paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image

Kim Youwang, Zhengyu Yang, Liuhao Ge, Yu Rong, Timur Bagautdinov, Su Zhaoen, Nir Sopher, Jovan Popović, Teng Deng, Tae-Hyun Oh, Chen Cao

We introduce FiCA, a Feed-forward, instant Gaussian Codec Avatar generation pipeline that creates lifelike avatars from a single portrait image. Generating a photorealistic and drivable avatar from just a single image is significantly challenging due to the limited visual information available to accurately infer the 3D appearance and geometry of human heads. To address this, we develop a novel system that combines human-centric vision foundation models with a diffusion model. This system is designed to fully exploit partial visual observations to generate lifelike human avatars. Our proposed diffusion model learns a generative mapping from these partial observations to complete and authentic 3D mesh reconstruction. Additionally, we introduce a feed-forward mesh refinement network that enhances the fidelity and identity preservation of the generated avatars, eliminating the need for person-specific test-time optimization. By leveraging a universal prior model that decodes a generated mesh into a set of 3D Gaussians, we generate a photorealistic 3D Gaussian avatar, capable of being driven with novel expressions in real-time. Our experiments demonstrate that the avatars generated by our feed-forward approach faithfully represent diverse identities and surpass the visual quality of avatars produced by recent competing methods.

arXiv

Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition

Xucheng Shen, Kun Li, Fei Wang, Wei Qian, Jin Jiang, Dan Guo

Micro-gesture online recognition aims to temporally localize and classify subtle gestures in untrimmed videos. Owing to their extremely short duration, low motion amplitude, and ambiguous visual cues, capturing discriminative spatiotemporal representations remains highly challenging. Existing parameter-efficient adapters typically employ a single branch to model spatial and temporal cues jointly, which may fail to capture the fine-grained patterns of micro-gestures. To address this limitation, we propose a Spatial-Temporal Decoupled Adapter that decomposes video adaptation into independent temporal and spatial branches via lightweight depthwise convolutions. In addition, to alleviate the long-tailed class distribution inherent in the benchmark dataset, we introduce an Adaptive Soft Balanced Augmentation method, which dynamically allocates augmentation intensity based on class rarity and learning difficulty, without manual thresholds. Our method achieves an F1 score of 0.43808, ranking 1st in Track 2 of the 4th EI-MiGA-IJCAI Challenge.

arXiv

DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models

Abdullah Al Shafi, Kazi Saeed Alam, Sk Imran Hossain, Engelbert Mephu Nguifo

Parameter compression of class-conditional diffusion models exposes a structural limitation in output-level distillation: supervising only the guided output leaves the two score branches non-identifiable, so the classifier-free guidance gap is not determined in the student. The zero-loss set admits degenerate solutions in which both branches collapse toward identical predictions, and guidance loses its effect at inference despite low training loss. For each fixed input the objective is exactly flat in a branch-output direction at every residual value, so the ambiguity is a property of the output-level objective rather than a poor local minimum. This paper introduces DASH, which supervises the conditional and unconditional branches independently. An anchor term regularises the conditional prediction toward ground-truth noise, and the teacher's final learned per-timestep curriculum transfers into the student as a frozen prior. Across CIFAR-10, CIFAR-100, and class-conditional ImageNet-64, a more than 5x compressed student stays within four FID points of its teacher and recovers at least 89% of the teacher's guidance-gap magnitude, where no other two-branch baseline with defined calibration exceeds 82%. Ablation isolates unconditional supervision as the term that separates this formulation from output-level distillation. The account is quantitative: the null space fixes the ratio between a composite student's two branch errors, and the measured ratios approximately match that prediction on all three datasets.

arXiv

Prefix-Adaptive Block Diffusion for Efficient Document Recognition

Mingxu Chai, Ziyu Shen, Chenyu Liu, Jihua Kang, Tao Gui, Qi Zhang

Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing. However, existing BDMs bind denoising and cache commitment to fixed block boundaries: parallelism shrinks during intra-block denoising, while generated tokens cannot be cached until the whole block is completed. Moreover, intra-block bidirectional denoising conflicts with inter-block autoregression, creating inconsistent information flow that can challenge structure-sensitive recognition. We propose the Prefix-Adaptive Block Diffusion Model (PA-BDM), which replaces intra-block bidirectional denoising with causal denoising from prefix to suffix and treats the block size as a maximum candidate range rather than a fixed commitment unit. PA-BDM uses Confidence-gated Structural Loss (CSL) to build low-entropy prefixes before extending training to longer continuations. During inference, Progressive Prefix Commitment (PPC) then dynamically commits the longest reliable prefix into the KV cache and resets the next candidate range from the updated prefix, restoring a large parallel decoding space at each step. Experiments show that the 3B PA-BDM achieves higher recognition scores on several benchmarks and improves inference throughput by 71.6\% over the 2.5B MinerU-Diffusion.

arXiv

Spatial-Frequency Gated Swin Transformer for Cross-Sensor Remote Sensing Super-Resolution

Md Aminur Hossain, Ayush V. Patel, Sanjay K. Singh, Yogesh Jethani, Biplab Banerjee

Remote sensing single-image super-resolution aims to generate high-resolution imagery from low-resolution observations while preserving fine structures such as roads, building boundaries, field edges, and land-cover transitions. Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling through shifted-window self-attention, but their feed-forward networks remain generic channelmixing modules that do not explicitly distinguish low-frequency structure from residual details. We propose SFG-SwinSR, which replaces the standard Swin2SR feed-forward network with a lightweight SpatialFrequency Gated Feed-Forward Network. The module estimates a smoothed feature component through a depthwise low-pass branch, derives residual details by subtraction, refines them spatially, and adaptively reinjects useful details through a bottleneck gate. Experiments on the real crosssensor SEN2VENμS, OLI2MSI, and SEN2NAIP benchmarks, together with an auxiliary synthetic SpaceNet Challenge 3 setting, show consistent improvements across most evaluation settings and competitive performance against recent Swin-based baselines. The results indicate that spatial-frequency transformation within transformer feed-forward networks provides an effective lightweight inductive bias for structure-aware cross-sensor remote sensing super-resolution. Source code is available at https://github.com/aminurhossain/SFG-SwinSR

arXiv

TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos

Hengyi Feng, Hao Liang, Mingrui Chen, Bohan Zeng, Meiyi Qiang, Zhengyang Zhao, Zimo Meng, Zeang Sheng, Wentao Zhang

Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks largely fail to evaluate this capability. They restrict videos to short clips, isolate modalities, or reduce questions to one-hop perception. We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness. TraceAV-Bench comprises 2,200 rigorously validated multiple-choice questions over 578 long videos, totaling 339.5 hours, spanning 4 evaluation dimensions and 15 sub-tasks. Each question is grounded in an explicit multi-hop evidence trajectory that averages 3.68 hops across a 15.1-minute temporal span. The dataset is built by a three-step pipeline followed by a strict quality assurance process. Evaluation of multiple representative OmniLLMs on TraceAV-Bench reveals that the benchmark poses a persistent challenge across all models, with the strongest closed-source model (Gemini 3.1 Pro) reaching only 68.29% on general tasks, and the best open-source model (Ming-Flash-Omni-2.0) reaching 51.70%, leaving substantial headroom. Further analysis shows that current models struggle to gather and combine evidence across long audio-visual videos, with performance varying across modalities and reasoning tasks. We hope TraceAV-Bench will facilitate progress toward reliable long-form audio-visual reasoning in OmniLLMs.

arXiv

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning

Guangfu Guo, Xiaoqian Lu, Yue Feng, Mingming Sun

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted from the most informative regions to secondary cues-we propose Structural Sequential Visual CoT SSV-CoT. First, a question-relevant saliency map identifies and organizes key visual regions, explicitly modeling the spatial distribution of visual importance. Second, reasoning is performed following this discriminative order, inducing a curriculum-like semantic progression from primary to secondary cues. This method is trained end-to-end, using text cot and answer supervision, without relying on region-level annotations or specialized external tools. Experiments on diverse visual reasoning benchmarks show gains, validating structured and sequential visual cognition.

arXiv

ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling

Daowen Li, Ruixiao Dong, Kai Li, Ying Chen, Ding Ding, Li Li

Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their generative modules are weakly coupled with entropy coding, limiting bitrate reduction. Inspired by the next-scale prediction in the Visual Auto-Regressive (VAR) models, we propose ProGVC, a Progressive-based Generative Video Compression framework that unifies progressive transmission, efficient entropy coding, and detail synthesis within a single codec. ProGVC encodes videos into hierarchical multi-scale residual token maps, enabling flexible rate adaptation by transmitting a coarse-to-fine subset of scales in a progressive manner. A Transformer-based multi-scale autoregressive context model estimates token probabilities, utilized both for efficient entropy coding of the transmitted tokens and for predicting truncated fine-scale tokens at the decoder to restore perceptual details. Extensive experiments demonstrate that as a new coding paradigm, ProGVC delivers promising perceptual compression performance at low bitrates while offering practical scalability at the same time.

arXiv

Generalization and Memorization in Rectified Flow

Mingxing Rao, Daniel Moyer

Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF models memorize training data remain largely underexplored. In this paper, we systematically investigate the memorization behaviors of RF through the test statistics of Membership Inference Attacks (MIA). We progressively formulate three test statistics, culminating in a complexity-calibrated metric that successfully decouples intrinsic image spatial complexity from genuine memorization signals. This calibration yields a significant performance surge -- boosting attack AUC by up to 15% and the privacy-critical TPR@1%FPR metric by up to 45% -- establishing the first non-trivial MIA specifically tailored for RF. Leveraging these refined metrics, we uncover a distinct temporal pattern: under standard uniform temporal training, a model's susceptibility to MIA strictly peaks at the integration midpoint, a phenomenon we justify via the network's forced deviation from linear approximations. Finally, we demonstrate that substituting uniform timestep sampling with a Symmetric Exponential (U-shaped) distribution effectively minimizes exposure to vulnerable intermediate timesteps. Extensive evaluations across three datasets confirm that this temporal regularization suppresses memorization while preserving generative fidelity.

arXiv

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval

Zhuchenyang Liu, Yao Zhang, Yu Xiao

Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both document indexing and query encoding, incurring high latency and GPU dependence even for plain-text queries. We observe that this design is unnecessarily symmetric: documents are visually complex and demand strong visual understanding, whereas queries are just short text strings. NanoVDR exploits this query--document asymmetry by decoupling the two encoding paths: a frozen 2B VLM teacher indexes documents offline, while a distilled text-only student as small as 69M parameters encodes queries at inference. The key design choice is the distillation objective. Through systematic comparison of six objectives across three backbones and 22 ViDoRe benchmark datasets, we find that pointwise cosine alignment on query text consistently outperforms ranking-based and contrastive alternatives, while requiring only pre-cached teacher query embeddings and no document processing during training. Furthermore, we identify cross-lingual transfer as the primary performance bottleneck, and resolve it cheaply by augmenting training data with machine-translated queries. The resulting NanoVDR-S-Multi (DistilBERT, 69M) retains 95.1\% of teacher quality and outperforms DSE-Qwen2 (2B) on v2 and v3 with 32$\times$ fewer parameters and 50$\times$ lower CPU query latency, at a total training cost under 13 GPU-hours.

arXiv

ProGS: Towards Progressive Coding for 3D Gaussian Splatting

Zhiye Tang, Lingzhuo Liu, Shengjie Jiao, Qiudan Zhang, Junhui Hou, You Yang, Xu Wang

Progressive transmission of 3D Gaussian Splatting (3DGS) requires each completed transmission stage to be decodable from received data and directly renderable. This work presents ProGS, a progressive codec that organizes anchor-based 3DGS as parent-closed octree prefixes. ProGS combines parent-causal entropy coding, level-balanced anchor growth, bounded multi-prefix training, and lightweight parent-anchor refinement to improve early-prefix quality without altering the complete-model rendering path. One fixed-$λ$ training run yields five deployable rate--quality points from a single bitstream. Experiments on 17 scenes from three datasets evaluate rate--distortion performance, rendering speed, and transmission efficiency against progressive and single-rate baselines. On one representative scene per dataset, ProGS reaches a common quality target with 30.7 $\sim$ 60.7\% fewer bytes than HAC-Rand and 22.6 $\sim$ 53.4\% fewer bytes than HAC++-Rand. Across the three dataset averages, ProGS-LR uses 4.7 $\sim$ 6.1\% fewer bytes than HAC-high while improving SSIM by 0.002 $\sim$ 0.041 and reducing LPIPS by 4.8 $\sim$ 51.2\%. The parent-closed syntax makes every prefix causally decodable and directly renderable without future topology. ProGS-HR also yields higher endpoint SSIM and lower LPIPS than PCGS across all three dataset averages, and all five prefixes render in real time. Code is available at https://github.com/ZhiyeTang/ProGS-Official

arXiv

DiffInf: Influence-Guided Diffusion for Supervision Alignment in Facial Attribute Learning

Basudha Pal, Zhaoyang Wang, Rama Chellappa

Facial attribute classification relies on large-scale annotated datasets in which many traits, such as age and expression, are inherently ambiguous and continuous but are discretized into categorical labels. Annotation inconsistencies arise from subjectivity and visual confounders such as pose, illumination, expression, and demographic variation, creating mismatch between images and assigned labels. These inconsistencies introduce supervision errors that impair representation learning and degrade downstream prediction. We introduce DiffInf, a self-influence--guided diffusion framework for mitigating annotation inconsistencies in facial attribute learning. We first train a baseline classifier and compute sample-wise self-influence scores using a practical first-order approximation to identify training instances that disproportionately destabilize optimization. Instead of discarding these influential samples, we apply targeted generative correction via a latent diffusion autoencoder to better align visual content with assigned labels while preserving identity and realism. To enable differentiable guidance during correction, we train a lightweight predictor of high-influence membership and use it as a surrogate influence regularizer. The edited samples replace the originals, yielding an influence-refined dataset of unchanged size. Across multi-class facial attribute classification, DiffInf consistently improves generalization compared with standard noisy-label training, robust optimization baselines, and influence-based filtering. Our results demonstrate that repairing influential annotation inconsistencies at the image level enhances downstream facial attribute classification without sacrificing distributional coverage.

arXiv

Social-JEPA: Emergent Geometric Isomorphism

Haoran Zhang, Youjin Wang, Yi Duan, Rong Fu, Dianyu Zhao, Sicheng Fan, Shuaishuai Cao, Wentao Guo, Xiao Zhou

World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or coordination. After training, their internal representations exhibit a striking emergent property: the two latent spaces are related by an approximate linear isometry, enabling transparent translation between them. This geometric consensus survives large viewpoint shifts and scant overlap in raw pixels. Leveraging the learned alignment, a classifier trained on one agent can be ported to the other with no additional gradient steps, while distillation-like migration accelerates later learning and markedly reduces total compute. The findings reveal that predictive learning objectives impose strong regularities on representation geometry, suggesting a lightweight path to interoperability among decentralized vision systems. The code is available at https://anonymous.4open.science/r/Social-JEPA-5C57.

arXiv

InfScene-SR: Seamless Super-Resolution of Arbitrarily Large Remote-Sensing Scenes via Variance-Preserving Joint Denoising

Shoukun Sun, Zhe Wang, Xiang Que, Jiyin Zhang, Xiaogang Ma

Diffusion models now give the best perceptual quality in super-resolution (SR), but their architecture and training confine them to small fixed crops. Operational remote sensing needs seamless scenes orders of magnitude larger. Joint denoising fuses overlapping tiles at every reverse step and lets text-to-image diffusion generate beyond its training crop, but it assumes deterministic ODE samplers. With the stochastic sampler of SR models such as SR3, the averaging also partly cancels independent per-tile noise. This known variance erosion blurs the detail SR should recover and must be corrected. We carry variance-corrected fusion to conditional SR and derive Spatially-Decoupled Variance Correction (SDVC), an exact reformulation that replaces per-step global normalization with independent per-tile contributions accumulated in one additive pass. SDVC turns the coupled per-step computation into independent tile-local work, so the resulting pipeline, InfScene-SR, runs in parallel across GPUs and makes SR of arbitrarily large scenes feasible. On a 5$\times$ SR task built from NAIP aerial imagery, we evaluate whole scenes with fidelity, perceptual, seam-continuity, and faithfulness metrics. Under one backbone, InfScene-SR is the only fusion strategy that is seamless and sharp at once, the closest to the low-resolution observation among those that synthesize detail, and within 0.003 IoU of native high-resolution imagery on downstream invasive-plant segmentation. Code is available at https://github.com/TitorX/infscene-sr.

arXiv

DesignAsCode: Bridging Structural Editability and Visual Fidelity in Graphic Design Generation

Ziyuan Liu, Shizhao Sun, Danqing Huang, Yingdong Shi, Meisheng Zhang, Ji Li, Jingsong Yu, Jiang Bian

Graphic design generation demands a delicate balance between high visual fidelity and fine-grained structural editability. However, existing approaches typically bifurcate into either non-editable raster image synthesis or abstract layout generation devoid of visual content. Recent combinations of these two approaches attempt to bridge this gap but often suffer from rigid composition schemas and unresolvable visual dissonances (e.g., text-background conflicts) due to their inexpressive representation and open-loop nature. To address these challenges, we propose DesignAsCode, a novel framework that reimagines graphic design as a programmatic synthesis task using HTML/CSS. Specifically, we introduce a Plan-Implement-Reflect pipeline, incorporating a Semantic Planner to construct dynamic, variable-depth element hierarchies and a Visual-Aware Reflection mechanism that optimizes the code to rectify rendering artifacts. Extensive experiments demonstrate that DesignAsCode significantly outperforms baselines in both structural validity and aesthetic quality. Furthermore, our code-native representation unlocks advanced capabilities, including automatic layout retargeting, complex document generation (e.g., resumes), and CSS-based animation. Our project page is available at https://liuziyuan1109.github.io/design-as-code/.

arXiv

StableWorld: Towards Stable and Consistent Long Interactive Video Generation

Ying Yang, Zhengyao Lv, Yujia Zeng, Tianlin Pan, Haofan Wang, Yueming Lyu, Binxin Yang, Hubery Yin, Chen Li, Jing Lyu, Ziwei Liu, Chenyang Si

In this paper, we explore the overlooked challenge of stability and temporal consistency in interactive video generation, which synthesizes dynamic and controllable video worlds through interactive behaviors such as camera movements and text prompts. Despite remarkable progress in world modeling, current methods still suffer from severe instability and temporal degradation, often leading to spatial drift and scene collapse during long-horizon interactions. To better understand this issue, we initially investigate the underlying causes of instability and identify that the major source of error accumulation originates from the same scene, where generated frames gradually deviate from the initial clean state and propagate errors to subsequent frames. Building upon this observation, we propose a simple yet effective method, \textbf{StableWorld}, a Dynamic Frame Eviction Mechanism. By continuously filtering out degraded frames while retaining geometrically consistent ones, StableWorld effectively prevents cumulative drift at its source, leading to more stable and temporal consistency of interactive generation. Promising results on multiple interactive video models, \eg, Matrix-Game, Open-Oasis, and Hunyuan-GameCraft, demonstrate that StableWorld is model-agnostic and can be applied to different interactive video generation frameworks to substantially improve stability, temporal consistency, and generalization across diverse interactive scenarios.

arXiv

POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generation

Andrea Rigo, Luca Stornaiuolo, Weijie Wang, Mauro Martino, Bruno Lepri, Nicu Sebe

Training robust visual surveillance models requires large-scale datasets with precise spatial annotations, yet collecting real surveillance data is costly, privacy-sensitive, and often legally constrained. Synthetic data generation offers a compelling alternative, but existing methods lack fine-grained 3D control over object placement and appearance, limiting geometric consistency across camera viewpoints. We introduce POCI-Diff (Positioning Objects Consistently and Interactively), a framework that generates annotated synthetic scenes from explicit 3D bounding-box layouts with per-object semantic control. By integrating Blended Latent Diffusion with depth-conditioned ControlNet, POCI-Diff synthesises complex multi-object scenes in a single forward pass, binding individual text descriptions to specific 3D locations. We further propose a warping-free editing pipeline supporting object insertion, removal, and transformation via regeneration, enabling efficient scene variation for data augmentation. Object identity across edits is preserved by conditioning on reference images via IP-Adapter, ensuring appearance consistency throughout interactive scene manipulation. Experiments show that POCI-Diff outperforms state-of-the-art 3D layout-guided generation methods in visual fidelity and layout adherence, while eliminating warping-induced geometric artifacts.

arXiv

MedVision: Benchmarking Quantitative Medical Image Analysis

Yongcheng Yao, Yongshuo Zong, Raman Dutt, Yongxin Yang, Sotirios A. Tsaftaris, Timothy Hospedales

Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., "Is this normal or abnormal?") or qualitative descriptive tasks. However, clinical decision-making often relies on quantitative assessments, such as measuring the size of a tumor or the angle of a joint, from which clinicians draw their own diagnostic conclusions. This quantitative reasoning capability remains underexplored and poorly supported in existing VLMs. In this work, we introduce MedVision, a large-scale dataset and benchmark specifically designed to evaluate and improve VLMs on quantitative medical image analysis. MedVision spans 22 public datasets covering diverse anatomies and modalities, with 29.0K 3D images, 11.2M annotated 2D slices, and 24.3M single-instance annotations. We focus on three representative quantitative tasks: (1) detection of anatomical structures and abnormalities, (2) tumor/lesion (T/L) size estimation, and (3) angle/distance (A/D) measurement. We show that current off-the-shelf VLMs perform poorly on these tasks. However, supervised and reinforcement fine-tuning (RFT) on MedVision significantly enhances performance across detection, T/L size estimation, and A/D measurement, yielding MedVision-V0 as a strong open baseline. In the RFT stage, we design and evaluate the efficacy of process rewards, multiplicative reward composition, and multi-task RFT with curriculum learning. MedVision provides a foundation for developing VLMs with robust quantitative reasoning capabilities in medical imaging.

arXiv

Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey

Rui Shao, Wei Li, Lingsen Zhang, Renshan Zhang, Zhiyang Liu, Ran Chen, Liqiang Nie

Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional rule-based methods fail to scale or generalize in unstructured, novel environments. In recent years, Vision-Language-Action (VLA) models, built upon Large Vision-Language Models (VLMs) pretrained on vast image-text datasets, have emerged as a transformative paradigm. This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation. We begin by clearly defining large VLM-based VLA models and delineating two principal architectural paradigms: (1) monolithic models, encompassing single-system and dual-system designs with differing levels of integration; and (2) hierarchical models, which explicitly decouple planning from execution via interpretable intermediate representations. Building on this foundation, we present an in-depth examination of large VLM-based VLA models: (1) integration with advanced domains, including reinforcement learning, training-free optimization, learning from human videos, and world model integration; (2) synthesis of distinctive characteristics, consolidating architectural traits, operational strengths, and the datasets and benchmarks that support their development; (3) identification of promising directions, including memory mechanisms, 4D perception, efficient adaptation, multi-agent cooperation, and other emerging capabilities. This survey consolidates recent advances to resolve inconsistencies in existing taxonomies, mitigate research fragmentation, and fill a critical gap through the systematic integration of studies at the intersection of large VLMs and robotic manipulation. We provide a regularly updated project page to document ongoing progress: https://github.com/JiuTian-VL/Large-VLM-based-VLA-for-Robotic-Manipulation

arXiv

Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention

Yuang Ai

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this issue with sparse or window-based attention, yet inherently limit global context modeling. Linear attention, a variant of softmax attention, demonstrates promise in global context modeling while maintaining linear complexity, offering a potential solution to the above challenge. Despite its efficiency benefits, vanilla linear attention suffers from a significant performance drop in IR, largely due to the low-rank nature of its attention map. To counter this, we propose Rank Enhanced Linear Attention (RELA), a simple yet effective method that enriches feature representations by integrating a lightweight depthwise convolution. Building upon RELA, we propose an efficient and effective Vision Transformer, named LAformer. LAformer eliminates hardware-inefficient operations such as softmax and window shifting, enabling efficient processing of high-resolution images. Extensive experiments across 7 IR tasks and 21 benchmarks demonstrate that LAformer outperforms SOTA methods and offers significant computational advantages. Furthermore, we extend LAformer to diffusion-based and flow-based visual generation, showcasing its strong potential as a competitive alternative to DiT and SiT. Code and models are available at https://github.com/shallowdream204/LAformer.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →