跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 05:01 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 05:29 — 2026-11-10 05:29（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-10 05:01最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 4,042 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 04:59（北京时间）
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c4a41c776c99f0341c5ebfd68c4b80e8CVF · CVPR 2026

Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding

Nagrani, Arsha, Uijlings, Jasper, Buch, Shyamal, Weyand, Tobias, Vijayanarasimhan, Sudheendra, Hu, Bo, Mehran, Ramin, A Ross, David 等 9 位作者

原文摘要

Video reasoning models are a core component of egocentric and embodied agents. However, standard benchmarks for assessing models provide only evaluation of the output (e.g. the answer to a question), without evaluation of inter- mediate reasoning steps, and most provide answers only in the text domain. We introduce Minerva-Ego, a bench- mark for evaluating complex egocentric visual reasoning. We extend recent high-quality video data sources recorded from egocentric / embodied settings with a set of challenging, multi-step multimodal questions and spatiotemporally-dense human-annotated reasoning traces. Benchmarking experiments show that state-of-the-art models still have a large gap to human performance. To investigate this gap in detail, we annotate each reasoning trace in the dataset with the objects of interest required to solve the question, as spatio-temporal mask annotations. Through extensive evaluations, we identify that prompting frontier models with hints of 'where' and when to look yields substantial improvements in performance.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c4b36780bb3abce6b9e54bcadc20b618CVF · CVPR 2026

UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models

Pan, Hewen, Wei, Cong, Liang, Dashuang, Huang, Zepeng, Gao, Pengfei, Zhou, Ziqi, Xue, Lulu, Yan, Pengfei 等 11 位作者

原文摘要

With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding tasks, failing to achieve a comprehensive and multi-grained video perception. To bridge this gap, we introduce UFVideo, the first Video LLM with unified multi-grained cooperative understanding capabilities. Specifically, we design unified visual-language guided alignment to flexibly handle video understanding across global, pixel and temporal scales within a single model. UFVideo dynamically encodes the visual and text inputs of different tasks and generates the textual response, temporal localization, or grounded mask. Additionally, to evaluate challenging multi-grained video understanding tasks, we construct the UFVideo-Bench consisting of three distinct collaborative tasks within the scales, which demonstrates UFVideo's flexibility and advantages over GPT-4o. Furthermore, we validate the effectiveness of our model across 9 public benchmarks covering various common video understanding tasks, providing valuable insights for future Video LLMs.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c4d9415525c2efc69f33613e67aadd03CVF · CVPR 2026

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

Liu, Haozhe, Liu, Ding, Zhuge, Mingchen, Zhou, Zijian, Xie, Tian, He, Sen, Yang, Yukang, Liu, Shuming 等 19 位作者

原文摘要

We introduce MoS (Mixture of States), a novel fusion paradigm for multimodal diffusion models that merges modalities using flexible, state-based interactions. The core of MoS is a learnable, token-wise router that creates denoising timestep- and input-dependent interactions between modalities' hidden states, precisely aligning token-level features with the diffusion trajectory. This router sparsely selects the top-k hidden states and is trained with an epsilon-greedy strategy, efficiently selecting contextual features with minimal learnable parameters and negligible computational overhead. We validate our design with text-to-image generation (MoS-Image) and editing (MoS-Editing), which achieve state-of-the-art results. With only 3B to 5B parameters, our models match or surpass counterparts up to 4xlarger. These findings establish MoS as a flexible and compute-efficient paradigm for scaling multimodal diffusion models. The project homepage is available at https://haozheliu-st.github.io/mos-homepage/

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c4eceffbf106a32b61a4ac0bb0eeb144CVF · CVPR 2026

Masked-Diffusion Autoencoders for 3D Medical Vision Representation Learning

Tu, Jiachen, Qin, Guanghui, Zhao, Theodore Zhengde, Valanarasu, Jeya Maria Jose, Zhang, Sheng, Naumann, Tristan, Lam, Fan, Wang, Sheng 等 9 位作者

原文摘要

Effective medical image analysis requires representations that capture both global anatomical structure and fine-grained tissue texture. Current self-supervised approaches exhibit limited capacity to address both requirements simultaneously. Invariance-based methods learn through augmentation consistency but face challenges in medical imaging where common augmentations may discard diagnostically relevant intensity patterns. Masked image modeling approaches employ high masking ratios to enforce holistic reasoning, yet inherently limit exposure to fine-grained texture. Recent work in general-domain vision demonstrates that generative and semantic objectives can mutually benefit each other, yet this paradigm remains unexplored for 3D medical imaging. We introduce Masked-Diffusion Autoencoders (MDAE), a self-supervised framework that imposes concurrent spatial masking and diffusion corruption, encouraging the model to learn complementary objectives: masked region reconstruction for structural coherence and visible region denoising for textural characteristics. This dual corruption enables the network to learn structure-texture representations within a unified time-conditioned objective. Evaluated on brain MRI across tumor classification, molecular marker detection, and dense segmentation benchmarks, MDAE consistently outperforms state-of-the-art baselines, with improvements most pronounced in cross-modal generalization tasks.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c4ed4ab303c38f4957147b62a16dca75CVF · CVPR 2026

TimeBridge: Self-Supervised Video Representation Learning via Start-End Joint Embedding and In-Between Frame Prediction

Wang, Qin, Morrison, Abigail, Scharr, Hanno, Krajsek, Kai

原文摘要

Learning temporal transformations, that is, how visual objects evolve across frames, is a fundamental challenge in video representation learning. Frame-to-frame dynamics involve complex, non-linear, and non-local changes that go far beyond conventional spatial augmentations. We propose TimeBridge, a self-supervised method that combines the joint embedding for video representation with learning temporal transformations by reconstructing in-between frames from only the start and end frames. This formulation encourages the model to infer the temporal evolution bridging the two endpoints, rather than merely encoding static frame representations. Unlike joint-embedding methods that lack explicit transformation modelling or future-prediction objectives that rely on unconstrained extrapolation, TimeBridge learns concrete frame-to-frame dynamics by promoting temporal consistency. We realise this through cross-concatenated class tokens and lightweight decoders, which recombine features from the start and end frames to reconstruct intermediates. TimeBridge achieves new state-of-the-art performance on multiple dense video prediction benchmarks, including 73.5 J&F on DAVIS 2017 video object segmentation, 47.5 mIoU on VIP semantic part propagation.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c4eef6e6f1dc5276367cab8f44d3a0bbCVF · CVPR 2026

When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters

Lyu, Liangwei, Xu, Jiaqi, Ding, Jianwei, Deng, Qiyao

原文摘要

Low-Rank Adaptation (LoRA) has emerged as a leading technique for efficiently fine-tuning text-to-image diffusion models, and its widespread adoption on open-source platforms has fostered a vibrant culture of model sharing and customization. However, the same modular and plug-and-play flexibility that makes LoRA appealing also introduces a broader attack sur-face. To highlight this risk, we propose Masquerade-LoRA (MasqLoRA), the first backdoor attack that leverages the LoRA mechanism to stealthily inject malicious behavior into text-to-image diffusion models. MasqLoRA operates by freezing the base model parameters and updating only the low-rank adapter weights using a small number of "trigger word-target image" pairs. This enables the attacker to train a standalone backdoor LoRA module that embeds a hidden cross-modal mapping: when the module is loaded and a specific textual trigger is provided, the model produces a predefined visual output; other-wise, it behaves indistinguishably from the clean model, ensuring the stealthiness of the attack. Experimental results demonstrate that MasqLoRA can be trained with minimal resource overhead and achieves a high attack success rate of 99.8%. MasqLoRA reveals a severe and unique threat in the AI supply chain, underscoring the urgent need for dedicated defense mechanisms for the LoRA-centric sharing ecosystem.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c505e14f4e19d0210d84bbb3c87e5b0dCVF · CVPR 2026

Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification

Yang, William, Wu, Xindi, Deng, Zhiwei, Tureci, Esin, Russakovsky, Olga

原文摘要

Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating synthetic training data to improve fine-grained classification performance remains challenging. Fine-tuning the T2I model with a few real examples can help generate more appropriate synthetic training data; however, this fine-tuning may also introduce overfitting and reduce diversity in the generated samples. We propose a fine-tuning strategy BOB (Beyond OBjects) for mitigating these concerns. Given a small set of real examples, we first describe them using class-agnostic attributes such as scene background and object pose. We then explicitly condition on these attributes during fine-tuning of the T2I model and marginalize them out during generation. This design mitigates overfitting, thus preserving the T2I model's generative prior and reducing estimation errors, and further minimizes unintended inter-class associations. Extensive experiments across multiple T2I models, backbones, and datasets demonstrate state-of-the-art performance in low-shot fine-grained classification when augmented with synthetic data. Concretely, BOB outperforms DataDream by 7.4% on the Aircraft dataset (from 50.0% to 57.4% when fine-tuning a CLIP classifier with 5 real images augmented with 100 synthetic images). Additionally, in three of the four datasets, the fine-tuning downstream models with synthetic data generated from BOB and five real images achieves better performance than fine-tuning with 10 real images. Collectively, BOB outperforms prior art in 18 of 24 experimental settings, with over 2% accuracy improvements in 14 of these settings.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c548a670e933ef7d919c4fb5edc2fa39CVF · CVPR 2026

ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals

Li, Xuelu, Wang, Zhaonan, Wang, Xiaogang, Wu, Lei, Li, Manyi, Tu, Changhe

原文摘要

Reconstructing articulated objects into high-fidelity digital twins is crucial for applications such as robotic manipulation and interactive simulation. Recent self-supervised methods using differentiable rendering frameworks like 3D Gaussian Splatting remain highly sensitive to the initial part segmentation. Their reliance on heuristic clustering or pre-trained models often causes optimization to converge to local minima, especially for complex multi-part objects.To address these limitations, we propose ArtPro, a novel self-supervised framework that introduces adaptive integration of mobility proposals. Our approach begins with an over-segmentation initialization guided by geometry features and motion priors, generating part proposals with plausible motion hypotheses. During optimization, we dynamically merge these proposals by analyzing motion consistency among spatial neighbors, while a collision-aware motion pruning mechanism prevents erroneous kinematic estimation. Extensive experiments on both synthetic and real-world objects demonstrate that ArtPro achieves robust reconstruction of complex multi-part objects, significantly outperforming existing methods in accuracy and stability.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c54cda0989e3e8354f507ed085dde4afCVF · CVPR 2026

Human-Centric Multi-Exposure Fusion: Benchmark and Bi-level Cognition Distillation Framework

Shang, Jingjie, Ma, Tengyu, Zhang, Heng, Liu, Jinyuan, Liu, Risheng, Wang, Yuan, Bo, Xiaochen

原文摘要

Multi-Exposure Fusion (MEF) seeks to generate a single high-quality image from multiple inputs captured at different exposure levels. Despite substantial progress, most existing approaches depend on statistical metrics that poorly reflect human perceptual preferences. Electroencephalography (EEG) provides a direct physiological window into human cognition, yet its use in low-level vision remains limited due to scarce paired data and the absence of bio-signals during inference. We address these challenges through two key contributions. First, we introduce Cog-Expo, the first dataset capturing human cognitive responses to multi-exposure stimuli, establishing a bridge between neuroscience and computational photography. Second, we propose a bi-level coupled learning framework that leverages this cognitive information without requiring it during inference. A Mental Integrated Transformer serves as the Teacher, incorporating cognitive priors to guide visual feature learning, while a lightweight Student is trained to approximate these cues using only image inputs. Through bi-level optimization, the Teacher learns inherently distillable representations, enabling the Student to emulate cognitive guidance efficiently. Extensive experiments confirm that our method achieves state-of-the-art fusion performance and aligns more closely with human perception.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c56874d4c607c644c983224cd08b10fbCVF · CVPR 2026

Describe Anything Anywhere At Any Moment

Gorlo, Nicolas, Schmid, Lukas, Carlone, Luca

原文摘要

Computer vision and robotics applications ranging from augmented reality to robot autonomy in large-scale environments require spatio-temporal memory frameworks that capture both geometric structure for accurate language-grounding and semantic detail. Existing methods face a tradeoff, where producing rich open-vocabulary descriptions comes at the expense of real-time performance when these descriptions have to be grounded in 3D. To address these challenges, we propose Describe Anything, Anywhere, at Any Moment (DAAAM), a novel spatio-temporal memory framework for large-scale and real-time 4D scene understanding. DAAAM introduces a novel optimization-based frontend to infer detailed semantic descriptions from localized captioning models, such as the Describe Anything Model (DAM), using batch processing to speed up inference by an order of magnitude for online deployment. It leverages such semantic understanding to build a hierarchical 4D scene graph (SG), which acts as an effective globally spatially and temporally consistent memory representation. DAAAM constructs 4D SGs with detailed, geometrically grounded descriptions while maintaining real-time performance. We show that DAAAM's 4D SG interfaces well with a tool-calling agent for inference and reasoning. We thoroughly evaluate DAAAM in the complex task of spatio-temporal question answering (SQA) on the NaVQA benchmark and show its generalization capabilities for sequential task grounding on the SG3D benchmark. We further curate an extended OC-NaVQA benchmark for large-scale and long-time evaluations. DAAAM achieves state-of-the-art results in both tasks, improving OC-NaVQA question accuracy by 53.6%, reducing position errors by 21.9% and temporal errors by 21.6%, and improving SG3D task grounding accuracy by 27.8% over the most competitive baselines. We release our data and code open-source.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c57873191df45b5c5327673d6920e536CVF · CVPR 2026

MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving

Wang, Junli, Zheng, Yinan, Liu, Xueyi, Xing, Zebin, Li, Pengfei, Ma, Kun, Ye, Hangjun, Chen, Guang 等 12 位作者

原文摘要

Generative models have shown great potential in trajectory planning. Recent studies demonstrate that anchor-guided generative models are effective in modeling the uncertainty of driving behaviors and improving overall performance. However, these methods rely on discrete anchor vocabularies that must sufficiently cover the trajectory distribution during testing to ensure robustness, inducing an inherent trade-off between vocabulary size and model performance.To overcome this limitation, we propose MeanFuser, an end-to-end autonomous driving method that enhances both efficiency and robustness through three key designs. (1) We introduce Gaussian Mixture Noise (GMN) to guide generative sampling, enabling a continuous representation of the trajectory space and eliminating the dependency on discrete anchor vocabularies. (2) We introduce "MeanFlow Identity", which models the mean velocity field between GMN and data distribution instead of the instantaneous velocity field used in naive flow-matching methods, effectively eliminating numerical errors from ODE solvers and significantly accelerating inference. (3) We design a lightweight Adaptive Reconstruction Module (ARM) that enables the model to consider all sampled proposals and adaptively decide whether to reconstruct a trajectory when none of the proposals is satisfactory. Experiments on the NAVSIM closed-loop benchmark demonstrate that MeanFuser achieves outstanding performance and exceptional inference efficiency, offering a robust and efficient solution for end-to-end autonomous driving.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c5917f0006de93deb1a794175293a52eCVF · CVPR 2026

Distilling Unsigned Distance Function for Surface Reconstruction from 3D Gaussian Splatting

Li, Qian, Fu, Rao, Li, Jiangtao, Liu, Fan

原文摘要

Unsigned distance fields (UDFs) are well suited for representing open surfaces, but learning them from multi-view images is challenging because ground-truth surfaces are unavailable for supervision in most cases and the gradient of a UDF is undefined on the underlying surface. Prior methods optimize UDFs with global objectives and apply gradient-based priors ignoring the non-differentiability for queries on the target surface, which leads to unstable training and over-smoothing on fine details. We address these issues by distilling a patch-based UDF prior, trained on synthetic ground truth algebraic surfaces with closed form expressions, into a lightweight student UDF inside Gaussian optimization process. We design band-limited knowledge distillation strategy that leverages a pretrained patch-based UDF predictor to provide reliable near-surface UDF supervision, enabling stable student training and the recovery of high-frequency geometric details. In addition, we introduce a visibility- and geometry-aware confidence weighting that modulates teacher influence, further steering the student toward accurate surfaces in ambiguous or weakly constrained regions. Extensive experiments on various datasets demonstrate that our approach consistently improves reconstruction accuracy while maintaining competitive efficiency compared to existing UDF- and SDF-based methods.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c5df474c1117b6ec9049d343e829d8aeCVF · CVPR 2026

The Midas Touch for Metric Depth

Ma, Yu, Guo, Zizhan, Xiong, Zuyi, Zhang, Haoran, Feng, Yi, Zhao, Hongbo, Wang, Hanli, Fan, Rui

原文摘要

Recent advances have markedly improved the cross-scene generalization of relative depth estimation, yet its practical applicability remains limited by the absence of metric scale, local inconsistencies, and low computational efficiency. To address these issues, we present Midas Touch for Depth (MTD), a mathematically interpretable approach that converts relative depth into metric depth using only extremely sparse 3D data. To eliminate local scale inconsistencies, it applies a segment-wise recovery strategy via sparse graph optimization, followed by a pixel-wise refinement strategy using a discontinuity-aware geodesic cost. MTD exhibits strong generalization and achieves substantial accuracy improvements over previous depth completion and depth estimation methods. Moreover, its lightweight, plug-and-play design facilitates deployment and integration on diverse downstream 3D tasks.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c5e6288fb10796cfeb3635435f486d83CVF · CVPR 2026

Rethinking Concept Bottleneck Models: From Pitfalls to Solutions

Tapli, Merve, Bouniot, Quentin, Stammer, Wolfgang, Akata, Zeynep, Akbas, Emre

原文摘要

Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts but face fundamental limitations: the absence of a metric to pre-evaluate concept relevance, the "linearity problem" causing recent CBMs to bypass the concept bottleneck entirely, an accuracy gap compared to opaque models, and finally the lack of systematic study on the impact of different visual backbones and VLMs. We introduce CBM-Suite, a methodological framework to systematically addresses these challenges. First, we propose an entropy-based metric to quantify the intrinsic suitability of a concept set for a given dataset. Second, we resolve the linearity problem by inserting a non-linear layer between concept activations and the classifier, which ensures that model accuracy faithfully reflects concept relevance. Third, we narrow the accuracy gap by leveraging a distillation loss guided by a linear teacher probe. Finally, we provide comprehensive analyses on how different vision encoders, vision-language models, and concept sets interact to influence accuracy and interpretability in CBMs. Extensive evaluations show that CBM-Suite yields more accurate models and provides insights for improving concept-based interpretability.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c5f1cef7baf159147c54741549eba9ddCVF · CVPR 2026

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers

Xiao, Chaodong, Zhang, Zhengqiang, Zhang, Lei

原文摘要

Transformers have achieved widespread and remarkable success, while the computational complexity of their attention modules remains a major bottleneck for vision tasks. Existing methods mainly employ 8-bit or 4-bit quantization to balance efficiency and accuracy. In this paper, with theoretical justification, we indicate that binarization of attention preserves the essential similarity relationships, and propose BinaryAttention, an effective method for fast and accurate 1-bit qk-attention. Specifically, we retain only the sign of queries and keys in computing the attention, and replace the floating dot products with bit-wise operations, significantly reducing the computational cost. We mitigate the inherent information loss under 1-bit quantization by incorporating a learnable bias, and enable end-to-end acceleration. To maintain the accuracy of attention, we adopt quantization-aware training and self-distillation techniques, mitigating quantization errors while ensuring sign-aligned similarity. BinaryAttention is more than 2xfaster than FlashAttention2 on A100 GPUs. Extensive experiments on vision transformer and diffusion transformer benchmarks demonstrate that BinaryAttention matches or even exceeds full-precision attention, validating its effectiveness. Our work provides a highly efficient and effective alternative to full-precision attention, pushing the frontier of low-bit transformers for vision tasks. The codes and models can be found at https://github.com/EdwardChasel/BinaryAttention.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c5f50101bd9748775400bb789c6fc33aCVF · CVPR 2026

Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory

Qi, Yu, Li, Hongyu, Huang, Shaofei, Hui, Tianrui, Wang, Yaxiong, Cheng, Lechao, Zhong, Zhun, Liu, Si 等 9 位作者

原文摘要

In this paper, we tackle the Aerial Vision-and-Dialog Navigation (AVDN) task in the training-free setting for resource-efficient high-altitude UAV navigation.Naively applying MLLMs leads to unreliable navigation due to weak directional grounding and the lack of explicit spatial memory.To address these issues, we propose PSC-AVDN, a training-free framework that tightly couples a three-stage Parsing-Search-Confirmation reasoning pipeline with a Structured Spatial Memory (SSM).The parsing stage uses an LLM to convert ambiguous dialogue instructions into stable geometric directional and destination cues.A Search Chain-of-Thought (S-CoT) then performs stepwise target exploration under high-altitude observations, and a Confirmation Chain-of-Thought (C-CoT) conducts fine-grained verification around candidate regions to resolve visual ambiguity.Meanwhile, SSM integrates three complementary sources of spatial cues, including multi-scale visual observation, spatial visual memory, and structured geometric memory to provide global spatial context and long-horizon consistency.Extensive experiments on ANDH and ANDH-Full show that PSC-AVDN establishes new state-of-the-art performance in the training-free setting, matching or surpassing several finetuned methods.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c60639ec7eca8dbe81c33a2ceffa940aCVF · CVPR 2026

Is the Modality Gap a Bug or a Feature? A Robustness Perspective

Chowers, Rhea, Naparstek, Oshri, Barzelay, Udi, Weiss, Yair

原文摘要

Many modern multi-modal models (e.g. CLIP) seek an embedding space in which the two modalities are aligned. Somewhat surprisingly, almost all existing models show a strong modality gap: the distribution of images is well-separated from the distribution of texts in the shared embedding space. Despite a series of recent papers on this topic, it is still not clear why this gap exists nor whether closing the gap in post-processing will lead to better performance on downstream tasks. In this paper we show that under certain conditions, minimizing the contrastive loss will lead to a representation in which the two modalities are separated by a global gap vector that is orthogonal to the embeddings of both modalities. We also show that under these conditions the modality gap is monotonically related to robustness: decreasing the gap does not change the clean accuracy of the models but makes it less likely that a model will change its output when small, semantically inconsequential changes are made to the input. Our experiments show that for many real-world VLMs we can significantly increase robustness by a simple post-processing step that moves one modality towards the mean of the other modality, without any loss to clean accuracy.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c60a930a83f4d6b13153aa87d2a35e3dCVF · CVPR 2026

FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories

Ke, Lei, Yin, Hubery, Liu, Gongye, Lv, Zhengyao, Guo, Jingcai, Li, Chen, Luo, Wenhan, Yang, Yujiu 等 9 位作者

原文摘要

With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical consistency with flow matching. This is primarily due to its suboptimal performance in practical scenarios compared to consistency distillation and score distillation. In this work, we investigate this issue within the ReFlow framework and propose FlowSteer, a method unlocks the potential of ReFlow-based distillation by guiding the student along teacher's authentic generation trajectories. We first identify that Piecewised ReFlow's performance is hampered by a critical distribution mismatch during the training and propose Online Trajectory Alignment(OTA) to resolve it. Then, we introduce a adversarial distillation objective applied directly on the ODE trajectory, improving the student's adherence to the teacher's generation trajectory. Furthermore, we find and fix a previously undiscovered flaw in the widely-used \texttt FlowMatchEulerDiscreteScheduler that largely degrades few-step inference quality. Our experiment result on SD3 demonstrates our method's efficacy.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c61abd234359ca758f4e8edf20b4185bCVF · CVPR 2026

OneHOI: Unifying Human-Object Interaction Generation and Editing

Hoe, Jiun Tian, Hu, Weipeng, Jiang, Xudong, Tan, Yap-Peng, Chan, Chee Seng

原文摘要

Human-Object Interaction (HOI) modelling captures how humans act upon and relate to objects, typically expressed as triplets. Existing approaches split into two disjoint families: HOI generation synthesises scenes from structured triplets and layout, but fails to integrate mixed conditions like HOI and object-only entities; and HOI editing modifies interactions via text, yet struggles to decouple pose from physical contact and scale to multiple interactions. We introduce OneHOI, a unified diffusion transformer framework that consolidates HOI generation and editing into a single conditional denoising process driven by shared structured interaction representations. At its core, the Relational Diffusion Transformer (R-DiT) models verb-mediated relations through role- and instance-aware HOI tokens, layout-based spatial Action Grounding, a Structured HOI Attention to enforce interaction topology, and HOI RoPE to disentangle multi-HOI scenes. Trained jointly with modality dropout on our HOI-Edit-44K, along with HOI and object-centric datasets, OneHOI supports layout-guided, layout-free, arbitrary-mask, and mixed-condition control, achieving state-of-the-art results across both HOI generation and editing.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c636adc89f98f3aa3e48aa4562f1d74eCVF · CVPR 2026

AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generation

Girish, Sharath, Ivanov, Viacheslav, Chen, Tsai-Shien, Chen, Hao, Siarohin, Aliaksandr, Tulyakov, Sergey

原文摘要

Recent advances in subject-driven video generation with large diffusion models have enabled personalized content synthesis conditioned on user-provided subjects. However, existing methods lack fine-grained temporal control over subject appearance and disappearance, which are essential for applications such as compositional video synthesis, storyboarding, and controllable animation. We propose AlcheMinT, a unified framework that introduces explicit timestamps conditioning for subject-driven video generation. Our approach introduces a novel positional encoding mechanism that unlocks the encoding of temporal intervals, associated in our case with subject identities, while seamlessly integrating with the pretrained video generation model positional embeddings. Additionally, we incorporate subject-descriptive text tokens to strengthen binding between visual identity and video captions, mitigating ambiguity during generation. Through token-wise concatenation, AlcheMinT avoids any additional cross-attention modules and incurs negligible parameter overhead. We establish a benchmark evaluating multiple subject identity preservation, video fidelity, and temporal adherence. Experimental results demonstrate that AlcheMinT achieves visual quality matching state-of-the-art video personalization methods, while, for the first time, enabling precise temporal control over multi-subject generation within videos.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c64927e6d7e0d810b7c58d51e692e589CVF · CVPR 2026

MR-RAG: Multimodal Relevance-Aware Retrieval-Augmented Generation for Medical Visual Question Answering

Li, Xuze, Wang, Haozhao, Huang, Zhenyu, Wang, Zhongxu, Zhang, Jinghua, Li, Ruixuan

原文摘要

Large Vision Language Models (LVLMs) with retrieval-augmented generation (RAG) are emerging as a main paradigm for processing vision-language medical tasks due to their promising achievements. However, existing approaches exhibit two significant limitations in both retrieval and generation stage: First, during the retrieval stage, most methods typically rely on a single similarity signal to estimate document relevance, ignoring the rich information available in multimodal data, which may fail to accurately retrieve matching content. Second, in the generation stage, retrieved documents are integrated directly and uniformly into the input for LVLMs, without taking into account their varying relevance to the question, which may result in the dilution of crucial information and exacerbate the negative impact of irrelevant content. To address these limitations, we propose MR-RAG, a dual-stage RAG enhancement framework by considering multimodal relevance in both retrieval and generation phases. Specifically, a Multimodal Cooperative Retrieval (MCR) module leverages intra- and cross-modal signals for precise document alignment. Subsequently, an Importance-Aware Information Flow Augmentation (IFA) mechanism adjusts attention paths based on fused relevance to refine answer generation. By bridging retrieval and generation via multimodal signals, MR-RAG significantly improves factual accuracy. Experiments on three medical datasets show our method outperforms state-of-the-art baselines, achieving up to a 6.4% accuracy gain.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6924010c9514aff362ac2d6c5b2d177CVF · CVPR 2026

CASPA: Graph-Structured Concept Anchors for Modality-Agnostic Adaptation in Vision-Language Models

Chatterjee, Abhiroop, Ghosh, Susmita, Ghosh, Ashish, Ientilucci, Emmett

原文摘要

Recent advances in vision-language models (VLMs) have revealed both the promise and the rigidity of large-scale pretraining. Despite their impressive zero-shot generalization, existing adaptation paradigms--whether prompt-tuning, adapter injection, or fine-tuning--remain class-specific, modality-biased, and structure-agnostic. However, these design choices limit reasoning-level transfer across tasks. To this end, we rethink adaptation as a shared conceptual structure rather than a per-class specialization. We propose CASPA (Concept-Anchored Semantic Prompt Adapter), a dual-anchor semantic adapter that jointly learns shared text and image anchors as a bidirectional conceptual interface between modalities. Each class learns a soft association distribution over these anchors, producing compositional representations which enable parameter sharing and semantic reuse. To further align visual and textual reasoning spaces, CASPA employs Semantic Cross-Consistency Regularization (S-XCR), enforcing geometric and semantic agreement between text- and image-conditioned anchor mixtures. CASPA, therefore, provides a structurally constrained alternative to class-conditional prompt parameterization while keeping the CLIP backbone frozen. Evaluated across four regimes, Base-to-Novel setup, cross-data transfer, few-shot, and backbone-agnostic evaluations, on eleven diverse visual recognition datasets, CASPA matches or outperforms state-of-the-art methods.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6bae4c1f18f06019d98897cc8e9583cCVF · CVPR 2026

Decoupled Generative Modeling for Human-Object Interaction Synthesis

Jung, Hwanhee, Lee, Seunggwan, Yoon, Jeongyoon, Kim, SeungHyeon, Nam, Giljoo, Huang, Qixing, Kim, Sangpil

原文摘要

Synthesizing realistic human-object interaction (HOI) is essential for 3D computer vision and robotics, underpinning animation and embodied control. Existing approaches often require manually specified intermediate waypoints and place all optimization objectives on a single network, which increases complexity, reduces flexibility, and leads to errors such as unsynchronized human and object motion or penetration. To address these issues, we propose Decoupled Generative Modeling for Human-Object Interaction Synthesis (DecHOI), which separates path planning and action synthesis. A trajectory generator first produces human and object trajectories without prescribed waypoints, and an action generator conditions on these paths to synthesize detailed motions. To further improve contact realism, we employ adversarial training with a discriminator that focuses on the dynamics of distal joints. The framework also models a moving counterpart and supports responsive, long-sequence planning in dynamic scenes, while preserving plan consistency. Across two benchmarks, FullBodyManipulation and 3D-FUTURE, DecHOI surpasses prior methods on most quantitative metrics and qualitative evaluations, and perceptual studies likewise prefer our results.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6bd237f15814480e40853d72fccc293CVF · CVPR 2026

How to Take a Memorable Picture? Empowering Users with Actionable Feedback

Laiti, Francesco, Talon, Davide, Staiano, Jacopo, Ricci, Elisa

原文摘要

Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual input to boost the image likelihood of being remembered. Yet, none of these paradigms supports users at capture time, when the crucial question is how to improve a photo memorability. We introduce the task of **Mem**orability **Feed**back (**MemFeed**), where an automated model should provide actionable, human-interpretable guidance to users with the goal to enhance an image future recall. We also present **MemCoach**, the first approach designed to provide concrete suggestions in natural language for memorability improvement (e.g., "emphasize facial expression," "bring the subject forward"). Our method, based on Multimodal Large Language Models (MLLMs), is training-free and employs a teacher-student steering strategy, aligning the model internal activations toward more memorable patterns learned from a teacher model progressing along least-to-most memorable samples. To enable systematic evaluation on this novel task, we further introduce **MemBench**, a new benchmark featuring sequence-aligned photoshoots with annotated memorability scores. Our experiments, considering multiple MLLMs, demonstrate the effectiveness of MemCoach, showing consistently improved performance over several zero-shot models. The results indicate that memorability can not only be predicted but also taught and instructed, shifting the focus from mere prediction to actionable feedback for human creators. Dataset and code will be publicly released upon publication.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6be36e1387780916208433093c7836bCVF · CVPR 2026

Intra-class Distribution-guided Generative Hashing with Neighbor Refinement for Cross-modal Retrieval

Sun, Hao, Huo, Yadong, Qin, Qibing, Zhang, Wenfeng, Huang, Lei

原文摘要

Recent cross-modal hashing methods have introduced sample generation strategies to enrich training signals. Despite these advances, sample generation-driven hashing still faces two major challenges: (1) Interpolation-based methods adopt deterministic and class-independent generation that restricts synthetic samples to a small region around the original data. Consequently, intra-class diversity is limited, which weakens the model's ability to learn discriminative binary codes. (2) Generation network-based methods, which leverage a complex generative model to produce synthetic samples, leading to extra model complexity. To address these issues, we propose a novel Intra-class Distribution-guided Generative Hashing (IDGH) that adaptively generates synthetic samples directly from estimated intra-class distributions. Specifically, we suggest an Intra-class Distribution Estimation (IDE) scheme to model the characteristic distribution of each class, providing essential support for adaptive sample generation. Meanwhile, by utilizing the distribution information from neighboring classes, we design a Neighbor-guided Distribution Refinement (NDR) mechanism to correct flawed estimations for classes. With refined intra-class distributions, we propose a Distribution-aware Adaptive Generation (DAG) strategy that synthesizes informative training samples by shifting features along diverse directions guided by intra-class distribution patterns. The proposed approach is plug-and-play and can be seamlessly integrated into various objective functions, providing semantically diverse training samples, thus enhancing similarity learning. Extensive experiments on benchmark datasets demonstrate that IDGH outperforms existing methods. Code is available at https://github.com/QinLab-WFU/IDGH.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6c3ffdebb1193318052f413e96b3f77CVF · CVPR 2026

EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models

Song, Mingchen, Deng, Xiang, Wei, Jie, Jiang, Dongmei, Nie, Liqiang, Guan, Weili

原文摘要

Recent advances in unimanual manipulation policies have achieved remarkable success across diverse robotic tasks through abundant training data and well-established model architectures. However, extending these capabilities to bimanual manipulation remains challenging due to the lack of bimanual demonstration data and the complexity of coordinating dual-arm actions. Existing approaches either rely on extensive bimanual datasets or fail to effectively leverage pre-trained unimanual policies. To address this limitation, we propose EnergyAction, a novel framework that compositionally transfers unimanual manipulation policies to bimanual tasks through the Energy-Based Models (EBMs). Specifically, our method incorporates three key innovations. First, we model individual unimanual policies as EBMs and leverage their compositional properties to compose left and right arm actions, enabling the fusion of unimanual policies into a bimanual policy. Second, we introduce an energy-based temporal-spatial coordination mechanism through energy constraints, ensuring the generated bimanual actions are both temporal coherence and spatial feasibility. Third, we propose two different energy-aware denoising strategies that dynamically adapt denoising steps based on action quality assessment. These strategies ensure the generation of high-quality actions while maintaining superior computational efficiency compared to fixed-step denoising approaches. Experimental results demonstrate that EnergyAction effectively transfers unimanual knowledge to bimanual tasks, achieving superior performance on both simulated and real-world tasks with minimal bimanual data.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6c42d2dcff8a3b785b1f8f3f673d3fdCVF · CVPR 2026

Envisioning the Future, One Step at a Time

Baumann, Stefan Andreas, Wiese, Jannik, Martorella, Tommaso, Kalayeh, Mahdi M., Ommer, Björn

原文摘要

Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains, and efficiently explore many plausible futures. Yet most existing approaches rely on dense video or latent-space prediction, expending substantial capacity on dense appearance rather than on the underlying sparse trajectories of points in the scene. This makes large-scale exploration of future hypotheses costly and limits performance when long-horizon, multi-modal motion is essential. We address this by formulating the prediction of open-set future scene dynamics as step-wise inference over sparse point trajectories. Our autoregressive diffusion model advances these trajectories through short, locally predictable transitions, explicitly modeling the growth of uncertainty over time. This dynamics-centric representation enables fast rollout of thousands of diverse futures from a single image, optionally guided by initial constraints on motion, while maintaining physical plausibility and long-range coherence. We further introduce OWM, a benchmark for open-set motion prediction based on diverse in-the-wild videos, to evaluate accuracy and variability of predicted trajectory distributions under real-world uncertainty. Our method matches or surpasses dense simulators in predictive accuracy while achieving orders-of-magnitude higher sampling speed, making open-set future prediction both scalable and practical.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6d886b5ccce7d011433c2f64c5095e6CVF · CVPR 2026

MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment

Nguyen, Duc Duy, Chin, Tat-Jun, Hoai, Minh

原文摘要

We aim to learn a joint representation between inertial measurement unit (IMU) signals and 2D pose sequences extracted from video, enabling accurate cross-modal retrieval, temporal synchronization, subject and body-part localization, and action recognition. To this end, we introduce MoBind, a hierarchical contrastive learning framework designed to address three challenges: (1) filtering out irrelevant visual background, (2) modeling structured multi-sensor IMU configurations, and (3) achieving fine-grained, sub-second temporal alignment. To isolate motion-relevant cues, MoBind aligns IMU signals with skeletal motion sequences rather than raw pixels. We further decompose full-body motion into local body-part trajectories, pairing each with its corresponding IMU to enable semantically grounded multi-sensor alignment. To capture detailed temporal correspondence, MoBind employs a hierarchical contrastive strategy that first aligns token-level temporal segments, then fuses local (body-part) alignment with global (body-wide) motion aggregation. Evaluated on mRi, TotalCapture, and EgoHumans, MoBind consistently outperforms strong baselines across all four tasks, demonstrating robust fine-grained temporal alignment while preserving coarse semantic consistency across modalities.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c6f97a7291f141ee8beb330cec2f3d37CVF · CVPR 2026

Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation

You, Yuyang, Li, Yongzhi, Li, Jiahui, Mu, Yadong, Chen, Quan, Jiang, Peng

原文摘要

Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite its significance, there is a scarcity of methods specifically designed for video diffusion models. Prevailing approaches often directly adapt image distillation techniques, which frequently lead to artifacts such as oversaturation, temporal inconsistency, and mode collapse. To address these challenges, we propose a novel distillation framework tailored specifically for video diffusion models. Its core innovations include: (1) an adaptive regression loss that dynamically adjusts spatial supervision weights to prevent artifacts arising from excessive distribution shifts; (2) a temporal regularization loss to counteract temporal collapse, promoting smooth and physically plausible sampling trajectories; and (3) an inference-time frame interpolation strategy that reduces sampling overhead while preserving perceptual quality. Extensive experiments and ablation studies on the VBench and VBench2 benchmarks demonstrate that our method achieves stable few-step video synthesis, significantly enhancing perceptual fidelity and motion realism. It consistently outperforms existing distillation baselines across multiple metrics.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:c7222eeb2980cdb1157e680e1d9f5202CVF · CVPR 2026

UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm

Kan, Zhehan, Jiang, Xinghua, Liu, Yanlin, Yang, Xiaochen, Wei, Zhixiang, Liu, Shifeng, Zhu, Yubo, Liao, Qingmin 等 13 位作者

原文摘要

Despite remarkable advancements in multimodal large language models (MLLMs), their fine-grained visual understanding is constrained by a primary reliance on sparse textual supervision. Existing efforts to introduce visual supervision typically do so during post-training, when visual representations have already been largely fixed, causing such signals to act mainly as auxiliary constraints rather than as a primary force for shaping perceptual features. In this paper, we aim to fundamentally reshape the model's perceptual backbone by incorporating vision supervision directly into the pre-training stage. We observe that pixel-level image patches and textual tokens naturally coexist in a shared, raw high-dimensional space characterized by an inherent input symmetry. Leveraging this insight, we propose UVU, a novel vision-language unified autoregressive framework that eschews vector quantization. It uniquely employs continuous visual encoding for lossless representation of visual inputs and proposes a large-scale iterative hierarchical clustering algorithm to construct a pixel-level visual codebook, thereby extending the vocabulary for unified supervision and enabling autoregressive generation of pixel-level image tokens alongside textual tokens. UVU effectively synergizes pixel-level visual perception with semantic-level visual understanding, internalizing visual reconstruction capabilities and unlocking the facilitative role of visual supervision in enhancing understanding in the pre-training stage. Extensive experiments across multiple tasks demonstrate that MLLMs are capable of achieving superior multimodal understanding performance under the supervised learning paradigm of UVU.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗