Ruichuan An

Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes

Can Vision–Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective.

SpikeGen: Decoupled “Rods and Cones” Visual Representation Processing with Latent Generative Framework

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval

Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM

Robobench: A Comprehensive Evaluation Benchmark For Multimodal Large Language Models as Embodied Brain

UniCTokens-R1: Boosting Unified Personalization via Reinforcement Learning

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

HyperAdapter: Generating Adapters for Pre-Trained Model-Based Continual Learning