Picture for Hung Le

Hung Le

Pick

Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models

Add code
Apr 03, 2025
Viaarxiv icon

S2MoE: Robust Sparse Mixture of Experts via Stochastic Learning

Add code
Mar 29, 2025
Viaarxiv icon

Sparse Mixture of Experts as Unified Competitive Learning

Add code
Mar 29, 2025
Viaarxiv icon

On the effectiveness of discrete representations in sparse mixture of experts

Add code
Nov 28, 2024
Viaarxiv icon

CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models

Add code
Nov 07, 2024
Figure 1 for CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
Figure 2 for CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
Figure 3 for CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
Figure 4 for CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
Viaarxiv icon

Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning

Add code
Oct 14, 2024
Viaarxiv icon

Technical Design Review of Duke Robotics Club's Oogway: An AUV for RoboSub 2024

Add code
Oct 13, 2024
Figure 1 for Technical Design Review of Duke Robotics Club's Oogway: An AUV for RoboSub 2024
Figure 2 for Technical Design Review of Duke Robotics Club's Oogway: An AUV for RoboSub 2024
Figure 3 for Technical Design Review of Duke Robotics Club's Oogway: An AUV for RoboSub 2024
Figure 4 for Technical Design Review of Duke Robotics Club's Oogway: An AUV for RoboSub 2024
Viaarxiv icon

Oogway: Designing, Implementing, and Testing an AUV for RoboSub 2023

Add code
Oct 13, 2024
Figure 1 for Oogway: Designing, Implementing, and Testing an AUV for RoboSub 2023
Figure 2 for Oogway: Designing, Implementing, and Testing an AUV for RoboSub 2023
Figure 3 for Oogway: Designing, Implementing, and Testing an AUV for RoboSub 2023
Figure 4 for Oogway: Designing, Implementing, and Testing an AUV for RoboSub 2023
Viaarxiv icon

ALIAS: DAG Learning with Efficient Unconstrained Policies

Add code
Aug 27, 2024
Figure 1 for ALIAS: DAG Learning with Efficient Unconstrained Policies
Figure 2 for ALIAS: DAG Learning with Efficient Unconstrained Policies
Figure 3 for ALIAS: DAG Learning with Efficient Unconstrained Policies
Figure 4 for ALIAS: DAG Learning with Efficient Unconstrained Policies
Viaarxiv icon

Large Language Models Prompting With Episodic Memory

Add code
Aug 14, 2024
Viaarxiv icon