Tianyi Huai, Tianshun Li, Zihang Xu, Liuqing Yang, Rongqing Zhang, Xinhu Zheng

The increasing diversity and density of traffic participantshave made modern driving environments highly complex, posing greatchallenges to reliable perception in autonomous driving. Single-vehicleperception is fundamentally limited by sensor range and occlusions, whilevehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) cooperationonly partially mitigate these issues due to their fixed or ground-levelviewpoints. In contrast, aerial platforms offer global and flexible sens-ing perspectives that can dynamically adjust their positions to providebroader spatial coverage and reduce blind zones. These advantages mo-tivate the exploration of aerial-ground cooperative perception (AGCP).However, progress in this area is hindered by the lack of public datasetsand standardized benchmarks. To bridge this gap, we introduce VVSim,a large-scale dataset for AGCP that provides synchronized multimodaldata and state information from both vehicles and unmanned aerial ve-hicles (UAVs). VVSim consists of about 61k fully annotated frames span-ning diverse interaction scenarios (e.g., cut-in, lane change), 5 weatherconditions (sunny, foggy, rainy, cloudy, snowy), and 11 scenes (e.g., city,town, university, highway, mountain). In total, it comprises 255k Li-DAR sweeps and 3.5M images (RGB, semantic segmentation, and depth)collected from vehicles and UAVs, along with detailed annotations for2D/3D bounding boxes, object trajectories, and agent states. To supportunified evaluation, we further propose VVFormer, a novel architecturethat integrates multi-agent and multimodal features from UAVs and ve-hicles. Extensive experiments on VVSim demonstrate that VVFormerachieves superior performance, significantly outperforming strong V2Vand V2I cooperative baselines on 3D perception tasks. The code is avail-able at https://github.com/LOTEAT/vvdetection3d.

ECCV 2026

VOCA: Visual Odometry with Codec Awareness

Nouri Alexander Hilscher, Mateo de Mayo, Dominik Muhle, Christoph Otten genannt Hermes, Daniel Cremers

Camera pose estimation from image streams is a critical com-ponent of spatial world models that integrate perception into planningand decision-making. Nearly all Visual Odometry (VO) and SimultaneousLocalization and Mapping (SLAM) systems have focused on datasetscontaining raw, uncompressed videos. Many working systems insteaduse ubiquitous hardware units to efficiently compress and decode videostreams, saving orders of magnitude in storage and bandwidth. However,this lossy compression introduces visual artifacts that hinder the per-formance of traditional tracking systems. We present VOCA, a causalstereo visual-odometry method that exploits codec information to im-prove tracking performance. We achieve state-of-the-art performance oncausal VO for relative trajectory error, efficiency, and absolute trajec-tory error on compressed streams. This work highlights the potential ofleveraging widely available video codec information for vision tasks.

ECCV 2026

VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection

Songsong Duan, Xi Yang, Nannan Wang

Camouflaged Object Detection (COD) aims to identify andsegment camouflaged objects in complex environments, which are oftenconcealed because their color and texture are similar to the background.Several existing COD methods introduce depth maps to boost detec-tion performance via learning complementary RGB-D features, ignor-ing modality-specific characteristics of concealed objects in the depthdomain. To address this issue, we propose a depth collaborative net-work, called VCP-DCN, to mine distinguishable multi-modality featuresbeyond visual concealed prototype in depth domain. Specifically, VCP-DCN progressively performs multi-modality alignment, interaction, andfusion for the COD task. In the alignment stage, we propose a SeparablePrototype Embedding (SPE) module to learn modality-consistency andmodality-specific RGB/depth prototype tokens through prototype con-trastive learning. Furthermore, we develop a Multi-modality Dual Atten-tion (MDA) module to enhance the cross-modal feature representationthrough local response maps between modality-consistency RGB/depthprototype tokens and visual tokens on the interaction stage. Finally,we design a Depth Adaptive Injection (DAI) module to adaptively mea-sure contribution of RGB/depth features with a decision-making mecha-nism, which calculates similarity distance between RGB/depth modality-specific prototype tokens and modality-consistency ones on the fusionstage. Extensive experiments demonstrate the effectiveness of our VCP-DCN on three authoritative datasets. The code is available at https://github.com/duan-song/VCPDCN.

ECCV 2026

Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild

Ting Lei, Jialin Liu, Zhu Xu, Yuxin Peng, Yang Liu

Human-object interaction detection (HOID) has traditionally been formulated as a supervised detection problem over predefined interaction categories. While such paradigms achieve strong performance on closed-set benchmarks, they fundamentally entangle interaction understanding with dataset-specific supervision, limiting their ability to generalize to open-world and compositional scenarios. Recent HOI detectors attempt to leverage MLLMs through prompting strategies to transfer interaction-specific knowledge. However, such prompt-based approaches primarily focus on extracting discriminative representations from pretrained models, while underexploring their inherent multimodal reasoning capabilities. As a result, they struggle to provide informative contextual reasoning for ambiguous and open-world interaction scenarios. In this work, we present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild. Instead of learning interaction classifiers, AgentHOI modularly orchestrates complementary vision foundation modules to perform open-ended semantic reasoning and spatial grounding in a coordinated manner. To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms: (1) Context-aware Multi-round Reasoning, which progressively refines interaction hypotheses to ensure exhaustive and compositional HOI discovery, and (2) Multifaceted Interaction Localization, which enhances grounding precision by generating instance-specific descriptions that integrate semantic, spatial, and appearance cues. Extensive experiments demonstrate that AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings, despite requiring no HOID data for training. Code is available at https://github.com/ oceanflowlab/AgentHOI.

ECCV 2026

Tri-Efficient Transfer Learning for Point Cloud Videos

Yiding Sun, Dongxu Zhang, Jihua Zhu, Haozhe Cheng, Zhengqiao Li, Pengcheng Li, Chaowei Fang, Yonghao Dong, Lin Chen

While point cloud foundation models have significantly ad-vanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two critical limitations: pro-hibitive annotation costs for large-scale point cloud datasets and severememory bottlenecks. In this paper, we aim to mine richer supervisionsignals from existing data rather than blindly scaling datasets. A furtherkey principle is that the memory footprint of fine-tuning must be dras-tically reduced compared to full fine-tuning, which remains elusive forcurrent PEFT techniques. Driven by these challenges, we identify threecore desiderata: data-, parameter-, and memory efficiency, and presentPoinTriE, a unified framework that excels along all three dimensions.For pre-training, pseudo-motion trajectories are synthesized via rigidtransformations, paired with text corpora and 2D projections derivedfrom raw point clouds. We then propose a Geometric-Motion DualityNetwork optimized via multimodal contrastive learning, rigid rotationprediction, and motion distribution divergence to produce dense self-supervision. During fine-tuning, we freeze the pretrained backbone andonly update a lightweight Spatio-temporal Side Network built with LoRAunits. Equipped with a gradient flow masking strategy, PoinTriE simul-taneously reduces memory consumption and parameter overhead. Exten-sive experiments confirm that PoinTriE establishes new state-of-the-artresults on action recognition and semantic segmentation tasks.

ECCV 2026

Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models

Wanpeng Zhang, Ye Wang, Hao Luo, Haoqi Yuan, Yicheng Feng, Chaoyi Xu, Sipeng Zheng, Qin Jin, Zongqing Lu

Vision-language-action (VLA) models that generate contin-uous action chunks via flow matching lack an internal signal for judgingwhether a given prediction is reliable. Distribution shift and long-horizonrollouts can push backbone representations away from the region the ac-tion head decodes reliably, yet the policy has no mechanism to detector react to this drift. We observe that the cost of transporting observa-tion features to the action representation in a shared feature space risesprecisely when such drift occurs, providing a per-step reliability esti-mate without extra supervision. Building on this observation, we proposeDiG (Discrepancy Gate), a lightweight plug-in module for flow-matchingVLA policies. DiG computes a sliced Wasserstein transport cost betweenbackbone features and the action expert’s own input projection, maps itthrough an exponential gate, and uses the gate to modulate both a resid-ual feature refinement and the training loss. At inference time, the gateenables DiG-Refine, an iterative refinement process that corrects actionchunks before execution. Experiments on both simulation and real-worldscenarios show that DiG consistently improves success rates, with thelargest gains under distribution shift and on long-horizon tasks.

ECCV 2026

Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives

Yuhao Shen, Jiahe Qian, Zhangtianyi Chen, Juexiao Zhou

Multimodal large language models (LLMs) are increasinglyused to generate dermatology diagnostic narratives directly from images.However, reliable evaluation remains the primary bottleneck for respon-sible clinical deployment. We introduce a novel evaluation frameworkthat combines DermBench, a meticulously curated benchmark, withDermEval, a robust automatic evaluator, to enable clinically meaning-ful, reproducible, and scalable assessment. We build DermBench, whichpairs 4000 real-world dermatology images with expert-certified diagnos-tic narratives and uses an LLM-based judge to score candidate narrativesacross clinically grounded dimensions, enabling consistent and compre-hensive evaluation of multimodal models. For individual case assessment,we train DermEval, a reference-free multimodal evaluator. Given an im-age and a generated narrative, DermEval produces a structured critiquealong with an overall score and per-dimension ratings. This capabil-ity enables fine-grained, per-case analysis, which is critical for identi-fying model limitations and biases. Experiments on a diverse dataset of4500 cases demonstrate that DermBench and DermEval achieve closealignment with expert ratings, with mean deviations of 0.251 and 0.117(out of 5) respectively, providing reliable measurement of diagnostic abil-ity and trustworthiness across different multimodal LLMs. The bench-mark resources are publicly available at https://github.com/yuhos16/DermBench.

ECCV 2026

Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors

Songlin Yang, Tianyi Wei, Yushi Lan, Zeqi Xiao, Anyi Rao, Xingang Pan

Semantic matching aims to establish pixel-level correspon-dences between instances of the same category, and previous approachesbased on 2D foundation models have achieved promising results on thistask. However, they fail to achieve geometry-grounded dense semanticmatching, which encompasses geometric awareness, manifold preserva-tion, and cross-image invisibility reasoning. This new matching task si-multaneously needs geometry-aware descriptors and holistic dense match-ing mechanisms, but existing approaches rarely provide both. To bridgethis gap, we leverage VGGT, a 3D geometric foundation model that in-herently provides strong geometry-grounded priors to support both capa-bilities in a unified framework. However, directly transferring faces twochallenges: task heterogeneity, where VGGT originally matches cross-view images of the same instance, not cross-instance variations in shapeor appearance; and scarce dense matching annotations for task adapta-tion. To address these challenges, we propose an approach that (i) retainsVGGT’s intrinsic capabilities by reusing early feature stages, fine-tuninglater ones, and adding a semantic head for bidirectional correspondences;and (ii) adapts VGGT for semantic matching under data scarcity throughcycle-consistent training strategy, synthetic data augmentation, and pro-gressive training recipe. Extensive experiments demonstrate that our ap-proach achieves superior geometric awareness, manifold preservation, andmatching reliability, outperforming previous baselines.

ECCV 2026

TOPA: Mitigating Concept Dominance in Diffusion Personalization via Target-Oriented Perturbation Augmentation

Jiayou Lu, Mingzhi Lyu*, Junfeng Huang, Wai-Kin Adams Kong*

Concept personalization injects a user-specified concept intoa pretrained diffusion model from only a few reference images, enablingcustomized content creation. However, existing personalization methodsfrequently suffer from concept-dominant failures—while the personal-ized concept is well preserved, other prompt-specified contexts (e.g.,background, attributes, and interactions) are not properly generated,thereby limiting controllability. To address this problem, in this paper, wepropose Target-Oriented Perturbation-based Augmentation (TOPA), areference images-only augmentation framework. TOPA optimizes addi-tive perturbations on reference images to provide token–region atten-tion guidance and further reduces background entanglement via subject-isolation compositing. Unlike prior solutions that modify training ob-jectives or architectures, TOPA requires no changes to personalizationpipelines, and its augmented datasets can be directly applied to existingmethods. Extensive experiments across multiple personalization methodsdemonstrate consistent improvement on context adherence while preserv-ing concept fidelity.

Keep browsing

More papers from top AI conferences

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