← Back to all news
Hugging Face Trending Papers

Unlocking the Potential of Vision Foundation Models for Multi-Task Dense Prediction via Mixture of Task Adapters

Read the original on Hugging Face Trending Papers →

The paper introduces D2MoE, a Mixture of Task Adapters designed for vision foundation models to handle multi-task dense prediction. It separates adaptation into a task‑generic low‑rank channel (TG‑LoRA) that preserves pretrained priors and a task‑adaptive sparse expert module (TA‑MoE) that resolves task‑specific conflicts. A Semantic Prior Injector further aligns multi‑level task features with frozen foundation knowledge, achieving robust multi‑task performance with a small trainable footprint.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

Related stories

arXiv Computer Vision
Aug 31

Task-State Adaptation with Prototype Memory for Multi-Task Dense Prediction

The paper introduces MemMTL, a multi‑task dense prediction framework that uses a compact task state derived from global visual context and refines it via a learnable prototype memory. This refined state informs task‑conditioned expert logits, which are combined with token‑level logits and routed through a sparse top‑k selection over a shared local expert bank. A task‑agnostic residual bank offers a common adaptation path, and both paths are added to the backbone feature before task‑specific prediction. The authors outline an evaluation protocol on NYUD‑v2 and PASCAL‑Context using SAM 3 and ViT‑L backbones to assess predictive quality, computational cost, and the contributions of task‑state conditioning, prototype retrieval, and sparse routing.

By Yangyang Xu, Haobo Yuan, Yuzhu Wang, Duo Su, Xi Ye, Yibo Yang, Jun Zhu
More like this →
arXiv AI
Sep 18

Lens: Bringing the Right Semantic Perspective into Focus for Training-Free Multimodal Representation Learning

The paper introduces Lens, a training‑free framework that aligns multimodal representations with the semantic perspective required by downstream tasks. Lens uses a task‑specific readout phrase to anchor the perspective and then aggregates token states after the full input, ensuring the extracted representation reflects task‑conditioned evidence integration rather than generic salient content. The method achieves a Precision@1 of 63.9 across 36 MMEB datasets, outperforming the nearest training‑free baseline by 10.2 points.

By Xinran Liu, Shouqian Shi, Yixian Chen, Ruizhi Chen, Xin-Wei Yao, Sheng Zhong
llmsragmultimodal
More like this →