3 papers
cs.CV2026
Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding
Haodi Liu, Xinhang Yang, Kunda Yan +3
Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occupy only small regions, a cap…
cs.CV2025
Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild
Wanpeng Hu, Haodi Liu, Lin Chen +4
Complex visual reasoning remains a key challenge today. Typically, the challenge is tackled using methodologies such as Chain of Thought (COT) and visual instruction tuning. Howeve…
cs.LG2021
A Theoretical View of Linear Backpropagation and Its Convergence
Ziang Li, Yiwen Guo, Haodi Liu +1
Backpropagation (BP) is widely used for calculating gradients in deep neural networks (DNNs). Applied often along with stochastic gradient descent (SGD) or its variants, BP is cons…