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

Ablation-Corrected Evaluation of Attribution Maps in Echocardiographic Ejection-Fraction Models

Hyunkyung Han, Min Jung Kim

Attribution maps for echocardiographic ejection-fraction models are evaluated by their overlap with an expert left-ventricular annotation, compared against a chance level that is computed from an area ratio rather than measured. We measure it. Two architectures trained on the same task attain overlap at 3.55 and 4.20 times measured chance, an eighteen percent difference a reader would take as the size of the gap between them. It is not. Replacing the annotated ventricle with a composition-matched surrogate changes one model's prediction six times more than replacing an equal-area control region and the other's twice, a factor of three; on sixty-two percent of cases for the second, neither the ventricle nor the attributed region moves the prediction at all. The reliability of this measurement, from two independent intervention batches, is 0.90 to 0.98. Overlap does not track the difference: scored against an ablation-derived label of which cases the model depends on the ventricle for, it reaches an area under the curve of 0.52 and 0.67. The design of the ablation also determines its answer, since ablating only the two annotated frames leaves the ventricle indistinguishable from a control region while ablating across all frames does not. A pediatric cohort reproduces all of these. We give the measured chance level, the symmetric-ablation protocol, the reliability estimate, and the ablation-prediction score as things to report alongside overlap.

arXiv

Fine-grained CLIP fine-tuning with self-annotated region alignment

Chenyang Zhao, Wei Lin, Janet H. Hsiao, Antoni B. Chan

Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme. However, existing works suffer from a variety of limitations: additional region annotations are usually required, which limits the semantic diversity due to the predefined categories and leads to a large effort to process the training data; and they usually sacrifice CLIP's original ability for global visual representation. To bypass these limitations, we propose SFF-CLIP (Self-annotated Fine-grained Fine-tuning for CLIP), which only uses image-text pairs as input to boost the fine-grained representation ability in the CLIP fine-tuning, while maintaining the global visual-semantic consistency. Concretely, a run-time region-phrase alignment scheme is designed, which obtains concept phrases from the input sentence, and aligns them with corresponding extracted region-based features using text-specific heat maps. Extensive experiments demonstrate that SFF-CLIP leads to significant performance improvements on fine-grained dense feature representation, as well as maintaining the performance of the original CLIP on image-level tasks. Code will be released later.

arXiv

MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs

Hantao Zhang, Jinru Sui, Ed Li, Dirk Bergemann, Zhuoran Yang

Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model. We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension. Unlike existing datasets that focus on pixel-level mapping or camera-relative navigation, MultiView-Bench requires models to decouple object positioning from transient perspectives and ground them in a fixed global coordinate system. This capability serves as a prerequisite for VLMs before being deployed for downstream tasks such as mechanical part assembly. Our systematic evaluation of frontier VLMs reveals consistent failure modes: strong performance on 2D planar relations from a single image, but marked difficulty with 3D spatial relations and with aggregating information across views. We further identify biases in VLMs, such as struggles with unconventional axis directions and sensitivity to object colorways and texture variations. Acknowledging these limitations, we propose ViewNavigator, which uses active viewpoint selection and evidence fusion to improve four base models by 12.3--20.0 percentage points under a six-image cap matching the fixed-view baseline; budget-extended gains are model-dependent and reach 27 percentage points for GPT-5.

arXiv

Cardiac MRI Through-Plane Super-Resolution Guided by Reference and Memory

Shaoming Pan, Chenchuhui Hu, Leon Axel, Meng Ye

Clinical cardiac MRI is commonly acquired with high in-plane resolution but coarse through-plane resolution to reduce scan time and accommodate breath-hold and cardiac-motion constraints, which limits 3D analysis and diagnostic accuracy. We propose STRMSR, a reference- and memory-guided through-plane super-resolution (SR) framework that reconstructs high-resolution (HR) cardiac volumes by leveraging HR reference views acquired from the same subject and intermediate SR results as the memory. Our method uses coarse-to-fine contextual matching to establish robust correspondence between low-resolution target and reference/memory images under spatial misalignment. A learnable patch-wise dynamic feature aggregation module predicts content-adaptive mixture weights for each local patch, effectively fusing dynamic information while suppressing unreliable feature transfers. The intermediate SR results stored in the memory bank ensure slice-to-slice consistency for the super-resolved 3D volume. Experiments on the WHS cardiac MRI dataset under two reference protocols, orthogonal-plane views and long-axis chamber views, demonstrate consistent improvements over baselines at 4x and 8x upsampling factors.Code is available at https://github.com/030108ming/STRMSR

arXiv

EventCoT: Event-centric Video Chain-of-thought for Reasoning Temporal Localization

Youngkil Song, Yoonjae Baek, Dongwon Kim, Inho Kim, Dongkeun Kim, Suha Kwak

Reasoning temporal localization (RTL) requires a model to generate an answer that itself contains the time interval supporting it, coupling high-level reasoning with temporal grounding in a single response. To tackle this challenge, we propose the first event-centric video chain-of-thought framework, dubbed EventCoT. EventCoT first performs event-centric tokenization, converting the video into compact event tokens that enable efficient identification of question-relevant events. It then reasons within these events to generate the answer, grounding the time interval via embedding matching that aligns placeholder tokens with visual embeddings. EventCoT achieves state-of-the-art results on ActivityNet-RTL while using substantially fewer visual tokens than previous work, and attains strong zero-shot results on the grounded video question answering benchmark ReXTime. Our code will be released for research purposes.

arXiv

The Calibrated Deepfake Trust Score (CDTS): Competence-Coupled Trust Degradation Across Deepfake Detectors

Md Anas Biswas

In moderation, provenance, and verification pipelines a deepfake detector's output probability is read as a degree of trust, so its calibration matters as much as raw accuracy. We reframe deepfake detection as a calibrated, self-auditing trust instrument, the Calibrated Deepfake Trust Score (CDTS), and identify what governs its trustworthiness. Our central finding is a competence-trust coupling with a sharp division: the raw score's miscalibration tracks discriminative competence almost perfectly (r = -0.98, -0.98, -0.95 across two convolutional networks and a CLIP vision transformer), and a calibrator deployed without target labels fails with competence just as tightly (r = -0.98 on the primary detector, for isotonic, Platt, and beta calibrators alike). Given target labels, by contrast, any well-specified calibrator repairs any detector, including inverted ones: in-domain calibratability is not competence-limited, and the trust failure is a distribution-shift phenomenon concentrated exactly on the low-competence generators that motivate deployment. Explanation faithfulness rises and falls on the same competence axis. We reach this conclusion after uncovering, and correcting, a tie-handling degeneracy in the standard equal-mass expected-calibration-error (ECE) estimator that fabricates strong spurious competence-calibration coupling on tie-heavy calibrated scores; the same degeneracy invalidates calibration-equity gaps we previously reported, a caution for fairness auditing. Competence is trackable without labels: batch predictive entropy flags generators with high deployed calibration error at ROC-AUC 0.99, and routing source-batches on label-free competence beats confidence-based routing precisely in the low-competence regimes the coupling identifies, while confidence regains the advantage where competence is high. Trust scoring must be competence-aware; CDTS is the mechanism.

arXiv

TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution

Xiang Gao, Chenxin Zhu, Yushun Fang, Qiang Hu, Xiaoyun Zhang

Diffusion models excel in Real-World Image Super-Resolution (Real-ISR) due to their powerful generative priors but suffer from slow iterative sampling. Although existing one-step distillation methods accelerate inference, they typically require auxiliary teacher models that inflate training memory and restrict scalability to large-scale architectures. Furthermore, these fixed-step models lack the flexibility to trade off speed for quality. In this paper, we propose TEASR, a training-efficient any-step diffusion framework for Real-ISR that enables both one-step and multi-step restoration within a unified model. Our key idea is to perform self-adversarial distillation within a single diffusion model, eliminating the need for auxiliary teachers or discriminators. Specifically, we propose a timestep-aware rectification strategy that stabilizes one-step generation across noise levels. These two designs further enables the distillation of 20B-parameter diffusion models on a single GPU, significantly improving training efficiency. Moreover, we introduce a dual-branch diffusion transformer with decoupled timestep condition to separate the current noise state and the denoising target to enhance sampling quality. Extensive experiments demonstrate that TEASR supports seamless any-step sampling and consistently outperforms state-of-the-art methods across multiple datasets.

arXiv

DIMOS: Disentangling Instance-level Moving Object Segmentation

Hongxiang Huang, Hongwei Ren, Xiaopeng LIN, Yulong Huang, Zeke Xie, Bojun Cheng

Moving instance segmentation (MIS) attracts increasing attention due to its broad applications in traffic surveillance, autonomous driving, and animal tracking. Event cameras record asynchronous brightness changes, providing high temporal resolution and dynamic range, which makes them highly sensitive to motion information. By fusing event and image features, motion cues from events can complement spatial details from images, enhancing the performance of MIS. However, current multimodal MIS methods still struggle to segment small moving instances, as event cameras often yield sparse features under limited resolution. Moreover, event features entangle appearance attributes with motion cues, which further restricts effective cross-modal fusion. To address these challenges, we first propose a dual-disentangling feature extraction framework that separates and extracts appearance and motion information within both image and event modalities, thereby improving feature density. Subsequently, a multi-granularity cross-modal alignment is introduced to align distributionally and semantically consistent features across modalities, enabling more effective fusion with rich spatial and temporal details. The experiment results demonstrate that our method achieves state-of-the-art performance in multimodal MIS, especially for small instances under challenging conditions such as fast motion and low-light settings.

arXiv

Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models

Hashmat Shadab Malik, Muzammal Naseer, Salman Khan

Vision-language models (VLMs) such as CLIP show strong zero-shot generalization but remain highly vulnerable to adversarial attacks. Adversarial training improves robustness but is computationally expensive, motivating test-time defenses. Recent approaches exploit how CLIP's visual representations respond to stochastic perturbations: aggregating predictions across noisy views, constructing Gaussian noise-averaged anchors and interpolating features toward them, or applying counter-perturbations. These strategies improve robustness but often degrade clean accuracy, yielding an unfavorable clean-robust trade-off. We revisit stochastic test-time defenses and identify an underexplored noise-regime transition in CLIP's representation space. Prior work explored perturbations mainly in the weak-noise regime, where adversarial examples can appear unusually stable (false stability). Our analysis shows this reverses as perturbation strength grows: beyond the weak-noise regime, adversarial representations become markedly more unstable than clean ones, giving a clearer separation signal. The transition is consistent across uniform and Gaussian noise, photometric and geometric transforms, datasets, and diverse attacks. It largely disappears in adversarially trained models, suggesting it is tied to the fragile local-basin geometry of adversarial representations in non-robust CLIP. We propose a training-free, plug-in drift-gated mechanism that uses high-noise feature drift as a lightweight gating signal to trigger existing test-time defenses only when adversarial-like instability is detected. Across 13 datasets it consistently improves the clean-robust trade-off. On eight fine-grained datasets, mean clean+adversarial accuracy rises from 65.7% to 71.4% for counterattack defenses and 68.4% to 73.2% for noise-anchoring; on ImageNet and four shifted variants, from 56.1% to 66.2% and 62.1% to 67.6%.

arXiv

Investigating Adversarial Robustness of Multi-modal Large Language Models

Hashmat Shadab Malik, Muzammal Naseer, Salman Khan

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e.g., CLIP) substantially expands the attack surface, making these models vulnerable to visual adversarial perturbations. Prior defenses typically preserve compatibility with pretrained MLLMs by enforcing strict alignment to CLIP's original embedding space during adversarial fine-tuning; while practical, this constraint fundamentally limits achievable robustness. We present a systematic investigation of adversarial robustness in MLLMs. We first introduce a diagnostic CLIP-alignment protocol that predicts, prior to full MLLM training, which robust vision encoders will transfer effectively to the multimodal setting, revealing that large-scale multimodal adversarial pretraining, rather than unimodal scale alone, is the critical factor for strong robustness transfer. Integrating such encoders into MLLMs via end-to-end multimodal training yields average gains of 28 CIDEr points on captioning and 11.7% VQA accuracy under strong adversarial attacks compared to constrained plug-and-play baselines. We further show that adversarial training applied directly to a standard non-robust MLLM degrades both clean and adversarial performance, establishing robust visual representations as a strict prerequisite, while end-to-end adversarial training from a robust backbone delivers additional gains of 1.9 CIDEr points and 4.3% VQA accuracy. Beyond training-time defenses, lightweight test-time visual stochastic transformations serve as an effective black-box defense for non-robust MLLMs, elevating adversarial performance from near-zero to levels comparable with robust models. Finally, we show that our robust models substantially reduce toxic generation under white-box visual jailbreak attacks. Code and pretrained weights will be released publicly.

arXiv

TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing

Tim-Felix Faasch, Jochen Kall, Lucas Nunes, Jens Behley, Cyrill Stachniss

High-fidelity semantic 3D scene representations are crucial for numerous applications, including robotics, autonomous driving, and simulation. Beyond this, the ability to edit such representations enables developers to adapt these applications more easily to specific target scenarios. Current approaches provide limited support for controllable editing. We introduce TASE, a method that projects pretrained 2D semantic features into a truncation-aware embedding space to enable flexible 3D scene editing. Our method explicitly optimizes a feature space in which progressively reducing feature channels yields increasingly abstract semantic representations, while retaining more channels preserves fine-grained detail. Additionally, we improve multi-view consistency of the features using a scale- and translation-equivariance loss. The resulting truncation-aware embedding space enables text-driven edits to 3D scenes, providing explicit control over how strongly edits adhere to the original scene content and allowing more substantial modifications than prior methods. Moreover, we propose a finetuning stage for the editing diffusion model to mitigate artifacts caused by geometric changes. Experimental results demonstrate competitive performance in 3D scene editing, substantially outperforming prior methods on edits involving large geometric modifications.

arXiv

Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications

Roman Pavelkin, Luis A. Zavala-Mondragon, Christiaan G. A. Viviers, Fons van der Sommen

Numerous modern applications in signal processing and medical imaging necessitate acquiring high-dimensional signals under tight resource constraints. Traditional sampling theory suggests that accurate signal reconstruction requires a number of measurements proportional to the signal's ambient dimension, a requirement often too expensive or impractical. Compressed sensing challenges this notion by demonstrating that sparse signals can be recovered with fewer measurements, provided the measurement operator meets certain conditions. This proof-of-concept study presents a task-aware flow-based generative framework -- a reformulation of the conventional Flow Matching training paradigm with a flow model trained to optimize subsampling in compressed sensing applications. We establish the fundamental feasibility of the proposed framework of learning subsampling masks that substantially enhance the performance of compressed sensing for image classification, image reconstruction, and MRI acceleration. For the image reconstruction task, our method demonstrated state-of-the-art performance, achieving Peak Signal-to-Noise Ratio of 25.17 dB at the subsampling rate of 5\% on the CelebA dataset and 29.24 dB when reconstructing $8\times$ accelerated MRI measurements (fastMRI dataset) with the minimal computational overhead. These results highlight the effectiveness of task-conditioning within generative flow models and reveal a promising direction for representation learning strategies. Overall, the proposed framework offers a unified, flexible approach to designing data- and task-driven sensing schemes that can be potentially adapted to a broad range of inverse problems.

arXiv

HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models

Xinyu Wang, Mingze Li, Sicheng Lyu, Dongxiu Liu, Kaicheng Yang, Ziyu Zhao, Yufei Cui, Xiao-Wen Chang, Peng Lu

Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive. Low-bit post-training quantization (PTQ) is the natural remedy, yet the diffusion action head that emits continuous control signals is highly sensitive to it: a few weight and activation outliers are enough to destabilize the head, so prior work leaves it at full precision or falls back to mixed-precision schemes, and uniformly quantizing the whole model to low bit-width remains an open challenge. We present HoloQ-VLA, the first training-free PTQ framework that compresses both the language backbone and the entire diffusion action head to uniform W4A4 precision without mixed-precision allocation. Instead of trading weight quality against activation quality, HoloQ-VLA targets the two outlier sources with complementary transforms: a weight-adapted rotation composed with an activation-dispersing Hadamard transform, together with per-step scaling that absorbs the dynamic-range drift exhibited by the action head across denoising steps. On LIBERO, HoloQ-VLA compresses Pi-0.5 and GR00T-N1.5 to W4A4 with 98.0% and 87.8% task success rates, matching or exceeding their FP16 references of 97.1% and 87.0%, while reducing the static memory footprint by 74.2%. Real-world manipulation experiments further demonstrate that HoloQ-VLA maintains smooth and accurate control across diverse real-world scenarios.

arXiv

R2AoP: Reliable and Robust Angle of Progression Estimation from Intrapartum Ultrasound

Yuanhan Wang, Yifei Chen, Beining Wu, Mingxuan Liu, Xiaotian Hu, Chunbo Jiang, Yijin Li, Changmiao Wang, Feiwei Qin, Qiyuan Tian

Accurate estimation of the Angle of Progression (AoP) from intrapartum transperineal ultrasound is critical for objective assessment of labor progression, yet remains highly sensitive to imaging noise, boundary ambiguities, and the geometric amplification of local segmentation errors. We propose R2AoP, a reliable and robust AoP estimation framework that integrates structurally informed segmentation and confidence-guided geometric modeling to achieve stable and reproducible measurements. A three-branch local-structure-enhanced backbone improves the delineation of the pubic symphysis (PS) and fetal head (FH), while confidence-weighted contour fitting explicitly suppresses the influence of unreliable boundary points in AoP computation. To further improve performance under heterogeneous acquisition conditions, we introduce a lightweight geometry-reliable test-time adaptation strategy as an auxiliary component, enabling stable inference without target annotations. Extensive evaluations on multi-center benchmarks demonstrate consistent reductions in AoP error and boundary metrics compared with state-of-the-art AoP methods. Our source code is available at https://github.com/baiyou1234/R2AoP.

arXiv

AnyAct: Towards Human Reenactment of Character Motion From Video

Liuhan Chen, Lei Zhong, Jiawei Wang, Qing Shuai, Li Yuan, Leidong Fan, Qing Li, Kanglin Liu

We study the problem of directly deriving an initial human reenactment from a monocular video of a non-human character. Our goal is not to reconstruct the source character itself but to reinterpret its motion as a plausible and editable human performance for downstream animation authoring. This task is challenging because existing video-based motion capture methods are largely restricted to human-centric structural spaces, while motion retargeting methods typically require structured 3D source motions and known source topologies. Our key insight is that sparse local articulated motion cues can preserve essential dynamics across large structural differences, providing a stable bridge from character video to human reenactment. Based on this observation, we propose AnyAct, which formulates character-video-driven human reenactment as conditional human motion generation from transferable sparse local 2D articulated motion. To make this practical, we introduce three key designs: human-motion-only supervision via augmented 3D-to-2D projection, progressive 3D-to-2D training to alleviate conditioning ambiguity, and global-local motion decoupling for reliable local motion control. We further construct a benchmark primarily covering diverse non-human character videos. Experiments on the benchmark show that AnyAct produces high-fidelity initial human reenactments that preserve the essential dynamics of the characters in reference videos, and further ablation studies validate the effectiveness of its core designs.

arXiv

Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptation

Kieran Carrigg, Sigur de Vries, Amirhossein Sadough, Marcel van Gerven

Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer normalization. Recent methods attempt to bypass this by replacing normalization layers with hardware-friendly scalar approximations. However, these homogeneous replacements do not optimally fit to all layers' behaviour and rely on expensive model retraining. In this work, we propose a highly efficient, hardware-aware framework that utilizes genetic programming (GP) to evolve heterogeneous, layer-specific scalar functions directly from pre-trained weights. Coupled with a novel post-training re-alignment strategy, our approach eliminates the need to retrain models from scratch entirely. Our evolved expressions accurately approximate the target normalization behaviours, capturing $90\%$ of the variance ($R^2$) compared to only $70.2\%$ for homogeneous baselines, allowing our modified architecture to recover $84.32\%$ Top-1 ImageNet-1K accuracy in only 20 epochs. By preserving this performance while eliminating the global reduction bottleneck, our approach achieves a strict reduction in both arithmetic complexity and off-chip memory traffic compared to standard LayerNorm, removing a primary barrier to the efficient deployment of ViTs on edge accelerators.

arXiv

On-Policy Distillation with Best-of-N Teacher Rollout Selection

Ke Zhang, Yunjie Tian, Dongdi Zhao, Yijiang Li, Yuanye Liu, Vishal M. Patel, Di Fu

On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for improving reasoning while avoiding the reward dependence of reinforcement learning and the catastrophic forgetting often observed in standard supervised fine-tuning. However, standard OPD typically computes teacher supervision under noisy student-generated contexts and often relies on a single stochastic teacher rollout per prompt. As a result, the supervision signal can be high-variance: the sampled teacher trajectory can be incorrect, uninformative, or poorly matched to the student's current reasoning behavior. To address this limitation, we propose BRTS, a Best-of-N Rollout Teacher Selection framework for on-policy distillation. BRTS augments standard student-context OPD with a teacher-context supervision branch constructed from the curated teacher trajectory. Rather than distilling from the first sampled teacher rollout, BRTS samples a small pool of teacher trajectories and selects the auxiliary trajectory using a simple priority rule: correctness first, student alignment second. When multiple correct teacher trajectories are available, BRTS chooses the one most aligned with the student's current behavior; when unconditioned teacher samples fail on harder prompts, it invokes a ground-truth-conditioned recovery step to elicit a natural derivation. The selected trajectory is then used to provide reliable teacher-context supervision inside the OPD loop, augmented with an auxiliary loss on the teacher trajectory. Experiments on AIME 2024, AIME 2025, and AMC 2023 show that BRTS improves over standard OPD on challenging reasoning benchmarks, with the largest gains on harder datasets. Our code is available at https://github.com/BWGZK-keke/BRTS.

arXiv

Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models

Cyril Shih-Huan Hsu, Wig Yuan-Cheng Cheng, Chrysa Papagianni

Deploying Vision-Language Models (VLMs) on edge devices remains challenging due to their substantial computational and memory demands, which exceed the capabilities of resource-constrained embedded platforms. Conversely, fully offloading inference to the cloud is often impractical in bandwidth-limited environments, where transmitting raw visual data introduces substantial latency overhead. While recent edge-cloud collaborative architectures attempt to partition VLM workloads across devices, they typically rely on transmitting fixed-size representations, lacking adaptability to dynamic network conditions and failing to fully exploit semantic redundancy. In this paper, we propose a progressive semantic communication framework for edge-cloud VLM inference, using a Meta AutoEncoder that compresses visual tokens into adaptive, progressively refinable representations, enabling plug-and-play deployment with off-the-shelf VLMs without additional fine-tuning. This design allows flexible transmission at different information levels, providing a controllable trade-off between communication cost and semantic fidelity. We implement a full end-to-end edge-cloud system comprising an embedded NXP i.MX95 platform and a GPU server, communicating over bandwidth-constrained networks. Experimental results show that, at 1 Mbps uplink, the proposed progressive scheme significantly reduces network latency compared to full-edge and full-cloud solutions, while maintaining high semantic consistency even under high compression. The implementation code will be released upon publication at https://github.com/open-ep/ProSemComVLM.

arXiv

Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift

Lixian Chen, Mingxuan Huang, Yanhui Chen, Junyi Lin, Yang Shi

Vision--language models can face asymmetric visual and textual shifts at deployment. These shifts expose a multimodal failure mode in which an unreliable branch remains overconfident, dominates fusion, and causes entropy-based test-time adaptation to sharpen an incorrect prediction. We model this behavior as doubly stochastic posterior mixing and cast adaptation as constrained de-mixing. Majorization-Guided Multimodal Test-Time Adaptation (MG-MTTA) freezes both encoders and updates only a lightweight fusion module. Running-anchor consistency estimates relative branch drift, while cross-modal conflict regulates modality dominance before entropy sharpening. The analysis gives sufficient conditions for entropy reduction to preserve the clean decision and an explicit threshold at which a biased modality reverses the fused ranking. Across visual, textual, and joint shifts, MG-MTTA improves ImageNet top-1 accuracy from 57.97\% to 66.51\% under textual shift and from 21.68\% to 26.27\% under joint shift, while reducing wrong-more-confident failures. The largest gains occur under textual and joint shifts, where the two branches differ more in reliability. Project page: https://mg-mtta.github.io/.

arXiv

MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation

Haojie Zhang, Di Wu, Bingyan Liu, Linjie Zhong, Yuancheng Wei, Xingsong Ye, Nanqing Liu, Yaling Liang

While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained by the absence of datasets that address three core challenges: authentic narrative logic, spatiotemporal text-video alignment conflicts, and the "copy-paste" dilemma prevalent in Subject-to-Video (S2V) generation. To bridge this gap, we introduce MuSS, a large-scale, dual-track dataset tailored for multi-shot video and S2V generation. Sourced from over 3,000 movies, MuSS explicitly supports both complex montage transitions and subject-centric narratives. To construct this dataset, we pioneer a progressive captioning pipeline that eliminates contextual conflicts by ensuring local shot-level accuracy before enforcing global narrative coherence. Crucially, we implement a cross-shot matching mechanism to fundamentally eradicate the S2V copy-paste shortcut. Alongside the dataset, we propose the Cinematic Narrative Benchmark, featuring a visual-logic-driven paradigm and a novel Anti-Copy-Paste Variance (ACP-Var) metric to rigorously assess continuous storytelling and 3D structural consistency. Extensive experiments demonstrate that while current baselines struggle with continuous narrative logic or degenerate into trivial 2D sticker generators, our MuSS-augmented model achieves state-of-the-art narrative effectiveness and cross-shot identity preservation.

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 →