Yi Li

10

Papers

239

Total Citations

Papers (10)

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

Faster Approximation Algorithms for k-Center via Data Reduction

Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement

Split Adaptation for Pre-trained Vision Transformers

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

Token Activation Map to Visually Explain Multimodal LLMs

Zeitgebers-Based User Experience Analysis and Time Perception Modeling via Transformer in VR

Community-Centric Graph Unlearning