arXiv subjects

Yinjie Huang

Publications and source records attributed to Yinjie Huang.

4 recordsLinked to original sources

arXiv2026

Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale

Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-scale iterations on a self-contained program. Online autoresearch instead spans asynchronous systems, hours-long variants, and weeks-long campaigns that can influence a product. A completed run can still support an invalid conclusion when a code change is a no-op, data windows leak, evaluator semantics drift, or the two arms traverse different serving funnels. We present EvoPilot, a human-gated method for long-horizon online autoresearch. Role-specific agents execute each round through a versioned domain skill and typed adapter. Durable records preserve experiments and failures; deterministic checks enforce recorded lessons. We study a 37-day campaign for the retrieval system that powers Video Deep Dive (VDD), an online experience for discovering follow-on videos after a user opens a seed video. The campaign covered seven directions and used an hourly refreshed index of hundreds of millions of videos. Earlier manual experiments had not established a benefit from an interaction head. A primitive autoresearch attempt revisited the direction but incorrectly attributed an offline hit-rate decline of 22 percentage points to the head. We then introduced EvoPilot. Its human-gated verification traced the drop to a pre-existing evaluation defect that produced output depths of 3,000 and 600. After repair, a matched comparison measured an offline improvement of 3.20 percentage points. Post-study replay and mutation tests rejected invalid comparisons while admitting valid counterparts. Durable state recovered an interrupted round, and artifact reuse avoided approximately five GPU-hours. Separately, a seven-day randomized online evaluation estimated a 0.66% relative increase in the VDD slice of Good Search Result Rate for Retention (GSRR).

cs.IR↗

arXiv2026

Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale

Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, expressive personalization for queries with rich user intent, and broad coverage of a massive inventory under fixed latency and resource budgets. We characterize this as the personalization-scale paradox: hosting the full serving inventory in GPU memory is too resource intensive, while CPU compute cannot execute the same interaction-heavy model on the latency-critical path. We present a hybrid GPU-CPU co-serving system that resolves the paradox through orchestration rather than a new model class. A high-depth GPU pathway fuses retrieval and interaction pre-ranking over a curated online pool on the order of a billion documents, while a high-breadth CPU pathway searches an independently selected online inventory roughly twenty times larger with lightweight personalized scoring. Either or both pathways can run per request; candidates are deduplicated before shared downstream ranking. The system is deployed in production. A full-system A/B test against the legacy CPU-only configuration improves model-scored relevance and substantive engagement, while separate pathway experiments show positive value at their own deployment scopes. Retrieval logs show that the pathways contribute structurally distinct candidates, production serving measurements characterize their latency, and a matched capacity plan quantifies the economic rationale for assigning modeling depth to GPUs and inventory breadth to CPUs. Together, these results validate a practical, independently evolvable depth-breadth architecture for ultra-large-scale personalized search.

cs.IR↗

arXiv2019

Learning Hash Function through Codewords

In this paper, we propose a novel hash learning approach that has the following main distinguishing features, when compared to past frameworks. First, the codewords are utilized in the Hamming space as ancillary techniques to accomplish its hash learning task. These codewords, which are inferred from the data, attempt to capture grouping aspects of the data's hash codes. Furthermore, the proposed framework is capable of addressing supervised, unsupervised and, even, semi-supervised hash learning scenarios. Additionally, the framework adopts a regularization term over the codewords, which automatically chooses the codewords for the problem. To efficiently solve the problem, one Block Coordinate Descent algorithm is showcased in the paper. We also show that one step of the algorithms can be casted into several Support Vector Machine problems which enables our algorithms to utilize efficient software package. For the regularization term, a closed form solution of the proximal operator is provided in the paper. A series of comparative experiments focused on content-based image retrieval highlights its performance advantages.

cs.LG↗

arXiv2015

Hash Function Learning via Codewords

In this paper we introduce a novel hash learning framework that has two main distinguishing features, when compared to past approaches. First, it utilizes codewords in the Hamming space as ancillary means to accomplish its hash learning task. These codewords, which are inferred from the data, attempt to capture similarity aspects of the data's hash codes. Secondly and more importantly, the same framework is capable of addressing supervised, unsupervised and, even, semi-supervised hash learning tasks in a natural manner. A series of comparative experiments focused on content-based image retrieval highlights its performance advantages.

cs.LG↗