ECCV 2026 Papers

Current CT report generation frameworks predominantlyrely on global feature representations, often failing to capture region-specific details and potentially missing certain abnormalities. To over-come this limitation, we propose MedRegion-CT, a region-focused mul-timodal large language model framework featuring three key innova-tions. First, we revisit the SlowFast strategy to jointly model globaland fine-grained information and adapt it to the medical domain via aRegion-based SlowFast Tokenizer that extracts tokens guided by clin-ically meaningful regions. Second, generated pseudo-masks guide themodel to attend to diagnostically important anatomical regions, facilitat-ing a systematic understanding of the overall scan context. Third, quanti-tative lesion information, including size, diameter, and spatial location,is encoded as structured textual prompts, enabling context-aware andclinically informed report generation. To enable rigorous evaluation, wevalidate our framework on multi-institutional structured report genera-tion benchmarks. Experimental results demonstrate that MedRegion-CTachieves state-of-the-art performance, outperforming existing approachesin both linguistic quality and clinical accuracy. All code is publicly avail-able at: https://github.com/babbu3682/MedRegion-CT.

Graphical user interface (GUI) grounding is a key capa-bility for computer-use agents, mapping natural-language instructionsto actionable regions on the screen. Existing Multimodal Large Lan-guage Model (MLLM) approaches typically formulate GUI groundingas a text-based coordinate generation task. However, directly gener-ating precise coordinates from visual inputs is challenging and oftendata-intensive. A more intuitive strategy is to first identify instruction-relevant visual patches and then determine the exact click location withinthem. Motivated by recent observations that general MLLMs exhibitnative grounding ability embedded in their attention maps, we pro-pose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the in-trinsic multimodal attention of MLLMs with patch-wise grounding sig-nals. These signals are calculated adaptively for diverse user instructionsby multi-head aggregation on simplified query-visual attention matri-ces. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 509k sam-ples (∼101k screenshots), demonstrating exceptional data efficiency andverifying that light training can trigger the native grounding capabil-ity of MLLMs. It achieves state-of-the-art performance among 3B mod-els, attaining an average accuracy of 61.5% on ScreenSpot-Pro, 92.1%on ScreenSpot-v2, 68.1% on OSWorld-G, 79.1% on MMBench-GUI-L2and 60.0% on UI-Vision. Project page: https://github.com/sjz5202/GUI-AIMA.

Snapshot hyperspectral imaging avoids sequential scanning,but systems that jointly achieve stable reconstruction, low cost, andcompact optics remain limited. We present a snapshot hyperspectralimaging system based on angular-to-spectral diversity conversion. A ta-pered kaleidoscope creates replicated views with distinct incidence di-rections, and a directly attached birefringent filter converts them intoview-channel-dependent spectral transmittances, yielding complemen-tary measurements that better condition the inverse problem for morestable single-shot spectral reconstruction. The system preserves a sim-ple pixel-wise linear model for fast non-learning-based reconstruction anduses only off-the-shelf components without relay optics or cascaded mod-ules. We select the birefringent filter configuration using a condition-number-based criterion and validate the system on both synthetic andreal data.

Automated fine-grained perception of calligraphy styles—a task vital to cultural heritage preservation—remains a critical challenge for Large Vision-Language Models (LVLMs), largely constrained by existing datasets that suffer from modal mixture and flattened labels. To bridge this gap, we introduce HCSU, the first comprehensive dataset tailored for fine-grained Historical Calligraphy Style Understanding. HCSU comprises 39,307 meticulously curated character images from 49 historically prominent calligraphers across 10 dynasties, systematically decoupling authentic ink manuscripts (Tie) from stone rubbings (Bei) to resolve the long-standing modal mixture problem. Moving beyond conventional flattened labels, HCSU provides hierarchical expert-written aesthetic descriptions, enabling two rigorous evaluation protocols: finegrained style discrimination and interpretable aesthetic reasoning. Extensive evaluations reveal a persistent gap between calligraphy-related knowledge and visually grounded style perception: state-of-the-art LVLMs show non-trivial performance but remain sensitive to script-level, textual, and source-specific cues, and often struggle to ground aesthetic judgments in fine-grained brushwork evidence. Ultimately, the HCSU benchmark exposes fundamental limitations in current multimodal architectures, aiming to inspire the evolution of expert-level visual reasoning for cultural heritage preservation. The dataset is available at https://huggingface.co/datasets/Tongji209/HCSU.

Latent diffusion models (LDMs) have emerged as a lead-ing paradigm for image generation by performing denoising in a com-pressed latent space, which provides high fidelity and efficiency but alsointensifies forensic and security concerns. While most existing detectionapproaches rely on supervised learning, training-free detectors are ap-pealing for their simplicity and ease of deployment. However, their per-formance remains limited and degrades markedly on novel generators.Our analysis reveals a more pronounced context dependence in LDM-generated images compared to real ones. Motivated by this, we intro-duce GLARE, a novel training-free method designed to exploit this de-pendence as a detection signal. Specifically, GLARE measures the rela-tive difference between full-image and patch-wise reconstruction errorswithin a shared autoencoder. Dividing the image into patches implicitlyremoves global context, thereby inducing a characteristic shift in recon-struction error that serves as a discriminative feature. Furthermore, alightweight semantic complexity calibration is incorporated to compen-sate for content-induced variation. Extensive experiments across a widerange of generators demonstrate the effectiveness and remarkable gener-alization capability of GLARE. Our method outperforms state-of-the-artsupervised and training-free baselines significantly and shows strong ro-bustness against common post-processing operations.

A common way to improve vision-language model outputsis Best-of-N (BoN) selection: generate N candidate answers, score eachone, return the best. When the candidate pool and compute budget areheld fixed, the selected answer should be reproducible. We show it often isnot. Slightly adjusting the softmax temperature, toggling a probability-truncation option, or enabling dropout noise during the scoring passis enough to change the winning answer on 41–47% of test items —even though the candidate pool is identical. This failure is specific tolikelihood-based selection, where candidates are ranked by policy likeli-hoods or policy/reference likelihood ratios; a deterministic reward-modelor rule-based (e.g. RLVR) reranker assigns identical scores to identicaltext and is stable on a fixed pool by construction.Standard scoring conflates answer quality with two confounding factors:when token-level scores are summed, low-value suffixes can change thetotal without improving answer quality, and score magnitudes shift when-ever the model is updated. We propose DSPA, which separates two con-cerns into a test-time selector and a training-time filter. At test time,we score each candidate by comparing it token-by-token against a fixedreference model and averaging the result, which removes the additivelength accumulation of summed scores and keeps all scores on a fixedreference scale; this is the component responsible for selection stability.At training time, we filter preference pairs to prevent shortcuts based onanswer length, verbatim prompt copying, or hallucinated objects; thiscomponent improves the factual quality of the candidate pool, not thestability of selection. We evaluate stability by replaying the scoring stepon the same frozen pool under controlled perturbations (a protocol wecall SRP), where the anchored selector reduces the answer-flip rate from44.3% to 24.9%. Manual inspection shows roughly 70% of remainingflips are near-ties that differ only in phrasing. On identical pools, the an-chored selector also reduces object hallucination (POPE) from 9.6% to6.2%; the stability gain holds at 13B scale, while the utility gain transfersto Qwen2.5-VL-7B-Instruct.

Physical adversarial camouflage poses a significant threatto object detectors in safety-critical applications. However, synthesiz-ing robust 3D textures remains non-trivial due to the structural mis-match between static texture parameters and dynamic physical obser-vations. In this paper, we identify two fundamental optimization hur-dles: spatially inconsistent gradients arising from sparse rendering vis-ibility; and cross-view gradient misalignment, where contradictory sig-nals from diverse viewpoints cause destructive interference. To overcomethese, we propose a unified framework that reconciles spatial continu-ity with optimization stability. First, the Deformable Texture Field pa-rameterizes textures as continuous fields via learnable flow grids, en-forcing intrinsic smoothness while enabling adaptive geometric defor-mation to enhance the texture’s representational flexibility. Second, aGradient-Aligned Meta-Optimization strategy leverages multi-step ex-ploration trajectories to implicitly maximize gradient alignment acrossconflicting viewpoints. Extensive digital and physical experiments demon-strate that our method achieves state-of-the-art robustness and transfer-ability against advanced detectors under diverse viewing conditions.

World models have become central to autonomous driving,where accurate scene understanding and future prediction are crucialfor safe control. Recent work has explored using vision–language models(VLMs) for planning, yet existing approaches typically treat perception,prediction, and planning as separate modules. We propose UniDrive-WM, a unified VLM-based world model that jointly performs driving-scene understanding, trajectory planning, and trajectory-conditioned fu-ture image generation within a single architecture. UniDrive-WM’s tra-jectory planner predicts a future trajectory, which conditions a VLM-based image generator to produce plausible future frames. These predic-tions provide additional supervisory signals that enhance scene under-standing and iteratively refine trajectory generation. We further comparediscrete and continuous output representations for future image predic-tion, analyzing their influence on downstream driving performance. Ex-periments on the challenging Bench2Drive benchmark show that UniDrive-WM produces high-fidelity future images and improves planning perfor-mance by 7.3% in L2 trajectory error and 10.4% in collision rate overthe previous best method. These results demonstrate the advantagesof tightly integrating VLM-driven reasoning, planning, and generativeworld modeling for autonomous driving. The project page is available athttps://unidrive-wm.github.io/UniDrive-WM.

While Omni-modal Large Language Models have made strides in joint sensory processing, they fundamentally struggle with a cornerstone of human interaction: deciphering complex, multi-person conversational dynamics to accurately answer “Who said what and when.” Current models suffer from an “illusion of competence”—they exploit visual biases in conventional benchmarks to bypass genuine cross-modal alignment, while relying on sparse, low-frame-rate visual sampling that destroys crucial high-frequency dynamics like lip movements. To address this limitation, we introduce Visual-Registered Speaker Diarization and Recognition (VR-SDR) and the HumanOmni-Speaker Benchmark. By strictly eliminating visual shortcuts, this rigorous paradigm demands true end-to-end spatio-temporal identity binding using only natural language queries. To overcome the underlying architectural perception gap, we propose HumanOmni-Speaker, powered by a Visual Delta Encoder. By sampling raw video at 25 fps and explicitly compressing inter-frame motion residuals into just 6 tokens per frame, it captures fine-grained visemes and speaker trajectories without triggering a catastrophic token explosion. Ultimately, HumanOmni-Speaker demonstrates strong multimodal synergy, natively enabling end-to-end lip-reading and high-precision spatial localization without intrusive cropping, and achieving superior performance across a wide spectrum of speaker-centric tasks.

Segmenting 3D assets into their constituent parts is crucialfor enhancing 3D understanding, facilitating model reuse, and supportingvarious applications such as part generation. However, current methodsface limitations such as poor robustness when dealing with complex ob-jects and cannot fully automate the process. In this paper, we propose anative 3D point-promptable part segmentation model termed P3 -SAM,designed to fully automate the segmentation of any 3D objects into com-ponents. Inspired by SAM, P3 -SAM consists of a feature extractor, mul-tiple segmentation heads, and an IoU predictor, enabling interactive seg-mentation for users. We also propose an algorithm to automatically selectand merge masks predicted by our model for part instance segmentation.Our model is trained on a newly built dataset containing nearly 3.7 mil-lion models with reasonable segmentation labels. Comparisons show thatour method achieves precise segmentation results and strong robustnesson any complex objects, attaining state-of-the-art performance. Our codewill be released soon.

Reasoning agents increasingly rely on external tools such asweb search to answer complex queries. Reinforcement learning (RL) fine-tuning algorithms such as GRPO have improved long-form reasoningin text-only language models, particularly for coding and mathematics.Reliable tool use in multimodal agents, however, remains challengingbecause models must interpret text and images while integrating noisyretrieved evidence, often under sparse outcome-level supervision withoutexplicit verification signals. We present Self-Verification via Reinforce-ment Learning (SVRL), an RL-only finetuning framework that trainsmultimodal agents to verify and filter retrieved evidence within theirown reasoning traces, reducing reliance on external verifiers at infer-ence time. SVRL also introduces a search-aware penalty that discour-ages unnecessary tool calls and a query-diversity reward that encouragesdiverse, well-formed search queries, providing fine-grained feedback onwhen and what to search. Finetuning Qwen-2.5-VL-7B with SVRL ononly 5,000 visual question answering examples yields consistent gainsin multi-hop VQA generalization and tool efficiency across benchmarks.Overall, SVRL narrows the gap between compact agents and much largerproprietary models while requiring substantially lower training and in-ference cost.

Embodied manipulation requires accurate 3D understanding of objects and their spatial relations to plan and execute contactrich actions. While large-scale 3D foundation models provide strong priors, their computational cost incurs prohibitive latency for real-time control. We propose Real-time 3D-aware Policy (R3DP), which integrates powerful 3D priors into manipulation policies without sacrificing real-time performance. A core innovation of R3DP is the asynchronous fast–slow collaboration module, which sophisticatedly integrates largescale 3D model’s priors into the policy without compromising real-time performance. The system queries the pre-trained slow system (VGGT) only on sparse key frames, while simultaneously employing a lightweight Temporal Feature Prediction Network (TFPNet) to predict features for all intermediate frames. By leveraging historical data to exploit temporal correlations, TFPNet explicitly improves task success rates through consistent feature estimation. Additionally, we introduce a Multi-View Feature Fuser (MVFF) that aggregates features across views by explicitly incorporating camera intrinsics and extrinsics. R3DP offers a plug-and-play solution for integrating 3D foundation models into realtime inference systems. We evaluate R3DP against multiple baselines across different visual configurations. R3DP effectively harnesses largescale 3D priors to achieve superior results, outperforming single-view and multi-view DP by 32.9% and 51.4% in average success rates. Furthermore, by decoupling heavy 3D understanding from policy execution, R3DP achieves a 44.8% reduction in inference time compared to a naive DP+VGGT integration. Project page and code are available at: https://dazazh.github.io/r3dp-project-page/

Recently, Large Language Models (LLMs) have emerged aspromising layout agents for 3D scene generation. Existing layout agentsstill suffer from implausible layout generation because most of them con-vert 3D assets and 3D layouts into textual descriptions as inputs andoutputs, which involves severe information loss due to the modality gapbetween texts and 3D assets and 3D layouts. We propose NaLA, a native3D LLM layout Agent for high-quality 3D scene generation by placing 3Dassets in the scene. For the inputs, NaLA encodes 3D scene boundariesand 3D assets directly into the LLM, preserving fine-grained geometryand enabling explicit reasoning over relationships like collisions, surfacesupporting, and containment. To accurately output the positions and ori-entations of assets, NaLA adopts a coarse-to-fine prediction mechanismthat first predicts discrete poses in an autoregressive manner and thenrefines the discrete poses with a continuous regression. Trained on diverselayout datasets, NaLA attains strong geometric perception and layout co-herence. Experiments demonstrate that NaLA outperforms prior layoutagents in both generation quality and inference efficiency, with compre-hensive ablation studies to verify each component’s effectiveness.

For image editing with Multimodal Diffusion Transformers(MM-DiT), training-free methods face a critical trade-off: precise back-ground preservation limits editability, while high prompt fidelity de-grades the original scene and object structure. We argue that this tensionstems from suboptimal Key-Value (KV) injection strategies. Global KV-injection rigidly over-preserves the source, whereas strictly masked injec-tion acts as localized inpainting, destroying the edited object’s structuralidentity. We introduce LayerVerse, an optimization framework that re-solves this fundamental dilemma of layer selection for KV-injection byassigning specific layers to two distinct roles: Masked Injection to pre-cisely protect the background, and Global Injection to anchor the editedobject’s structure. Formulating optimal layer allocation as a combina-torial problem, we model the editing error based on pairwise layer in-teractions and solve it globally via Mixed-Integer Linear Programming(MILP). Supported by lightweight, single-step automatic masking, Lay-erVerse seamlessly integrates into training-free, inversion-based editors,achieving highly competitive results on the PIE-Bench benchmark.

Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditional Gaussian statistics provides a principled classification strategy, these parametric summaries remain sensitive to anisotropic representation drift. Existing methods often transport these statistics across tasks using a decoupled, post-hoc paradigm: optimizing a backbone without explicit geometric constraints can distort the legacy manifold, limiting the precision of retroactive alignment. In this paper, we formulate feature transport as an endogenous training constraint rather than a separate post-task step, presenting the Geometry-Anchored Transport Framework. First, we derive an Analytic Geometric Anchor via Mahalanobis-aligned regression to mitigate macroscopic anisotropic drift. Second, we introduce a Topology-Aware Evolution objective that regularizes localized manifold degradation while calibrating a residual network against the analytic prior. By coupling manifold evolution with transport constraints during the primary training phase, our framework mitigates evaluation errors without requiring decoupled fine-tuning. Experiments across CIFAR-100, TinyImageNet, and ImageNet-100 demonstrate that the proposed framework consistently improves upon existing post-hoc alternatives under strict exemplar-free constraints. The code is available at https://github.com/HXuSz11/GATF_ECCV2026.

We present RegHead, a framework for constructing semanticblendshape sets for animatable non-humanoid head avatars. With a fixedexpression vocabulary, semantic blendshapes provide a low-dimensionaland interpretable animation interface and support cross-identity retar-geting. Building such blendshape sets remains expensive because (i)expression-consistent supervision is scarce, (ii) generated 4D assets typ-ically lack correspondence, and (iii) facial motion is highly localized.We propose (1) a large-scale dataset of non-humanoid identities pairedwith a shared expression vocabulary, obtained by expanding a smallartist-rigged library via fine-tuned image editing; (2) a dense stochasticanchor motion representation tailored to localized facial deformations;and (3) a fast feed-forward registration model that converts unregis-tered expression meshes into a corresponded blendshape basis by pre-dicting anchor-based deformations from the neutral shape. Experimentsshow that our approach produces higher-fidelity expression meshes thanbaselines, while running orders of magnitude faster than optimization.We further demonstrate real-time retargeting from human face trackingsignals to non-humanoid characters, capturing both head pose and lo-calized facial motions. Our project page is available at https://snap-research.github.io/RegHead/.

Reconstructing high-fidelity, relightable 3D avatars from asingle in-the-wild image is a challenging ill-posed problem, primarilyhindered by the scarcity of high-quality PBR data and the complex-ity of disentangling illumination from intrinsic materials. In this paper,we present a data-efficient framework that leverages the robust priorsof a unified pre-trained diffusion backbone to sequentially address tex-ture completion, delighting, and material decomposition. Unlike exist-ing methods that rely on fragmented pipelines or extensive proprietarydatasets, we utilize cascaded Low-Rank Adaptations (LoRAs) to adaptthe strong generative prior of the diffusion model for each sub-task inUV space. Specifically, we first employ an Inpainting LoRA to completemissing UV textures caused by occlusion, leveraging the model’s seman-tic understanding to generate semantically and photometrically coher-ent details. Subsequently, a Light-Homogenization LoRA and a novelCross-Intrinsic Attention mechanism are introduced to remove baked-inlighting and collaboratively synthesize pixel-aligned PBR maps (Albedo,Normal, Roughness, Specular, and Displacement). To ensure physicalplausibility, we impose a UV-space differentiable BRDF shading lossduring the decomposition stage, forcing the generative process to adhereto the rendering equation without the artifacts typical of rasterization-based supervision. Extensive experiments demonstrate that our method,trained on fewer than 100 real 3D scans, generates comprehensive, 4K-resolution PBR assets with superior realism and generalization comparedto state-of-the-art methods, and all training code and model weights willbe released upon acceptance.

Controllable video generation remains challenging due tothe di"culty of specifying precise multi-object interactions using textprompts or motion-control inputs that primarily constrain pixel move-ment. In practice, trajectory-based control often requires users to drawaccurate tracks for multiple objects, which scales poorly with scene com-plexity and becomes ambiguous under occlusion or overlap. To enableflexible yet precise multi-subject control, we introduce GraphVid, agraph-conditioned image-to-video generation model that enables inter-active control through structured interaction graphs. We further cu-rate GraphVid-Bench, a large-scale interaction-centric video datasetwith structured relational annotations to enable training of interaction-aware video generation models. Despite using substantially less trainingdata and fewer trainable parameters than prior motion-control methods,GraphVid delivers strong controllability and video quality. Comparedwith Motion-I2V, GraphVid reduces FID by up to 39.9% and FVD by37.6%, while improving PSNR (9.87→15.98) and SSIM (0.38→0.61). Ourresults highlight the potential of structured semantic interfaces as a pow-erful paradigm for controllable video generation.PLAN Lab https://plan-lab.github.io/graphvid

Extracting dynamic 4D object interactions from massive, inthe-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction methods primarily focus on isolated objects, often failing under the severe occlusions and complex dynamics inherent in multi-object interactions. To bridge this gap, we propose HAT- 4D, the first agentic framework designed to reconstruct the 3D geometry, temporal dynamics, and physical interactions of multiple objects from a single video. By integrating VLMs with a multi-level human-in-the-loop feedback mechanism, HAT-4D efficiently resolves depth ambiguities and interaction-induced occlusions during 3D generation and 4D propagation, yielding physically plausible assets without relying on expensive multicamera rigs. As a scalable data engine, HAT-4D facilitates the creation of MVOIK-4D, an open-world benchmark for monocular 4D interaction reconstruction, accompanied by a novel multi-dimensional evaluation protocol focused on physical plausibility and temporal consistency. Extensive experiments demonstrate that HAT-4D achieves SOTA performance on most evaluation metrics, while maintaining competitive semantic alignment. Ablation studies show that introducing a small amount of human feedback improves interaction reconstruction. Moreover, the data produced by HAT-4D effectively improves baseline performance when used for finetuning. Our data and code are available at project webpage.