Search Results for author:
Found 18 papers, 9 papers with code
Language Model Evolution: An Iterated Learning Perspective
With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase.
Direct Language Model Alignment from Online AI Feedback
Moreover, responses in these datasets are often sampled from a language model distinct from the one being aligned, and since the model evolves over training, the alignment phase is inevitably off-policy.
Decoding-time Realignment of Language Models
Aligning language models with human preferences is crucial for reducing errors and biases in these models.
ICED: Zero-Shot Transfer in Reinforcement Learning via In-Context Environment Design
ICED generates levels using a variational autoencoder trained over an initial set of level parameters, reducing distributional shift, and achieves significant improvements in ZSG over adaptive level sampling strategies and UED methods.
Sample Relationship from Learning Dynamics Matters for Generalisation
Although much research has been done on proposing new models or loss functions to improve the generalisation of artificial neural networks (ANNs), less attention has been directed to the impact of the training data on generalisation.
How the level sampling process impacts zero-shot generalisation in deep reinforcement learning
A key limitation preventing the wider adoption of autonomous agents trained via deep reinforcement learning (RL) is their limited ability to generalise to new environments, even when these share similar characteristics with environments encountered during training.
How to prepare your task head for finetuning
We identify a significant trend in the effect of changes in this initial energy on the resulting features after fine-tuning.
Deep Reinforcement Learning for Multi-Agent Interaction
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning.
Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
After the great success of Vision Transformer variants (ViTs) in computer vision, it has also demonstrated great potential in domain adaptive semantic segmentation.
Ranked #7 on
Semantic Segmentation
on SYNTHIA-to-Cityscapes
Better Supervisory Signals by Observing Learning Paths
Observing the learning path not only provides a new perspective for understanding knowledge distillation, overfitting, and learning dynamics, but also reveals that the supervisory signal of a teacher network can be very unstable near the best points in training on real tasks.
Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability
Researchers are using deep learning models to explore the emergence of language in various language games, where simulated agents interact and develop an emergent language to solve a task.
Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability
Researchers are using deep learning models to explore the emergence of language in various language games, where agents interact and develop an emergent language to solve tasks.
Inductive Bias and Language Expressivity in Emergent Communication
Referential games and reconstruction games are the most common game types for studying emergent languages.
Compositional Languages Emerge in a Neural Iterated Learning Model
The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary.
Emergence of Numeric Concepts in Multi-Agent Autonomous Communication
Although their encodeing method is not compositional like natural languages from a perspective of human beings, the emergent languages can be generalised to unseen inputs and, more importantly, are easier for models to learn.
The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
Since first introduced, computer simulation has been an increasingly important tool in evolutionary linguistics.
IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations
The IJCNLP-2017 Multi-choice Question Answering(MCQA) task aims at exploring the performance of current Question Answering(QA) techniques via the realworld complex questions collected from Chinese Senior High School Entrance Examination papers and CK12 website1.
Which is the Effective Way for Gaokao: Information Retrieval or Neural Networks?
As one of the most important test of China, Gaokao is designed to be difficult enough to distinguish the excellent high school students.
