Bin Wang

MOORe: Model-based Offline-to-Online Reinforcement Learning

2022 · arXiv (Cornell University)

With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online. A smooth transfer of the policy matters in safe real-world deployment. Besides, fast …

Rethinking Reinforcement Learning based Logic Synthesis

2022 · arXiv (Cornell University)

Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process. However, through extensive experiments, we find out that the learned policy makes decisions …

Solving Word Function Problems in Line with Educational Cognition Way

2022

Intelligent solutions are an important research field in artificial intelligence education, automatic reasoning and solutions to function problems are a key technology of intelligent tutoring services, which has become a challenging research hotspot in the …

Just Rank: Rethinking Evaluation with Word and Sentence Similarities

2022 · arXiv (Cornell University)

Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence similarity …

Knowledge Graph Embedding with 3D Compound Geometric Transformations

2023 · arXiv (Cornell University)

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was …

Relational Sentence Embedding for Flexible Semantic Matching

2023

We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings.Prior work mainly models the similarity between sentences based on their embedding distance.Because of the complex semantic meanings conveyed, …

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy

2023 · arXiv (Cornell University)

Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies have focused on modeling reasoning steps using various thought …

Contract Theory Based Incentive Mechanism for Clustered Federated Learning

2023

Clustered Federated Learning (CFL) can be applied to Internet of Things (IoT) scenarios such as intelligent transportation and healthcare, which can effectively solve the problem of heterogeneous data distribution. However, users may be reluctant to …

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval

2024 · arXiv (Cornell University)

Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address …

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

2024 · arXiv (Cornell University)

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, …

أوراق هذا المؤلف

MOORe: Model-based Offline-to-Online Reinforcement Learning

Rethinking Reinforcement Learning based Logic Synthesis

Solving Word Function Problems in Line with Educational Cognition Way

Just Rank: Rethinking Evaluation with Word and Sentence Similarities

Knowledge Graph Embedding with 3D Compound Geometric Transformations

Relational Sentence Embedding for Flexible Semantic Matching

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy

Contract Theory Based Incentive Mechanism for Clustered Federated Learning

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

Data-Driven Discovery of Sulfur Mineralogy

Semantically Smooth Knowledge Graph Embedding

Knowledge Graph Embedding: A Survey of Approaches and Applications