I’m Jheng-Hong (Matt) Yang, an engineer and researcher building agentic systems around data systems. My recent work explores how strong language models can search, inspect evidence, and reason more effectively, which led to Pi-serini, a minimal search agent for building reliable, cost-efficient deep-research workflows.
I previously pursued doctoral research in computer science at the University of Waterloo, where I worked on information retrieval, neural ranking, conversational search, and multimodal retrieval. Before that, I conducted research at Academia Sinica on recommender systems and data-driven modeling. My earlier training was in physics and electrical engineering: I received a B.S. in Electrophysics and an M.Sc. in Electrical Engineering from National Chiao Tung University, then worked in TSMC R&D on semiconductor device modeling.
I am currently building Stencilzeit for consulting, engineering, and technical services around data systems and agentic AI. I enjoy building systems that are secure, fast, scalable, delightful to use, and ethically designed to serve the greater good.
Feel free to reach out at jhyang [at] stencilzeit [dot] com with ideas or collaborations.
The Anserini IR toolkit has come a long way since efforts began in 2015. Although the goals of the project - to bridge research and practice in information retrieval, and to provide reproducible, easy-to-use baselines - have remained constant, the world has...
This paper examines the integration of images into Wikipedia articles by evaluating image–text retrieval tasks in multimedia content creation, focusing on developing retrieval-augmented tools to enhance the creation of high-quality multimedia articles. Desp...
Vision–Language Models (VLMs) have demonstrated success across diverse applications, yet their potential to assist in relevance judgments remains uncertain. This paper assesses the relevance estimation capabilities of VLMs, including CLIP, LLaVA, and GPT-4V...
BEIR is a benchmark dataset originally designed for zero-shot evaluation of retrieval models across 18 different domain/task combinations. In recent years, we have witnessed the growing popularity of models based on representation learning, which naturally ...
Neural retrievers have been shown to be effective for math-aware search. Their ability to cope with math symbol mismatches, to represent highly contextualized semantics, and to learn effective representations are critical to improving math information retri...
This paper presents the AToMiC (Authoring Tools for Multi media Content) dataset, designed to advance research in image/text cross-modal retrieval. While vision–language pretrained transformers have led to significant improvements in retrieval effectiveness...
BEIR is a benchmark dataset for zero-shot evaluation of information retrieval models across 18 different domain/task combinations. In recent years, we have witnessed the growing popularity of a representation learning approach to building retrieval models, ...
The advent of multilingual language models has generated a resurgence of interest in cross-lingual information retrieval (CLIR), which is the task of searching documents in one language with queries from another. However, the rapid pace of progress has led ...
This paper presents an exploration of evaluating image–text retrieval tasks designed for multimedia content creation, with a particular focus on the dynamic interplay among various modalities, including text and images. The study highlights the pivotal role...
This publication page is generated from bibliography/papers.bib.Edit the BibTeX entry and run uv run python scripts/generate_publications.py to update it.
With the recent success of dense retrieval methods based on bi-encoders, studies have applied this approach to various interesting downstream retrieval tasks with good efficiency and in-domain effectiveness. Recently, we have also seen the presence of dense...
Default analysis plays an essential role in financial markets because it narrows the information gap between borrowers and lenders. Of late, machine learning-based methods have found their way to default analysis and typically view it as a risk classificati...
Sparse lexical representation learning has demonstrated much progress in improving passage retrieval effectiveness in recent models such as DeepImpact, uniCOIL, and SPLADE. This paper describes a straightforward yet effective approach for sparsifying lexica...
This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising conversational quer...
Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad hoc information retrieval (IR) systems due to the coreference and omission resolution problems inher...
We present an efficient training approach to text retrieval with dense representations that applies knowledge distillation using the ColBERT late-interaction ranking model. Specifically, we propose to transfer the knowledge from a bi-encoder teacher to a st...
Chatty Goose is an open-source Python conversational search framework that provides strong, reproducible reranking pipelines built on recent advances in neural models. The framework comprises extensible modular components that integrate with popular librari...
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations. It aims to provide effective, reproducible, and easy-to-use first-stage retrieval in a multi-stage ranking architecture. Our toolkit is self-...
Recently, much progress in natural language processing has been driven by deep contextualized representations pretrained on large corpora. Typically, the fine-tuning on these pretrained models for a specific downstream task is based on single-view learning,...
A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder dense retrieval (D...
Pyserini is an easy-to-use Python toolkit that supports replicable IR research by providing effective first-stage retrieval in a multi-stage ranking architecture. Our toolkit is self-contained as a standard Python package and comes with queries, relevance j...
While internalized “implicit knowledge” in pretrained transformers has led to fruitful progress in many natural language understanding tasks, how to most effectively elicit such knowledge remains an open question. Based on the text-to-text transfer transfor...
We present an approach to ranking with dense representations that applies knowledge distillation to improve the recently proposed late-interaction ColBERT model. Specifically, we distill the knowledge from ColBERT’s expressive MaxSim operator for computing ...
This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). We leverage PLMs to address the strong token-to-token independence assumption made in the co...
We applied the T5 sequence-to-sequence model to tackle the AI2 WinoGrande Challenge by decomposing each example into two input text strings, each containing a hypothesis, and using the probabilities assigned to the “entailment” token as a score of the hypot...
This notebook describes our participation (h2oloo) in TREC CAsT 2020. We first illustrate our multi-stage pipeline for conversational search: sequence-to-sequence query reformulation followed by an ad hoc text ranking pipeline; then, detail our proposed met...
Passage retrieval in a conversational context is essential for many downstream applications; it is however extremely challenging due to limited data resources. To address this problem, we present an effective multi-stage pipeline for passage ranking in conv...
In this paper, we present our methods, experimental analysis, and final submissions for the Conversational Assistance Track (CAsT) at TREC 2019. In addition to language understanding, extracting knowledge from historical dialogues (eg, previous queries, sea...
Recommender systems are vital ingredients for many e-commerce services. In the literature, two of the most popular approaches are based on factorization and graph-based models; the former approach captures user preferences by factorizing the observed direct...