arXiv subjects

Alex Li

Publications and source records attributed to Alex Li.

7 recordsLinked to original sources

arXiv2026

BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation

Police body-worn camera (BWC) footage has emerged as a critical aspect of law enforcement that ensures legal transparency, officer accountability, and the protection of civil rights. However, effectively processing this data remains a significant challenge due to its multimodal video format. BWC videos, in many cases, comprise chaotic scenes with low visual quality, rapid movement/interactions, and high-noise audio that make visual understanding a challenge for even SOTA multimodal models. Current Vision-Language Models (VLMs) frequently overlook critical forensic details, such as the presence of valuable evidence or the latent nuances of suspect-officer interactions, which are vital for fair legal outcomes and civilian/officer safety. To address these limitations, we propose an Adaptive Visual Question Answering (VQA) framework engineered for high-stakes law enforcement. Our framework employs a structured reasoning approach to extract fine-grained visual evidence that traditional captioning systems fail to capture. We experiment with multiple question generation models, including foundation models and fine-tuned open-weight models, to observe performance variation among question generation model implementations. Our results demonstrate that this VQA-driven architecture provides a more reliable, objective, and detailed record of enforcement events, ultimately serving as a powerful tool to protect both law enforcement officers and the public through AI-assisted forensic clarity.

cs.CV↗

arXiv2026

MIRAI: Prediction and Generation of High-Impact Academic Research

The rapid pace of scientific publishing has made the identification and synthesis of high-impact work an increasingly urgent challenge. We introduce MIRAI (Multi-year Inference of Research trends and Academic Impact), a deep learning framework that predicts paper impact using only it's title, abstract, and publication date. We train MIRAI on the arXiv academic graph to predict 5-year PageRank and citation counts, achieving Spearman's $\rho$ of 0.4686 on PageRank prediction and 0.6192 on citation prediction for papers published in 2021. We propose a research ideation pipeline built on top of MIRAI that produces research ideas oriented towards high impact. These ideas were judged as more impactful than a baseline without MIRAI by an unbiased LLM judge at a 4:3 ratio. We make the 5-year citation prediction model publicly available at https://predict-paper-impact.vercel.app.

cs.DL↗

arXiv2026

Unified Learning-to-Rank for Multi-Channel Retrieval in Large-Scale E-Commerce Search

Large-scale e-commerce search must surface a broad set of items from a vast catalog, ranging from bestselling products to new, trending, or seasonal items. Modern systems therefore rely on multiple specialized retrieval channels to surface products, each designed to satisfy a specific objective. A key challenge is how to effectively merge documents from these heterogeneous channels into a single ranked list under strict latency constraints while optimizing for business KPIs such as user conversion. Rank-based fusion methods such as Reciprocal Rank Fusion (RRF) and Weighted Interleaving rely on fixed global channel weights and treat channels independently, failing to account for query-specific channel utility and cross-channel interactions. We observe that multi-channel fusion can be reformulated as a query-dependent learning-to-rank problem over heterogeneous candidate sources. In this paper, we propose a unified ranking model that learns to merge and rank documents from multiple retrieval channels. We formulate the problem as a channel-aware learning-to-rank task that jointly optimizes clicks, add-to-carts, and purchases while incorporating channel-specific objectives. We further incorporate recent user behavioral signals to capture short-term intent shifts that are critical for improving conversion in multi-channel ranking. Our online A/B experiments show that the proposed approach outperforms rank-based fusion methods, leading to a +2.85\% improvement in user conversion. The model satisfies production latency requirements, achieving a p95 latency of under 50\,ms, and is deployed on Target.com.

cs.IR↗

arXiv2025

OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation

Traditional recommendation systems suffer from inconsistency in multi-stage optimization objectives. Generative Recommendation (GR) mitigates them through an end-to-end framework; however, existing methods still rely on matching mechanisms based on inductive patterns. Although responsive, they lack the ability to uncover complex user intents that require deductive reasoning based on world knowledge. Meanwhile, LLMs show strong deep reasoning capabilities, but their latency and computational costs remain challenging for industrial applications. More critically, there are performance bottlenecks in multi-scenario scalability: as shown in Figure 1, existing solutions require independent training and deployment for each scenario, leading to low resource utilization and high maintenance costs-a challenge unaddressed in GR literature. To address these, we present OxygenREC, an industrial recommendation system that leverages Fast-Slow Thinking to deliver deep reasoning with strict latency and multi-scenario requirements of real-world environments. First, we adopt a Fast-Slow Thinking architecture. Slow thinking uses a near-line LLM pipeline to synthesize Contextual Reasoning Instructions, while fast thinking employs a high-efficiency encoder-decoder backbone for real-time generation. Second, to ensure reasoning instructions effectively enhance recommendation generation, we introduce a semantic alignment mechanism with Instruction-Guided Retrieval (IGR) to filter intent-relevant historical behaviors and use a Query-to-Item (Q2I) loss for instruction-item consistency. Finally, to resolve multi-scenario scalability, we transform scenario information into controllable instructions, using unified reward mapping and Soft Adaptive Group Clip Policy Optimization (SA-GCPO) to align policies with diverse business objectives, realizing a train-once-deploy-everywhere paradigm.

cs.IR↗

arXiv2025

Large Scale Retrieval for the LinkedIn Feed using Causal Language Models

In large scale recommendation systems like the LinkedIn Feed, the retrieval stage is critical for narrowing hundreds of millions of potential candidates to a manageable subset for ranking. LinkedIn's Feed serves suggested content from outside of the member's network (based on the member's topical interests), where 2000 candidates are retrieved from a pool of hundreds of millions candidate with a latency budget of a few milliseconds and inbound QPS of several thousand per second. This paper presents a novel retrieval approach that fine-tunes a large causal language model (Meta's LLaMA 3) as a dual encoder to generate high quality embeddings for both users (members) and content (items), using only textual input. We describe the end to end pipeline, including prompt design for embedding generation, techniques for fine-tuning at LinkedIn's scale, and infrastructure for low latency, cost effective online serving. We share our findings on how quantizing numerical features in the prompt enables the information to get properly encoded in the embedding, facilitating greater alignment between the retrieval and ranking layer. The system was evaluated using offline metrics and an online A/B test, which showed substantial improvements in member engagement. We observed significant gains among newer members, who often lack strong network connections, indicating that high-quality suggested content aids retention. This work demonstrates how generative language models can be effectively adapted for real time, high throughput retrieval in industrial applications.

cs.IR↗

arXiv2024

Volatility Forecasting in Global Financial Markets Using TimeMixer

Predicting volatility in financial markets, including stocks, index ETFs, foreign exchange, and cryptocurrencies, remains a challenging task due to the inherent complexity and non-linear dynamics of these time series. In this study, I apply TimeMixer, a state-of-the-art time series forecasting model, to predict the volatility of global financial assets. TimeMixer utilizes a multiscale-mixing approach that effectively captures both short-term and long-term temporal patterns by analyzing data across different scales. My empirical results reveal that while TimeMixer performs exceptionally well in short-term volatility forecasting, its accuracy diminishes for longer-term predictions, particularly in highly volatile markets. These findings highlight TimeMixer's strength in capturing short-term volatility, making it highly suitable for practical applications in financial risk management, where precise short-term forecasts are critical. However, the model's limitations in long-term forecasting point to potential areas for further refinement.

q-fin.ST↗

arXiv2022

TransPOS: Transformers for Consolidating Different POS Tagset Datasets

In hope of expanding training data, researchers often want to merge two or more datasets that are created using different labeling schemes. This paper considers two datasets that label part-of-speech (POS) tags under different tagging schemes and leverage the supervised labels of one dataset to help generate labels for the other dataset. This paper further discusses the theoretical difficulties of this approach and proposes a novel supervised architecture employing Transformers to tackle the problem of consolidating two completely disjoint datasets. The results diverge from initial expectations and discourage exploration into the use of disjoint labels to consolidate datasets with different labels.

cs.CL↗