Sheng Liu

16

Papers

97

Total Citations

Papers (16)

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering

OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

Depth-Guided Sparse Structure-From-Motion for Movies and TV Shows

Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training

On Learning Contrastive Representations for Learning With Noisy Labels

Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning

LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization

PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels

Adaptive Early-Learning Correction for Segmentation From Noisy Annotations

OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition

Early-Learning Regularization Prevents Memorization of Noisy Labels

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Are All Losses Created Equal: A Neural Collapse Perspective