Zhaolu Kang

HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models

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

ChronosCore: Context-Aware Scheduling via Slack-Driven Temporal Reasoning

PerturbFormer: Adversarial Graph Transformers for Scalable and Resilient Representation Learning

Two Lenses are Better Than One: Dual Vector Quantization for Self-Supervised Graph Learning

Ethical Dialogue Modeling: Dual-Phase Prompt Design for Safety-Constrained Mental Health Language Models

ChainGeo: Enabling Effective Geometric Reasoning in Small VLMs through Interleaved Visual-Text Chains

Polymorphic: Plug-and-Play Visual Token Compression for Scalable VLMs