Pinned Repositories
RAP
Reasoning with Language Model is Planning with World Model
Aerial-Ace
Team repository for Aerial-Ace, a SJTU ICPC Team
Anonymous
RISCV-CPU
A Homework for Computer Architecture at SJTU
Rogue-Mx
SJTU-ReviewNotes
This repository keeps my review notes for classes at SJTU.
STLite
SJTU DataStructure STLite
textgame-revisiting-role
Trilling-PintOS
wu-qing-157.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
wu-qing-157's Repositories
wu-qing-157/RISCV-CPU
A Homework for Computer Architecture at SJTU
wu-qing-157/Anonymous
wu-qing-157/Rogue-Mx
wu-qing-157/Aerial-Ace
Team repository for Aerial-Ace, a SJTU ICPC Team
wu-qing-157/Trilling-PintOS
wu-qing-157/SJTU-ReviewNotes
This repository keeps my review notes for classes at SJTU.
wu-qing-157/STLite
SJTU DataStructure STLite
wu-qing-157/Train-Ticket-Android
wu-qing-157/Train-Ticket-BackEnd
wu-qing-157/Train-Ticket-Submit
wu-qing-157/Train-Ticket-Web
wu-qing-157/zsh-config
This is a backup of my z shell config
wu-qing-157/textgame-revisiting-role
wu-qing-157/wu-qing-157.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
wu-qing-157/3D-Vision-and-Touch
When told to understand the shape of a new object, the most instinctual approach is to pick it up and inspect it with your hand and eyes in tandem. Here, touch provides high fidelity localized information while vision provides complementary global context. However, in 3D shape reconstruction, the complementary fusion of visual and haptic modalities remains largely unexplored. In this paper, we study this problem and present an effective chart-based approach to fusing vision and touch, which leverages advances in graph convolutional networks. To do so, we introduce a dataset of simulated touch and vision signals from the interaction between a robotic hand and a large array of 3D objects. Our results show that (1) leveraging both vision and touch signals consistently improves single-modality baselines, especially when the object is occluded by the hand touching it; (2) our approach outperforms alternative modality fusion methods and strongly benefits from the proposed chart-based structure; (3) reconstruction quality boosts with the number of grasps provided; and (4) the touch information not only enhances the reconstruction at the touch site but also extrapolates to its local neighborhood.
wu-qing-157/Compiler-2020-local-judge
wu-qing-157/Datos
wu-qing-157/jericho
A learning environment for man-made Interactive Fiction games.
wu-qing-157/Lecture-of-ACM-Class-2018
wu-qing-157/llama-cpp-python
Python bindings for llama.cpp
wu-qing-157/models
Models and examples built with TensorFlow
wu-qing-157/Mx-Compiler-Submit
This repository is only used to submit my compiler
wu-qing-157/PaimonMenuBar
Track real-time Genshin Impact stats in your macOS menubar
wu-qing-157/PintOS-Assignment
--set private
wu-qing-157/ravel
A RISC-V simulator
wu-qing-157/rcdqn
This repository contains the source code of the EMNLP 2020 paper Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning.
wu-qing-157/RL4LMs
A modular RL library to fine-tune language models to human preferences
wu-qing-157/SJTU-ACM-Scripts
This repository keeps my scripts used when I work as a co-coach at SJTU-ACM team.
wu-qing-157/WechatMomentScreenshot
朋友圈转发截图生成工具