Picture for Tingchen Fu

Tingchen Fu

Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts

Add code
Aug 09, 2024
Viaarxiv icon

On the Transformations across Reward Model, Parameter Update, and In-Context Prompt

Add code
Jun 24, 2024
Viaarxiv icon

Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction

Add code
May 22, 2024
Viaarxiv icon

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models

Add code
Feb 21, 2024
Viaarxiv icon

Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models

Add code
Sep 03, 2023
Viaarxiv icon

Learning to Express in Knowledge-Grounded Conversation

Add code
Apr 12, 2022
Figure 1 for Learning to Express in Knowledge-Grounded Conversation
Figure 2 for Learning to Express in Knowledge-Grounded Conversation
Figure 3 for Learning to Express in Knowledge-Grounded Conversation
Figure 4 for Learning to Express in Knowledge-Grounded Conversation
Viaarxiv icon

There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory

Add code
Apr 06, 2022
Figure 1 for There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory
Figure 2 for There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory
Figure 3 for There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory
Figure 4 for There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory
Viaarxiv icon