activity
20222025
most citedMod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners

3 citations · 3 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2025

In Pursuit of Pixel Supervision for Visual Pre-training

Lihe Yang, Shang-Wen Li, Yang Li +5

At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging from low-level attri…

cs.CV2025

Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

Xin Lai, Junyi Li, Wei Li +3

Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often ex…

cs.LG2025

BOOD: Boundary-based Out-Of-Distribution Data Generation

Qilin Liao, Shuo Yang, Bo Zhao +2

Harnessing the power of diffusion models to synthesize auxiliary training data based on latent space features has proven effective in enhancing out-of-distribution (OOD) detection…

cs.CV2024

PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation

Zidong Cao, Jinjing Zhu, Weiming Zhang +4

Recently, Depth Anything Models (DAMs) - a type of depth foundation models - have demonstrated impressive zero-shot capabilities across diverse perspective images. Despite its succ…

cs.CV2022★ 3 cited

Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners

Zitian Chen, Yikang Shen, Mingyu Ding +4

Optimization in multi-task learning (MTL) is more challenging than single-task learning (STL), as the gradient from different tasks can be contradictory. When tasks are related, it…