papers

Publications (15)

cs.CV2025

SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models

Yichen Shi, Yuhao Gao, Yingxin Lai +7

Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-related tasks, capitalizing on their visual semantic comprehension and reasoning capabiliti…

gr-qc2016

Photon Emission Near Extreme Kerr Black Holes

Achilleas P. Porfyriadis, Yichen Shi, Andrew Strominger

Ongoing astronomical efforts extract physical properties of black holes from electromagnetic emissions in their near-vicinity. This requires finding the null geodesics which extend…

cs.AR2025

Automated SAR ADC Sizing Using Analytical Equations

Zhongyi Li, Zhuofu Tao, Yanze Zhou +4

Conventional analog and mixed-signal (AMS) circuit designs heavily rely on manual effort, which is time-consuming and labor-intensive. This paper presents a fully automated design…

cs.CV2026

CL-VISTA: Benchmarking Continual Learning in Video Large Language Models

Haiyang Guo, Yichen Shi, Fei Zhu +6

Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundat…

cs.CV2025

FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models

Hongyang Wang, Yichen Shi, Zhuofu Tao +7

Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking…

cs.AI2024

AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG

Yichen Shi, Zhuofu Tao, Yuhao Gao +9

High-performance analog and mixed-signal (AMS) circuits are mainly full-custom designed, which is time-consuming and labor-intensive. A significant portion of the effort is experie…

cs.CV2026

FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing

Hongyang Wang, Yichen Shi, Hongrui Li +3

The paper introduces FAS-R1, a two‑stage multimodal large language model that simultaneously classifies face authenticity, identifies attack types, and localizes spoof regions, usi…

#face anti-spoofing#multimodal large language models#reasoning#attack type recognition
hep-th2020

Polarization Whorls from M87* at the Event Horizon Telescope

Delilah Gates, Daniel Kapec, Alexandru Lupsasca +2

The Event Horizon Telescope (EHT) is expected to soon produce polarimetric images of the supermassive black hole at the center of the neighboring galaxy M87. There are indications…

cs.AI2026

Symbol and Footprint Database for Electronic Components by Agentic Recognition and Generation

Yichen Shi, Yuzhi Liu, Zhuofu Tao +4

A rich and recognizable component library is the cornerstone of printed circuit board (PCB) design and generation. Traditionally, engineers manually create symbols and footprints a…

gr-qc2018

Critical Emission from a High-Spin Black Hole

Alexandru Lupsasca, Achilleas P. Porfyriadis, Yichen Shi

We consider a rapidly spinning black hole surrounded by an equatorial, geometrically thin, slowly accreting disk that is stationary and axisymmetric. We analytically compute the br…

cs.CV2026

UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning

Hongrui Li, Yichen Shi, Hongyang Wang +4

Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminative or prompt-based methods l…

cs.CV2025

AMSnet 2.0: A Large AMS Database with AI Segmentation for Net Detection

Yichen Shi, Zhuofu Tao, Yuhao Gao +5

Current multimodal large language models (MLLMs) struggle to understand circuit schematics due to their limited recognition capabilities. This could be attributed to the lack of hi…

cs.LG2025

AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits

Yichen Shi, Ze Zhang, Hongyang Wang +10

Analog/Mixed-Signal (AMS) circuits play a critical role in the integrated circuit (IC) industry. However, automating Analog/Mixed-Signal (AMS) circuit design has remained a longsta…

cs.AR2026

AMSnet-q: Unsupervised Circuit Identification and Performance Labeling for AMS Circuits

Ze Zhang, Junzhuo Zhou, Yichen Shi +6

Analog and mixed-signal (AMS) circuit design remains heavily reliant on expert knowledge. While recent AI-driven automation tools can generate candidate topologies, they critically…

cs.CV2024

AMSNet: Netlist Dataset for AMS Circuits

Zhuofu Tao, Yichen Shi, Yiru Huo +8

Today's analog/mixed-signal (AMS) integrated circuit (IC) designs demand substantial manual intervention. The advent of multimodal large language models (MLLMs) has unveiled signif…