arXiv subjects

Albert Chen

Publications and source records attributed to Albert Chen.

11 recordsLinked to original sources

arXiv2026

SlimPer: Make Personalization Model Slim and Smart

Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for each pair without token-level supervision. Leveraging this observation, we propose SlimPer, which reformulates personalized ranking as iterative refinement of a compact, unified knowledge base. At each layer, the model selectively queries raw multi-modal user-side tokens, computes explicit relevance matching scores, and refines the knowledge base, all in O(N) per-layer cost with a fixed-size intermediate representation. As a result, model depth is decoupled from user history length, enabling deeper relevance understanding without proportional growth in compute or memory; request-only optimization further trims memory by sharing a single copy of user-side tokens across all candidate items. SlimPer unifies sparse, dense, and sequence features within a single backbone and provides inherent interpretability through its attention mechanism. Deployed on Instagram Reels and Feed, SlimPer yields measurable improvements in user engagement while streamlining the overall system and enabling effective modeling of 10k+ fine-grained user history events.

cs.IR↗

arXiv2025

Agentic Reinforcement Learning for Real-World Code Repair

We tackle the challenge of training reliable code-fixing agents in real repositories, where complex builds and shifting dependencies make evaluation unstable. We developed a verifiable pipeline with success defined as post-fix build validation and improved reproducibility across ~1K real issues by pinning dependencies and disabling automatic upgrades. Building on this, we introduced a scalable simplified pipeline for large-scale reinforcement learning (RL). Using this setup, we supervised fine-tuned Qwen3-32B in the full pipeline and applied RL on top of the SFT model in the simplified environment. The SFT model distilled from GPT-4.1 trajectories performs on par while being 56x smaller, and RL added 7-20% absolute gains under matched train-test conditions. "Thinking mode" was on par or worse in our experiments. Both SFT and RL models failed to generalize across environments, highlighting the importance of matching train-test environments for building reliable real-world code-fixing agents.

cs.LG↗

arXiv2025

ProCut: LLM Prompt Compression via Attribution Estimation

In large-scale industrial LLM systems, prompt templates often expand to thousands of tokens as teams iteratively incorporate sections such as task instructions, few-shot examples, and heuristic rules to enhance robustness and coverage. This expansion leads to bloated prompts that are difficult to maintain and incur significant inference latency and serving costs. To address this, we introduce Prompt Compression via Attribution Estimation (ProCut), a flexible, LLM-agnostic, training-free framework that compresses prompts through attribution analysis. ProCut segments prompt templates into semantically meaningful units, quantifies their impact on task performance, and prunes low-utility components. Through extensive experiments on five public benchmark datasets and real-world industrial prompts, we show that ProCut achieves substantial prompt size reductions (78% fewer tokens in production) while maintaining or even slightly improving task performance (up to 62% better than alternative methods). We further introduce an LLM-driven attribution estimator that reduces compression latency by over 50%, and demonstrate that ProCut integrates seamlessly with existing prompt-optimization frameworks to produce concise, high-performing prompts.

cs.CL↗

arXiv2025

Text-to-SQL for Enterprise Data Analytics

The introduction of large language models has brought rapid progress on Text-to-SQL benchmarks, but it is not yet easy to build a working enterprise solution. In this paper, we present insights from building an internal chatbot that enables LinkedIn's product managers, engineers, and operations teams to self-serve data insights from a large, dynamic data lake. Our approach features three components. First, we construct a knowledge graph that captures up-to-date semantics by indexing database metadata, historical query logs, wikis, and code. We apply clustering to identify relevant tables for each team or product area. Second, we build a Text-to-SQL agent that retrieves and ranks context from the knowledge graph, writes a query, and automatically corrects hallucinations and syntax errors. Third, we build an interactive chatbot that supports various user intents, from data discovery to query writing to debugging, and displays responses in rich UI elements to encourage follow-up chats. Our chatbot has over 300 weekly users. Expert review shows that 53% of its responses are correct or close to correct on an internal benchmark set. Through ablation studies, we identify the most important knowledge graph and modeling components, offering a practical path for developing enterprise Text-to-SQL solutions.

cs.CL↗

arXiv2024

tuGEMM: Area-Power-Efficient Temporal Unary GEMM Architecture for Low-Precision Edge AI

General matrix multiplication (GEMM) is a ubiquitous computing kernel/algorithm for data processing in diverse applications, including artificial intelligence (AI) and deep learning (DL). Recent shift towards edge computing has inspired GEMM architectures based on unary computing, which are predominantly stochastic and rate-coded systems. This paper proposes a novel GEMM architecture based on temporal-coding, called tuGEMM, that performs exact computation. We introduce two variants of tuGEMM, serial and parallel, with distinct area/power-latency trade-offs. Post-synthesis Power-Performance-Area (PPA) in 45 nm CMOS are reported for 2-bit, 4-bit, and 8-bit computations. The designs illustrate significant advantages in area-power efficiency over state-of-the-art stochastic unary systems especially at low precisions, e.g. incurring just 0.03 mm^2 and 9 mW for 4 bits, and 0.01 mm^2 and 4 mW for 2 bits. This makes tuGEMM ideal for power constrained mobile and edge devices performing always-on real-time sensory processing.

cs.AR↗

arXiv2024

tubGEMM: Energy-Efficient and Sparsity-Effective Temporal-Unary-Binary Based Matrix Multiply Unit

General Matrix Multiplication (GEMM) is a ubiquitous compute kernel in deep learning (DL). To support energy-efficient edge-native processing, new GEMM hardware units have been proposed that operate on unary encoded bitstreams using much simpler hardware. Most unary approaches thus far focus on rate-based unary encoding of values and perform stochastic approximate computation. This work presents tubGEMM, a novel matrix-multiply unit design that employs hybrid temporal-unary and binary (tub) encoding and performs exact (not approximate) GEMM. It intrinsically exploits dynamic value sparsity to improve energy efficiency. Compared to the current best unary design uGEMM, tubGEMM significantly reduces area, power, and energy by 89\%, 87\%, and 50\%, respectively. A tubGEMM design performing 128x128 matrix multiply on 8-bit integers, in commercial TSMC N5 (5nm) process node, consumes just 0.22 mm^2 die area, 417.72 mW power, and 8.86 uJ energy, assuming no sparsity. Typical sparsity in DL workloads (MobileNetv2, ResNet-50) reduces energy by more than 3x, and lowering precision to 4 and 2 bits further reduces it by 24x and 104x respectively.

cs.AR↗

arXiv2024

BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models

Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains. To enhance CLIP's performance while preserving the zero-shot paradigm, various test-time prompt tuning methods have been introduced to refine class embeddings through unsupervised learning objectives during inference. However, these methods often encounter challenges in selecting appropriate learning rates to prevent collapsed training in the absence of validation data during test-time adaptation. In this study, we propose a novel backpropagation-free algorithm BaFTA for test-time adaptation of vision-language models. Instead of fine-tuning text prompts to refine class embeddings, our approach directly estimates class centroids using online clustering within a projected embedding space that aligns text and visual embeddings. We dynamically aggregate predictions from both estimated and original class embeddings, as well as from distinct augmented views, by assessing the reliability of each prediction using R\'enyi Entropy. Through extensive experiments, we demonstrate that BaFTA consistently outperforms state-of-the-art test-time adaptation methods in both effectiveness and efficiency.

cs.CV↗

arXiv2023

ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation

Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data. However, while applying CLIP to a downstream target domain, the presence of visual and text domain gaps and cross-modality misalignment can greatly impact the model performance. To address such challenges, we propose ReCLIP, the first source-free domain adaptation method for vision-language models, which does not require any source data or target labeled data. ReCLIP first learns a projection space to mitigate the misaligned visual-text embeddings and learns pseudo labels, and then deploys cross-modality self-training with the pseudo labels, to update visual and text encoders, refine labels and reduce domain gaps and misalignments iteratively. With extensive experiments, we demonstrate ReCLIP reduces the average error rate of CLIP from 30.17% to 25.06% on 22 image classification benchmarks. Code available at https://github.com/michiganleon/ReCLIP_WACV.

cs.CV↗

arXiv2022

Greykite: Deploying Flexible Forecasting at Scale at LinkedIn

Forecasts help businesses allocate resources and achieve objectives. At LinkedIn, product owners use forecasts to set business targets, track outlook, and monitor health. Engineers use forecasts to efficiently provision hardware. Developing a forecasting solution to meet these needs requires accurate and interpretable forecasts on diverse time series with sub-hourly to quarterly frequencies. We present Greykite, an open-source Python library for forecasting that has been deployed on over twenty use cases at LinkedIn. Its flagship algorithm, Silverkite, provides interpretable, fast, and highly flexible univariate forecasts that capture effects such as time-varying growth and seasonality, autocorrelation, holidays, and regressors. The library enables self-serve accuracy and trust by facilitating data exploration, model configuration, execution, and interpretation. Our benchmark results show excellent out-of-the-box speed and accuracy on datasets from a variety of domains. Over the past two years, Greykite forecasts have been trusted by Finance, Engineering, and Product teams for resource planning and allocation, target setting and progress tracking, anomaly detection and root cause analysis. We expect Greykite to be useful to forecast practitioners with similar applications who need accurate, interpretable forecasts that capture complex dynamics common to time series related to human activity.

cs.LG↗

arXiv2021

A flexible forecasting model for production systems

This paper discusses desirable properties of forecasting models in production systems. It then develops a family of models which are designed to satisfy these properties: highly customizable to capture complex patterns; accommodates a large variety of objectives; has interpretable components; produces robust results; has automatic changepoint detection for trend and seasonality; and runs fast -- making it a good choice for reliable and scalable production systems. The model allows for seasonality at various time scales, events/holidays, and change points in trend and seasonality. The volatility is fitted separately to maintain flexibility and speed and is allowed to be a function of specified features.

stat.ME↗

arXiv2020

Influence Maximization with Spontaneous User Adoption

We incorporate self activation into influence propagation and propose the self-activation independent cascade (SAIC) model: nodes may be self activated besides being selected as seeds, and influence propagates from both selected seeds and self activated nodes. Self activation reflects the real-world scenarios such as people naturally share product recommendations with their friends even without marketing intervention. It also leads to two new forms of optimization problems: (a) {\em preemptive influence maximization (PIM)}, which aims to find $k$ nodes that, if self-activated, can reach the most number of nodes before other self-activated nodes; and (b) {\em boosted preemptive influence maximization (BPIM)}, which aims to select $k$ seeds that are guaranteed to be activated and can reach the most number of nodes before other self-activated nodes. We propose scalable algorithms for PIM and BPIM and prove that they achieve $1-\varepsilon$ approximation for PIM and $1-1/e-\varepsilon$ approximation for BPIM, for any $\varepsilon > 0$. Through extensive tests on real-world graphs, we demonstrate that our algorithms outperform the baseline algorithms significantly for the PIM problem in solution quality, and also outperform the baselines for BPIM when self-activation behaviors are non-uniform across nodes.

cs.SI↗