All Posts
Browse all articles in chronological order
-
DeepScaleR: Surpassing o1-Preview with a 1.5B Model by Scaling RL
The Path to Empowering Small Models with Inference Capabilities via RL.
-
Paper Reading: UI-TARS: Pioneering Automated GUI Interaction with Native Agents
An end-to-end GUI agent that achieves superior performance in automated GUI interactions through ...
-
Paper Reading: Offline Reinforcement Learning for LLM Multi-Step Reasoning
Proposing OREO, an offline RL method that improves LLM reasoning by jointly optimizing policy and...
-
YOLO in Autonomous Driving: A Systematic Review
Analyzing YOLO’s evolution and applications in autonomous vehicles.
-
Vision Transformer vs CNN
Exploring their fundamental differences and unique characteristics in visual tasks
-
Vision Transformer
Exploring their fundamental differences and unique characteristics in visual tasks.
-
Deepfake Detection Survey
Covering detection methods and future challenges.
-
Lips Don’t Lie
Exploring innovative approaches in face forgery detection using lip movement analysis.
-
Self-Blended Images
Paper reading: Detecting Deepfakes with Self-Blended Images
-
Dual Contrastive Learning
For face forgery detection, analyzing its dual-stream architecture.
-
My First Post
这是我的第一篇博客文章，主要介绍如何使用 Jekyll 搭建个人博客。