Guangyi Chen

7

Papers

31

Total Citations

Papers (7)

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees

Identification of Intermittent Temporal Latent Process

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition

S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment

Narrative Action Evaluation with Prompt-Guided Multimodal Interaction

CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process