activity
20242026
collaborators

6 papers

cs.LG2026

Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting

Junyi Ye, Ivy Gateri Wanjiku

Financial forecasting models are typically developed in full precision, yet production deployment often requires low-precision inference to reduce memory and computational cost. Po…

q-fin.ST2026

Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting

Junyi Ye, Gargi Vijay Borde

Financial volatility is regime dependent, yet incorporating regime information into neural networks can also destabilize training. This paper asks where such information should ent…

cs.MA2026

From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems

Jiayi Chen, Junyi Ye, Guiling Wang

Compound AI Systems (CAIS) are an emerging paradigm that integrates large language models (LLMs) with external components, including retrievers, agents, tools, and orchestrators, t…

cs.CV2025

Illusions in Humans and AI: How Visual Perception Aligns and Diverges

Jianyi Yang, Junyi Ye, Ankan Dash +1

By comparing biological and artificial perception through the lens of illusions, we highlight critical differences in how each system constructs visual reality. Understanding these…

cs.CL2025

From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problems

A M Muntasir Rahman, Junyi Ye, Wei Yao +5

Consider the math problem: "Lily received 3 cookies from her best friend yesterday and ate 5 for breakfast. Today, her friend gave her 3 more cookies. How many cookies does Lily ha…

cs.CV2024

Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding

Junyi Ye, Ankan Dash, Wenpeng Yin +1

Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i…