arXiv Machine Learning

DynaTokens: Controlling Token Dynamics for Continual Video-Language Understanding

arXiv AI
Jul 15

Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning

arXiv:2607. 12112v1 Announce Type: cross Abstract: Federated fine-tuning of Multimodal Large Language Models (MLLMs) across distributed networks enables privacy-sensitive adaptation to evolving data streams, yet a fundamental obstacle prevents robust deployment in dynamic environments: catastrophic forgetting, wherein sequential task updates erase previously acquired knowledge across visual, linguistic, and cross-modal representations.

By Jing Liu, Chenxuanyin Zou, Jiayang Ren, Gaoyun Fang, Chengfang Li, Yan Wang, Zhenchao Ma, Bo Hu
arXiv Computer Vision
Aug 27

A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training

The paper introduces a new task called Multimodal Unsupervised Continual Post-Training (MU‑CPT), which allows multimodal large language models (MLLMs) to continuously learn from streaming unlabeled data. It identifies token‑level visual dependence (VD) as essential for MU‑CPT, using its structural distortion to detect cross‑modal forgetting and its heterogeneity to guide new‑task learning. The proposed Visual Dependence‑Aware (VDA) framework includes Visually Constrained Optimal Transport (VC‑OT) to mitigate forgetting and Visually Modulated Adaptation (VMA) to enhance new‑task plasticity, achieving a balance between stability and adaptability in MU‑CPT.

By Kaichen Li, Zhilin Zhu, Jianhao Huang, Zhengqin Lai, Baochen Xiong, Zibo Shao, Yaguang Song, Linhui Xiao, Xiaoshan Yang, Changsheng Xu
arXiv AI
Jun 12

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

arXiv:2606. 13289v1 Announce Type: cross Abstract: Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space.

By Guozhen Zhang, Xuerui Qiu, Yutao Cui, Tianhui Song, Changlin Li, Junzhe Li, Tao Huang, Xiao Zhang, Yang Li, Jianbing Wu, Miles Yang, Zhao Zhong, Liefeng Bo, Limin Wang
arXiv AI
Jun 11

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

arXiv:2606. 11792v1 Announce Type: cross Abstract: Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video.

By Yuansheng Gao, Wenbin Xing, Jiahao Yuan, Kaiwen Zhou, Han Bao, Zonghui Wang, Wenzhi Chen
arXiv Computation and Language
Aug 28

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models introduces the VIG‑Sampler, a method that prioritizes tokens for decoding based on their attention to image tokens and penalizes redundancy in image‑attention distributions. The approach aims to improve the quality of multimodal generation by selecting more informative tokens during diffusion decoding. Experiments on seven captioning and VQA benchmarks with three open‑source dMLLMs show that VIG‑Sampler outperforms the Info‑Gain Sampler by an average of 19.3 CIDEr points and achieves better COCO Caption results using only half as many decoding steps.

By Insu Lee, Wooje Park, Wonseok Shin, Jinwoo Son, Byonghyo Shim
arXiv Computer Vision
Aug 28

RECAP-Forcing: Retaining Content Appearances for Long Video Generation

RECAP-Forcing is a new method for long autoregressive video generation that addresses the memory challenge by organizing memory based on appearance novelty rather than recency. The approach retains key-value caches for newly appearing content—such as entering subjects, disoccluded regions, and new scenes—at the moment they first appear, ensuring consistent identities over time. It combines an attention sink for the initial scene with an optical-flow-based novelty bank for later frames, improving visual quality and semantic fidelity without adding learnable parameters.

By Haiyang Xu, Zheng Ding, Zhuowen Tu