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

+1029新增论文
+789其中 AI 相关
+127已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-11 15:15 · 全站最近入库：2026-11-11 13:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-10 17:06 — 2026-11-11 17:06（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：2026-11-11 15:15最近发现新增版本：2026-11-11 13:09库内论文最新更新时间：2026-11-11 08:00

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。

21,672 已收录论文18,320 AI 相关6,055 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 3 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-11 15:13（北京时间）
新论文 · v1arXiv:2611.10348

Guided Co-Attention with Adaptive Gating for Multimodal Medical Data Fusion

Muntaqim Ahmed Raju, Priyanka Siddappa, Md Shifat Haider Al Amin, Ruizhe Ma, Md Ripon Ahammed

原文摘要

Multimodal fusion requires not only exchanging information across modalities but also determining which representations should participate in the interaction and how complementary cross-modal views should be combined. We introduce Guided Co-Attention with Adaptive Gating, a fusion framework that integrates token-wise guidance, bidirectional cross-attention, and sample-specific fusion. The proposed method constructs two directional representations: an image-conditioned text representation, obtained by allowing textual tokens to query visual features, and a text-conditioned image representation formed in the reverse direction. Token-wise guidance modulates the representations before cross-attention, while an adaptive gate learns the relative contribution of the two resulting directional representations for each sample. We evaluate the approach using paired chest radiographs and radiology reports as an image-text test bed for binary (normal vs. abnormal) classification. The two cross-attention directions exhibit distinct performance characteristics, demonstrating that reversing the query and source modalities does not produce interchangeable representations. Ablation experiments further show that bidirectional interaction, adaptive gating, and token guidance provide complementary benefits. The proposed model achieves 96.05% accuracy, 96.10% F1-score, 98.37% AUC, 95.60% Sens@95Spec, and 96.51% Spec@95Sens, yielding the highest mean performance across all evaluated metrics. These findings support explicitly modeling interaction direction, token relevance, and sample-dependent integration when constructing multimodal representations.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1213ACL Anthology · ACL 2026

Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths

YiJie Huang, Xiaocui Yang Northeastern University, Shi Feng Northeastern University, China, Wen Zhang Northeastern University, Kaisong Song, Yifei Zhang, Daling Wang

原文摘要

Efficiently aligning visual features with Large Language Models (LLMs) remains a critical bottleneck in Multimodal LLMs. Existing query-based alignment modules (e.g., Q-Former) rely on randomly initialized queries, resulting in an inefficient cold start exploration process. Furthermore, they enforce uniform cross-attention across all layers, leading to computational redundancy. Our empirical analysis reveals that query tokens initialized with language priors can rapidly capture global semantics, leading to early representation convergence after only a few layers. In this paper, we propose Cat-MoD, a Caption token Guided Asymmetric Mixture-of-Depths framework. It incorporates a Hybrid Query Construction module where Guide Tokens initialized from coarse-grained linguistic priors rapidly anchor global semantic context, and randomly initialized Explorer Tokens remain active to capture fine-grained visual details. Exploiting this early convergence, we introduce an Asymmetric Mixture-of-Depths mechanism, where a similarity-aware router dynamically prunes redundant tokens from expensive cross-attention layers while preserving their context in self-attention. Experiments on multiple benchmarks demonstrate that Cat-MoD matches or surpasses baseline performance, while substantially reducing alignment FLOPs by approximately 37% during both training and inference, offering a highly efficient solution for multimodal alignment. Code: https://github.com/JasonOrange0726/Cat-MoD.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2154ACL Anthology · ACL 2026

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs

Chaoyu Li Arizona State University, Yogesh Kulkarni Arizona State University, Pooyan Fazli Arizona State University

原文摘要

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits during training. We introduce ReGATE (Reference-Guided Adaptive Token Elision), an adaptive token pruning method for accelerating MLLM training. ReGATE adopts a teacher-student framework, in which a frozen teacher LLM provides per-token guidance losses that are fused with an exponential moving average of the student’s difficulty estimates. This adaptive scoring mechanism dynamically selects informative tokens while skipping redundant ones in the forward pass, substantially reducing computation without altering the model architecture. Across three representative MLLMs, ReGATE matches the peak accuracy of standard training on MVBench up to 2 \times faster, using only 38% of the tokens. With extended training, it even surpasses the baseline across multiple multimodal benchmarks, cutting total token usage by over 41%. Code and models will be released publicly.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表