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

Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs

Yung-Hsu Yang, Luigi Piccinelli, Samuel Rota Bulo, Sunghwan Hong, Denys Rozumnyi, Johannes Schonberger, Zuria Bauer, Hermann Blum, Peter Kontschieder, Marc Pollefeys

Metric 3D object detection is a core capability for embodied agents, yet most reliable systems lean on depth sensors, trading away cost, power, and integration simplicity. This motivates monocular 3D detection, which avoids additional constraints, yet it faces a major obstacle: from a single image, depth, and especially absolute scale, are underconstrained. As a result, the prevailing pattern of detecting in 2D and then predicting 3D attributes is often brittle, since modest range errors can dominate 3D localization, and the learned scale prior can fail when cameras, motion, or environments undergo domain shifts. To address this, we propose Map-Det3D, an online multi-view 3D object detection model that brings detection directly into a 3D space reconstructed from RGB. We map a short temporal window into multiple views and repurpose a feed-forward metric 3D reconstruction model as our geometric backbone while tuning its object-aware capabilities. Building on this representation, Map-Det3D directly predicts boxes in metric 3D space, without the widely used 2Dto-3D lifting. Experiments across different benchmarks show that this design supports strong online performance and robust transfer without adaptation, suggesting that training reconstruction priors for detection is a practical route to stable metric 3D detection from monocular video. Code and models are available at royyang0714.github.io/Map-Det3D.

ECCV 2026

Latent Fusion: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents

Laura Fink, Linus Franke, George Kopanas, Marc Stamminger, Peter Hedman

We propose a feed-forward method for dense Signed DistanceField (SDF) regression from unstructured image collections in less thanthree seconds, without camera calibration or post-hoc fusion. Our keyinsight is that the intermediate feature space of pretrained multi-viewfeed-forward geometry transformers (FFGT) already encodes a powerfuljoint world representation; yet, existing pipelines discard it, routing fea-tures through per-view prediction heads before assembling 3D geometrypost-hoc, which discards valuable completeness information and accu-mulates inaccuracies. We instead perform 3D extraction directly fromFFGT features via learned volumetric extraction: voxelized canonicalembeddings that progressively absorb multi-view geometry informationthrough interleaved cross- and self-attention into a structured volumet-ric latent grid. A simple convolutional decoder then maps this grid to adense SDF. We additionally propose a scalable, validity-aware supervi-sion scheme directly using SDFs derived from depth maps or 3D assets,tackling practical issues like non-watertight meshes. Our approach yieldscomplete and well-defined distance values across sparse- and dense-viewsettings and demonstrates geometrically plausible completions.

ECCV 2026

Weather-Conditioned Depth Anything

Zhaoming Xu, Chan-Wei Hu, Kuan-Ru Huang, Zihao Zhu, Renjie Li, Yang Zhou, Zhengzhong Tu

Monocular depth estimation foundation models, such as the Depth Anything series, have achieved remarkable performance across diverse domains. However, they still suffer from critical failures under adverse weather conditions, such as fog, rain, snow, or at night. To address this, we present Weather-Conditioned Depth Anything (DA-W), a framework that explicitly disentangles style from content for weatherrobust depth estimation. Specifically, we introduce a Style Filter trained on a curated mix of real and synthetic degradation datasets to extract content-independent, degradation-aware weather embeddings. This style embedding is then injected into the Depth Anything backbone using a parameter-efficient, zero-initialized adapter. Such a lightweight modulation allows a single unified model to robustly adapt to diverse conditions—including fog, rain, snow, and low-light—while avoiding catastrophic forgetting of its core generalization abilities in normal conditions. We train the adapter using a pseudo-label distillation and alignment strategy. Our comprehensive experiments demonstrate that our proposed DA-W achieves state-of-the-art robust depth estimation, improving AbsRel by an average of 3.7% on our curated weather benchmarks, while matching or slightly outperforming performance on standard clean benchmarks.

ECCV 2026

The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models

Adeel Yousaf, Soumik Ghosh, James Beetham, Amrit Singh Bedi, Shah Mubarak

Safety alignment of text-to-image (T2I) diffusion models aimsto suppress harmful generations while preserving utility on benign prompts.Recent methods often appear to deliver high safety with high utility, butthis conclusion rests largely on coarse global utility metrics (e.g., FID,CLIPScore) that are insensitive to fine-grained semantic correctness, cre-ating an illusion of high utility. We show that when utility is measuredwith structured evaluation, this illusion breaks: on TIFA (Text-to-ImageFaithfulness evaluation with Question Answering), safety-aligned modelssuffer substantial drops in semantic fidelity, including failures in objectcounts, attributes, and relationships. To diagnose the source of this gap,we analyze the text-encoder prompt embedding space and uncover se-mantic collapse, a contraction of embedding spread coupled with distor-tion of inter-prompt similarity structure, which strongly correlates withstructured utility loss. Guided by this insight, we propose Structure-Aware Geometric Regularization (SAGE)1 , a safety alignment objec-tive that explicitly preserves embedding spread and inter-prompt rela-tional structure during adaptation. Our method restores structured util-ity (TIFA +5.0% over prior state-of-the-art) while maintaining strongsafety performance and competitive coarse-grained utility scores.

ECCV 2026

GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces

Xinyu Geng, Yanjing Xiao, Yuyang Zhang, Hanwen Wang, Xinyan Liu, Rui Min, Tianqing Fang, Yi Ren Fung

Deep research agents integrate fragmented evidence throughmulti-step tool use. BrowseComp offers a text-only testbed for such agents,but existing multimodal benchmarks rarely require both weak visual cuescomposition and BrowseComp-style multi-hop verification. Geolocationis a natural testbed because answers depend on combining multipleambiguous visual cues and validating them with open-web evidence.Thus, we introduce GeoBrowse, a geolocation benchmark that combinesvisual reasoning with knowledge-intensive multi-hop queries. Level 1 testsextracting and composing fragmented visual cues, and Level 2 increasesquery difficulty by injecting long-tail knowledge and obfuscating keyentities. To support evaluation, we provide an agentic workflow GATEwith five think-with-image tools and four knowledge-intensive tools, andrelease expert-annotated stepwise traces grounded in verifiable evidencefor trajectory-level analysis. Experiments show that GATE outperformsdirect inference and open-source agents, indicating that no-tool, search-only or image-only setups are insufficient. Gains come from coherent,level-specific tool-use plans rather than more tool calls, as they morereliably reach annotated key evidence steps and make fewer errors whenintegrating into the final decision. The GeoBrowse benchmark and codesare provided in https://github.com/ornamentt/GeoBrowse.

ECCV 2026

Gradient sparsity regularization for training unlearning-compatible models

Sobhan Hemati, Soufiane Lamghari, Masoud Asgharian, Xu Li, Hongliang Li

In this paper, we approach the machine unlearning (MU)problem from a novel perspective: Can we design a learning strategythat simplifies the later MU problem, i.e., leads to unlearning-compatiblemodels? Motivated by recent findings that the cost to reverse SGD (un-learning error) is proportional to the accumulated loss curvature and thatthe generalization error (a measure of acquired subject-specific knowl-edge) is bounded by loss sharpness, we focus on the loss sharpness as thekey factor to train unlearning-compatible models. By studying the theo-retical implications of defining the sharpness over different perturbationnorms, we propose a variation of the sharpness, quantified by the l1 normof the gradient, which minimizing it leads to a flatter learning trajectoryand, as a result, smaller unlearning and generalization errors. Consider-ing these results, to have unlearning-compatible models, we propose toregularize the training loss with l1 norm of the gradient, which encour-ages gradient sparsity during training. Our experiments show that onlyby using our regularizer in the training stage, the MU performance ofvarious baselines is considerably improved, suggesting the effectivenessof our approach in simplifying the MU problem by training unlearning-compatible models. Moreover, we demonstrate that the benefits of ourapproach become even more significant when dealing with poisoned datain backdoor attack scenarios. Our investigations show that in such ascenario, gradient sparsity not only simplifies model cleaning but alsodamps the gradient spikes, which are typically caused by poisonous dataand encourage the model to automatically learn less from such poisonousdata points.

ECCV 2026

Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation

Sunggu Kyung, Jinyoung Seo, Hyunseok Lim, Dongyeong Kim, Hyungbin Park, Jimin Sung, Wooyoung Jo, Yoojin Nam, Namkug Kim

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.

ECCV 2026

GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

Shijie Zhou, Viet Lai, Hao Tan, Jihyung Kil, Wanrong Zhu, Changyou Chen, Ruiyi Zhang

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.

ECCV 2026

Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion

Kazuma Fujiwara, Takuya Funatomi, Kazuya Kitano, Yuki Fujimura, Yasuhiro Mukaigawa

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.

ECCV 2026

HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding

Yinsheng Yao, Yan Liu, Chen Ye

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.

ECCV 2026

GLARE: Towards Generalizable Detection of Latent Diffusion Images with Global-Local Reconstruction Error

Jiangtao Yan, Jiazhen Ji, Zhongyu Zhang, Yuge Huang, Wenbin Wang, Shouhong Ding

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.

ECCV 2026

Same Pool, Different Answer: Stable Best-of-N Selection for Vision-Language Models

PengFei Zheng

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.

ECCV 2026

Deformable and Multi-view Gradient-Aligned Physical Adversarial Camouflage

Jiawei Liang, Puning Zhao, Tianrui Lou, Haoqing Zhang, Xianghao Jiao, Bozheng Lin, Ming Zhang, Xiaochun Cao

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.

ECCV 2026

UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving

Zhexiao Xiong, Xin Ye, Burhaneddin Yaman, Sheng Cheng, Yiren Lu, Jingru Luo, Nathan Jacobs, Liu Ren

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.

ECCV 2026

HumanOmni-Speaker: Identifying Who said What and When

Detao Bai, Xihan Wei, Zhiheng Ma

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.

ECCV 2026

P3-SAM: Native 3D Part Segmentation

Changfeng Ma, Yang Li, Xinhao Yan, Jiachen Xu, Yunhan Yang, Chunshi Wang, Zibo Zhao, Yanwen Guo, Zhuo Chen, Chunchao Guo

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.

ECCV 2026

Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement Learning

Vishwas Sathish, Viresh Ranjan, Xinliang Zhu, Arnab Dhua, Douglas Gray

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.

ECCV 2026

R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation

Yuhao Zhang, Wanxi Dong, Yue Shi, Yi Liang, Jingnan Gao, Qiaochu Yang, Yaxing Lyu, Zhixuan Liang, Yibin Liu, Congsheng Xu, Xianda Guo, Wei Sui, Yaohui Jin, Xiaokang Yang, Yanyan Xu, Yao Mu

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/

ECCV 2026

NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation

Cheng Wan, Yongsen Mao, Wenzheng Wu, Yuxuan Xie, Chucheng Xiang, Runze Wang, Xiang Zhang, Zhongyuan Liu, Rushi Dai, Yuan Liu

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.

ECCV 2026

LayerVerse: Finding the Sweet Spot for KV-Injection in Training-Free Image Editing

Mikhail Zhirnov, Arsen Kuzhamuratov, Andrey Kuznetsov, Ivan Oseledets, Konstantin Sobolev

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.

Keep browsing

More papers from top AI conferences

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