Search Results for author:
Found 12 papers, 5 papers with code
MH-MoE: Multi-Head Mixture-of-Experts
Multi-Head Mixture-of-Experts (MH-MoE) demonstrates superior performance by using the multi-head mechanism to collectively attend to information from various representation spaces within different experts.
Textual Aesthetics in Large Language Models
Image aesthetics is a crucial metric in the field of image generation.
UNComp: Uncertainty-Aware Long-Context Compressor for Efficient Large Language Model Inference
By grouping layers and heads based on their uncertainty, UNComp adaptively compresses both the hidden states and the KV cache.
UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation
We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks.
The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs
Based on observations, we innovatively introduce the Heterophily Snowflake Hypothesis and provide an effective solution to guide and facilitate research on heterophilic graphs and beyond.
Ranked #3 on
Node Classification
on Texas
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles.
Enhancing Uncertain Demand Prediction in Hospitals Using Simple and Advanced Machine Learning
Accurately predicting patient care demand, however, is a ubiquitous challenge for hospitals across the world due, in part, to the demand's time-varying temporal variability, and, in part, to the difficulty in modelling trends in advance.
Multi-Head Mixture-of-Experts
These sub-tokens are then assigned to and processed by a diverse set of experts in parallel, and seamlessly reintegrated into the original token form.
Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation
Recent studies have demonstrated the exceptional potentials of leveraging human preference datasets to refine text-to-image generative models, enhancing the alignment between generated images and textual prompts.
Mixture of LoRA Experts
LoRA has gained widespread acceptance in the fine-tuning of large pre-trained models to cater to a diverse array of downstream tasks, showcasing notable effectiveness and efficiency, thereby solidifying its position as one of the most prevalent fine-tuning techniques.
Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing.
Investigating EEG-Based Functional Connectivity Patterns for Multimodal Emotion Recognition
The discrimination ability of the EEG connectivity features in emotion recognition is evaluated on three public emotion EEG datasets: SEED, SEED-V, and DEAP.
