Search Results for author:
Found 11 papers, 4 papers with code
Modality-specific Learning Rates for Effective Multimodal Additive Late-fusion
Moreover, for different modalities, the best unimodal models may work under significantly different learning rates due to the nature of the modality and the computational flow of the model; thus, selecting a global learning rate for late-fusion models can result in a vanishing gradient for some modalities.
CatCode: A Comprehensive Evaluation Framework for LLMs On the Mixture of Code and Text
Large language models (LLMs) such as ChatGPT are increasingly proficient in understanding and generating a mixture of code and text.
FLM-101B: An Open LLM and How to Train It with $100K Budget
We demonstrate that a 101B-parameter LLM with 0. 31T tokens can be trained with a budget of 100K US dollars.
Masked Structural Growth for 2x Faster Language Model Pre-training
In terms of growth schedule, the impact of each single dimension on a schedule's efficiency is under-explored by existing work.
nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales
With around 14% of the one-time pre-training cost, we can accurately forecast the loss for models up to 52B.
MUSER: MUltimodal Stress Detection using Emotion Recognition as an Auxiliary Task
The capability to automatically detect human stress can benefit artificial intelligent agents involved in affective computing and human-computer interaction.
The World in My Mind: Visual Dialog with Adversarial Multi-modal Feature Encoding
Visual Dialog is a multi-modal task that requires a model to participate in a multi-turn human dialog grounded on an image, and generate correct, human-like responses.
Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks
In this paper, we present a memory-augmented neural network which is motivated by the process of human concept learning.
Cascaded Mutual Modulation for Visual Reasoning
Our code is available at https://github. com/FlamingHorizon/CMM-VR.
Combining Lexical and Semantic-based Features for Answer Sentence Selection
As the result of the evaluation shows, our solution provides a valuable and brief model which could be used in modelling question answering or sentence semantic relevance.
Hierarchical Memory Networks for Answer Selection on Unknown Words
Recently, end-to-end memory networks have shown promising results on Question Answering task, which encode the past facts into an explicit memory and perform reasoning ability by making multiple computational steps on the memory.
