Teaching robots to see and act 🤖 | Assistant Professor @ SUAT | CV · Robotics · Embodied AI
Bayesian-Crowd-Counting. Official Implement of ICCV 2019 oral paper Bayesian Loss for Crowd Count Estimation with Point Supervision
343awesome-video-action-models. 🤖 A curated list of Video Action Models (VAMs) — papers using video generation models to produce executable robot actions. Covers UniPi, UVA, mimic-video, Motus, Cosmos Policy, DreamZero, and more.
10A-Prompts. The official Implement of paper "Remind of the Past: Incremental Learning with Analogical Prompts"
5group_sparcity. using L2,1 norm base one tensorflow
3tensorflow_face. An academic oriented face recognition framework base on tensorflow and tensorflow.slim
3Awsome-Multimodal-In-Context-Learning. A curated list of multimodal in context learning.
2Awesome-Robotics-Lifelong-Learning. Paper Collecttions of Robotics Lifelong Learning
1