Picture for Yubo Wang

Yubo Wang

Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images

Add code
Feb 23, 2025
Viaarxiv icon

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Add code
Feb 20, 2025
Viaarxiv icon

Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate

Add code
Jan 30, 2025
Figure 1 for Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Figure 2 for Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Figure 3 for Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Figure 4 for Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Viaarxiv icon

Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification

Add code
Jan 06, 2025
Figure 1 for Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification
Figure 2 for Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification
Figure 3 for Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification
Figure 4 for Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification
Viaarxiv icon

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

Add code
Dec 06, 2024
Figure 1 for MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Figure 2 for MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Figure 3 for MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Figure 4 for MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Viaarxiv icon

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Add code
Oct 14, 2024
Figure 1 for MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Figure 2 for MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Figure 3 for MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Figure 4 for MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Viaarxiv icon

Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models

Add code
Oct 09, 2024
Figure 1 for Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
Figure 2 for Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
Figure 3 for Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
Figure 4 for Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
Viaarxiv icon

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

Add code
Sep 04, 2024
Figure 1 for MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Figure 2 for MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Figure 3 for MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Figure 4 for MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Viaarxiv icon

PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents

Add code
Jun 20, 2024
Figure 1 for PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
Figure 2 for PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
Figure 3 for PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
Figure 4 for PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
Viaarxiv icon

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Add code
Jun 04, 2024
Figure 1 for MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Figure 2 for MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Figure 3 for MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Figure 4 for MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Viaarxiv icon