Picture for Yiwen Guo

Yiwen Guo

Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm

Add code
Mar 04, 2025
Viaarxiv icon

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models

Add code
Feb 13, 2025
Viaarxiv icon

Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model

Add code
Feb 08, 2025
Figure 1 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Figure 2 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Figure 3 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Figure 4 for Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Viaarxiv icon

CueTip: An Interactive and Explainable Physics-aware Pool Assistant

Add code
Jan 30, 2025
Viaarxiv icon

Multi-Task Model Merging via Adaptive Weight Disentanglement

Add code
Nov 27, 2024
Figure 1 for Multi-Task Model Merging via Adaptive Weight Disentanglement
Figure 2 for Multi-Task Model Merging via Adaptive Weight Disentanglement
Figure 3 for Multi-Task Model Merging via Adaptive Weight Disentanglement
Figure 4 for Multi-Task Model Merging via Adaptive Weight Disentanglement
Viaarxiv icon

Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs

Add code
Oct 20, 2024
Viaarxiv icon

Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation

Add code
Oct 15, 2024
Viaarxiv icon

Recent Advances in Speech Language Models: A Survey

Add code
Oct 01, 2024
Figure 1 for Recent Advances in Speech Language Models: A Survey
Figure 2 for Recent Advances in Speech Language Models: A Survey
Figure 3 for Recent Advances in Speech Language Models: A Survey
Figure 4 for Recent Advances in Speech Language Models: A Survey
Viaarxiv icon

Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis

Add code
Aug 29, 2024
Figure 1 for Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis
Figure 2 for Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis
Figure 3 for Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis
Figure 4 for Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis
Viaarxiv icon

Two Optimizers Are Better Than One: LLM Catalyst for Enhancing Gradient-Based Optimization

Add code
May 31, 2024
Figure 1 for Two Optimizers Are Better Than One: LLM Catalyst for Enhancing Gradient-Based Optimization
Figure 2 for Two Optimizers Are Better Than One: LLM Catalyst for Enhancing Gradient-Based Optimization
Figure 3 for Two Optimizers Are Better Than One: LLM Catalyst for Enhancing Gradient-Based Optimization
Figure 4 for Two Optimizers Are Better Than One: LLM Catalyst for Enhancing Gradient-Based Optimization
Viaarxiv icon