The paper introduces Modality-Aware Expert Pruning (MAEP), a training‑free method that decomposes expert importance by modality in a single forward pass for Mixture‑of‑Experts multimodal large language models. MAEP uses a Delta‑H Output metric to measure the impact of removing an expert and leverages low‑attention vision tokens as a stable pruning signal, while preserving text‑side importance. Experiments on three MoE‑based MLLMs show that MAEP reduces the BF16 expert weight footprint by about 27 GB (≈47% of total memory), enabling a 58 GB model to fit on a single 40 GB GPU and outperforming modality‑agnostic baselines on most multimodal benchmarks.
By Donggeun Kim
arXiv:2511. 04805v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input.
By Yushu Zhao, Zheng Wang, Minjia Zhang
MWOP (Modality-aware Width-wise Operation Pruning) is a method that independently prunes visual‑to‑visual, text‑to‑visual, and text‑to‑text attention paths within each layer of multimodal large language models, and separately selects feed‑forward network channels for visual and textual inputs. It uses a first‑order Taylor criterion to guide pruning, re‑evaluates FFN importance after attention pruning, and applies LoRA‑based recovery training. The approach is paired with path‑sparse Triton attention kernels and compact visual‑side FFN execution to achieve practical acceleration, preserving token sequences while reducing computation.
"whyItMatters":"MWOP achieves a 1.6× prefill speedup on LLaVA‑OneVision‑7B while retaining 99.7% performance, and further boosts token‑compression methods to 2.9× and 2.7× speedups, demonstrating its effectiveness across architectures."
By Xudong Wang, Hao Wu, Haozhe Hu, Peiran Yin, Xinghao Chen, Yunpu Ma, Wei Zhang, Xiaoyu Shen
arXiv:2606. 31903v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation.
By Zhaoyang Luo, Runmin Dong, Miao Yang, Fan Wei, Yushan Lai, Bin Luo, Haohuan Fu
arXiv:2605. 25820v2 Announce Type: replace Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel.
By Yulin Yuan, Hongshuo Zhao, Xiangming Meng
arXiv:2609.01200v1 Announce Type: new
Abstract: When the visual encoder and the language decoder of a vision-language model (VLM) run on different compute nodes, the intermediate visual-token embeddi...
By Reza Heidari, Hamed R. Tavakoli, Juho Kannala
arXiv:2609.15131v1 Announce Type: cross
Abstract: Multimodal large language models (MLLMs) require substantial computation to process numerous visual tokens across all transformer layers. Most method...
By Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang
VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
By Yuan Feng, Qize Yang, Ruizhe Chen, Sibo Song, Haolin He, Muzhi Zhu, Zihan Liu, Yunfei Chu, Xize Cheng, Yuxuan Wang, Jin Xu, Xike Xie
arXiv:2608.24763v1 Announce Type: cross
Abstract: Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedu...
By Muhammad Asad Ali, Umar Khan, Nadia Robertini, Didier Stricker
arXiv:2607. 20981v1 Announce Type: new Abstract: Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints.
By Jay Gor, Karm Dave, Akshita Abrol, Rajesh Gupta, Sudeep Tanwar, Zhengkui Wang
arXiv:2607. 26596v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified transformer architecture.
By Mingkuan Feng, Zhengqi Wen, Jianhua Tao
MASKerade is a new dense‑to‑MoE training method that learns experts as sparse subnetworks of a frozen pretrained feed‑forward network (FFN) using binary masks. A token‑level router selects which masked FFNs to execute, and both the router and mask scores are jointly optimized while the underlying FFN weights remain unchanged. In experiments on five vision‑language benchmarks with Qwen and Gemma backbones, a configuration of four 2:4 experts with top‑2 routing achieved the best performance among compared baselines, demonstrating that mask learning over frozen weights is a practical alternative for constructing token‑routed MoE experts.
By Mingyuan Zhang, Yue Bai, Zhongruo Wang, Yupin Huang, Yiyang Huang, Hailing Wang, Huimin Zeng, Yun Fu