activity
20242026
collaborators

7 papers

cs.CV2026

Pix2Key: Controllable Open-Vocabulary Retrieval with Semantic Decomposition and Self-Supervised Visual Dictionary Learning

Guoyizhe Wei, Yang Jiao, Nan Xi +4

Composed Image Retrieval (CIR) uses a reference image plus a natural-language edit to retrieve images that apply the requested change while preserving other relevant visual content…

cs.CV2025

RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models

Timing Yang, Guoyizhe Wei, Alan Yuille +1

Mamba has recently garnered attention as an effective backbone for vision tasks. However, its underlying mechanism in visual domains remains poorly understood. In this work, we sys…

cs.RO2025

OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation

Xinda Xue, Junjun Hu, Minghua Luo +7

Embodied navigation presents a core challenge for intelligent robots, requiring the comprehension of visual environments, natural language instructions, and autonomous exploration.…

cs.LG2025

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Wei Fu, Jiaxuan Gao, Xujie Shen +10

Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive paral…

cs.CV2025

ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models

Guoyizhe Wei, Rama Chellappa

Vision Transformers (ViTs) have delivered remarkable progress through global self-attention, yet their quadratic complexity can become prohibitive for high-resolution inputs. In th…

cs.CV2025

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

Feng Wang, Yaodong Yu, Guoyizhe Wei +4

Since the introduction of Vision Transformer (ViT), patchification has long been regarded as a de facto image tokenization approach for plain visual architectures. By compressing t…