Picture for Zhaoyang Wang

Zhaoyang Wang

EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment

Add code
Jun 13, 2025
Viaarxiv icon

FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution

Add code
Jun 13, 2025
Viaarxiv icon

Efficient Long CoT Reasoning in Small Language Models

Add code
May 24, 2025
Viaarxiv icon

Anyprefer: An Agentic Framework for Preference Data Synthesis

Add code
Apr 27, 2025
Viaarxiv icon

Synergistic Weak-Strong Collaboration by Aligning Preferences

Add code
Apr 22, 2025
Viaarxiv icon

Verifiable Format Control for Large Language Model Generations

Add code
Feb 06, 2025
Viaarxiv icon

MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation

Add code
Feb 03, 2025
Viaarxiv icon

CREAM: Consistency Regularized Self-Rewarding Language Models

Add code
Oct 17, 2024
Figure 1 for CREAM: Consistency Regularized Self-Rewarding Language Models
Figure 2 for CREAM: Consistency Regularized Self-Rewarding Language Models
Figure 3 for CREAM: Consistency Regularized Self-Rewarding Language Models
Figure 4 for CREAM: Consistency Regularized Self-Rewarding Language Models
Viaarxiv icon

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Add code
Oct 14, 2024
Figure 1 for MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Figure 2 for MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Figure 3 for MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Figure 4 for MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Viaarxiv icon

CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models

Add code
Jun 10, 2024
Figure 1 for CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Figure 2 for CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Figure 3 for CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Figure 4 for CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Viaarxiv icon