Picture for Xiaoran Fan

Xiaoran Fan

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations

Add code
Mar 19, 2025
Viaarxiv icon

EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection

Add code
Mar 03, 2025
Viaarxiv icon

Predicting Large Language Model Capabilities on Closed-Book QA Tasks Using Only Information Available Prior to Training

Add code
Feb 06, 2025
Viaarxiv icon

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Add code
Oct 24, 2024
Figure 1 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Figure 2 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Figure 3 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Figure 4 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Viaarxiv icon

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

Add code
Oct 15, 2024
Figure 1 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Figure 2 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Figure 3 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Figure 4 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Viaarxiv icon

Leveraging Foundation Models for Zero-Shot IoT Sensing

Add code
Jul 29, 2024
Figure 1 for Leveraging Foundation Models for Zero-Shot IoT Sensing
Figure 2 for Leveraging Foundation Models for Zero-Shot IoT Sensing
Figure 3 for Leveraging Foundation Models for Zero-Shot IoT Sensing
Figure 4 for Leveraging Foundation Models for Zero-Shot IoT Sensing
Viaarxiv icon

mmPlace: Robust Place Recognition with Intermediate Frequency Signal of Low-cost Single-chip Millimeter Wave Radar

Add code
Mar 07, 2024
Viaarxiv icon

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Add code
Feb 08, 2024
Figure 1 for Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Figure 2 for Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Figure 3 for Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Figure 4 for Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Viaarxiv icon

StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback

Add code
Feb 05, 2024
Figure 1 for StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
Figure 2 for StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
Figure 3 for StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
Figure 4 for StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
Viaarxiv icon

MouSi: Poly-Visual-Expert Vision-Language Models

Add code
Jan 30, 2024
Viaarxiv icon