Caixin Kang

Latest

• Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
• CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
• Multi-speaker Attention Alignment for Multimodal Social Interaction
• Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions