Picture for Yu Gu

Yu Gu

Road Rage Reasoning with Vision-language Models (VLMs): Task Definition and Evaluation Dataset

Add code
Mar 14, 2025
Viaarxiv icon

Force Aware Branch Manipulation To Assist Agricultural Tasks

Add code
Mar 11, 2025
Viaarxiv icon

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

Add code
Feb 25, 2025
Viaarxiv icon

LLM-QE: Improving Query Expansion by Aligning Large Language Models with Ranking Preferences

Add code
Feb 24, 2025
Viaarxiv icon

HIPPO: Enhancing the Table Understanding Capability of Large Language Models through Hybrid-Modal Preference Optimization

Add code
Feb 24, 2025
Viaarxiv icon

Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search

Add code
Feb 18, 2025
Viaarxiv icon

Magma: A Foundation Model for Multimodal AI Agents

Add code
Feb 18, 2025
Viaarxiv icon

SimSort: A Powerful Framework for Spike Sorting by Large-Scale Electrophysiology Simulation

Add code
Feb 05, 2025
Viaarxiv icon

Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale

Add code
Feb 02, 2025
Figure 1 for Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale
Figure 2 for Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale
Figure 3 for Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale
Figure 4 for Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale
Viaarxiv icon

CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder

Add code
Dec 12, 2024
Figure 1 for CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder
Figure 2 for CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder
Figure 3 for CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder
Figure 4 for CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder
Viaarxiv icon