Hui Wang

16

Papers

96

Total Citations

Papers (16)

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

CPPO: Continual Learning for Reinforcement Learning with Human Feedback

Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding

Correcting Large Language Model Behavior via Influence Function

Enhancing Question Generation through Diversity-Seeking Reinforcement Learning with Bilevel Policy Decomposition

Pushing the Limits of BFP on Narrow Precision LLM Inference

Centrality-guided Pre-training for Graph

Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling

SpeHeaTal: A Cluster-Enhanced Segmentation Method for Sperm Morphology Analysis

Enhancing Non-English Capabilities of English-Centric Large Language Models Through Deep Supervision Fine-Tuning

IOP: An Idempotent-Like Optimization Method on the Pareto Front of Hypernetwork

Iterative Context-Aware Graph Inference for Visual Dialog

SP-Net: Slowly Progressing Dynamic Inference Networks

Entropy-Driven Sampling and Training Scheme for Conditional Diffusion Generation

Exploring evolution-aware & -free protein language models as protein function predictors

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training