Picture for Kaipeng Zhang

Kaipeng Zhang

CLS-RL: Image Classification with Rule-Based Reinforcement Learning

Add code
Mar 20, 2025
Viaarxiv icon

Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction

Add code
Mar 20, 2025
Viaarxiv icon

PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models

Add code
Mar 16, 2025
Viaarxiv icon

MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification

Add code
Mar 16, 2025
Viaarxiv icon

MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning

Add code
Mar 10, 2025
Viaarxiv icon

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

Add code
Mar 09, 2025
Viaarxiv icon

ARMOR v0.1: Empowering Autoregressive Multimodal Understanding Model with Interleaved Multimodal Generation via Asymmetric Synergy

Add code
Mar 09, 2025
Viaarxiv icon

Enhance-A-Video: Better Generated Video for Free

Add code
Feb 11, 2025
Viaarxiv icon

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

Add code
Feb 10, 2025
Figure 1 for SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
Figure 2 for SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
Figure 3 for SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
Figure 4 for SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
Viaarxiv icon

ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality

Add code
Dec 05, 2024
Figure 1 for ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality
Figure 2 for ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality
Figure 3 for ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality
Figure 4 for ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality
Viaarxiv icon