Weik Zhu

More opportunities

12

🚀 I'm excited to share that our paper, "Enhancing E-commerce Product Title Translation with Retrieval-Augmented Generation and Large Language Models," has been accepted at CIKM 24' - Data-centric AI. Thanks for the co-authors Stephan Walter and Taichi Nakatani for the collaboration! 😀 Our study explores how we can improve the machine translation of e-commerce product titles using LLMs, particularly languages that the LLMs do not primarily support. The results of our experiments show that our proposed approach leverages large volumes of bilingual product data, and utilizes a probabilistic retrieval model to retrieve similar bilingual product information for few-shot learning, can improve overall product title translation quality by up to +15.3% in chrF scores. Notably, we observe that language pairs where the LLM has limited proficiency can benefit the most from our method, addressing a common challenge in this domain. As new and more capable LLMs continue to emerge, our RAG-based approach allows for the quick integration of these models (without extensive fine-tuning). By using the large volume of bilingual product data, including titles, bullet points, and descriptions, as few-shot learning examples, our method provides a flexible and adaptable solution that is particularly suitable for industrial applications, where the ability to keep pace with changing requirements is crucial. #amazonscience #LLM #CIKM #RAG #machinetranslation #searchengine #ecommerce #translation #GenerativeAI #search #MultilingualSearch #mixtral #localization #retail

66

2 Comments

📖 Exploring Non-Stationary User Behavior in Recommendation Systems Continuing my dive into ByteDance's "Monolith: Real-Time Recommendation System with Collisionless Embedding Table", I’ve come across a crucial challenge: non-stationary distribution—also known as Concept Drift. Unlike visual or linguistic data, which changes over centuries, a user's interests can shift in just minutes. This dynamic behavior makes it difficult for recommendation systems to keep up. 🧠 Why It Matters: Traditional systems struggle because they don’t update fast enough to reflect these real-time changes in user behavior. Monolith addresses this by: Collisionless Embedding: A smarter design that avoids data collisions using a dynamic hash table, improving the use of sparse features. Real-Time Feedback: The system loops user interactions back into training immediately, allowing the model to continuously update and adapt. 🚀 Results: Monolith not only reduces memory usage but also boosts performance (state-of-the-art AUC) without overwhelming server resources. This real-time adaptability is key for delivering more personalized, accurate recommendations! From next post, we will start discussing the design of this system. Keep learning, Keep growing ! Image source : https://lnkd.in/g42JiYKY #AI #RecommendationSystems #ConceptDrift #MachineLearning #DataScience #RealTimeAI #TechInnovation #Monolith #ByteDance #Scalability #LearningJourney

3

Hi LinkedIn Community,   Short version:  Grad student building low-code tool for ML data pipelines. Goal: Make ML dev work enjoyable again, not just endless debugging. Ask: Shadow sessions (see Calendly link below) Longer version: As ML devs, we often leave the office thinking, “Do I actually love doing my work?” because we had spent most of the day on inefficient whack-a-mole debugging and maintenance work. I want to get us back to where we can love coding for those reasons we originally chose to pick up coding in the first place.   A lot of AI tools are restrictive and end up mangling codebases, and I believe the current state of AI coupled with strong design principles can enable much better code native developer experiences. I’ve gone through prototypes/testing and have some competing hypotheses. I’d love to observe coders working on ML data pipelines (happy to sign NDAs if necessary, can also be personal projects instead). If you're open to sharing your expertise, please schedule a shadow session: https://lnkd.in/eBW6p6qE Let's make ML data development more efficient and actually enjoyable! #MachineLearning #DataPipelines #LowCode #DevTools #AI #SoftwareEngineering #GradStudent #Research #MLOps #DataScience #ArtificialIntelligence #ProductivityTools #DeveloperExperience #CodeQuality #TechInnovation #ComputerScience #DataEngineering #CloudComputing

84

8 Comments

Unlock the full potential of your Large Language Models (LLMs) with Intel® Extension for PyTorch (IPEX) and the Intel® LLM Library for PyTorch (IPEX-LLM). Download this whitepaper to explore the optimization of LLMs, including their performance, resource utilization, and response times in real-world applications. Link - https://intel.ly/3BBJ4ey

1

Celebrating two papers accepted this week! First, my internship work with AWS on "Tackling Missing Modalities in Audio-Visual Representation Learning Using Masked Autoencoders", where we propose curriculum Masked Autoencoders to deal with partially missing modalities during inference, accepted in Interspeech 2024. Then, my work on tracking and quantifying the emotional bias of LLMs arising from the "pull" of their prior knowledge (https://lnkd.in/d7RUwdPd) was accepted in ACII 2024.

78

I'm excited to share two papers from the Retrieval team at Walmart that were presented at CIKM last week. They're both about improving the relevance of Embedding-Based Retrieval. 𝗥𝗲𝗹𝗲𝘃𝗮𝗻𝗰𝗲 𝗙𝗶𝗹𝘁𝗲𝗿𝗶𝗻𝗴 𝗳𝗼𝗿 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴-𝗯𝗮𝘀𝗲𝗱 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹. https://lnkd.in/gNQe7QhA The first is about how to intelligently choose a query-dependent cutoff on the cosine score to remove irrelevant items from the retrieved set. Since cosine scores aren't comparable across queries, we introduce a "Cosine Adapter" to map the scores to interpretable scores. 𝗘𝗻𝗵𝗮𝗻𝗰𝗶𝗻𝗴 𝗥𝗲𝗹𝗲𝘃𝗮𝗻𝗰𝗲 𝗼𝗳 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴-𝗯𝗮𝘀𝗲𝗱 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗮𝘁 𝗪𝗮𝗹𝗺𝗮𝗿𝘁. https://lnkd.in/gdqkc2hR The second is about model training techniques we learned to improve the relevance of embedding models. In particular, we describe how to use a teacher model to provide relevance labels for training Juexin (Joy) Lin Nicholas Rossi, PhD Feng LIU Zhen Yang Sachin Yadav Praveen Reddy Suram Satya Chembolu Prijith Chandran Hrushikesh Mohapatra Alessandro Magnani Ciya Liao

139

1 Comment

I have been always fascinated by optimization algorithms used in ML and Deep Learning. From the simplicity of SGD, momentum etc. to more involved ones such as conjugate gradient, adagrad, adam etc. Among all of these I found one very interesting algorithm L-BFGS. Truth is L-BFGS is not actually a different algorithm but it is an optimization technique to 2nd order Newton approach. In fact L-BFGS has been widely applied across multiple different problems such as conditional random fields, language translation, speech recognition, LLM + Transformers, dynamic pricing and other optimization problems. I have been using it regularly in my work at Microsoft for dynamic pricing. Initially, found it very hard to understand L-BFGS basics from resources over the internet. In these 2 medium posts, I write about the basics of L-BFGS, implement from scratch in Python and improve it using automatic differentiation (again written from scratch). Hope people in ML and AI will find it useful. https://lnkd.in/g7ybeD3N https://lnkd.in/gCHWssv2 #machinelearning #artificialintelligence #optimization #dataengineering #algorithms

9

3 Comments

📣 📣 📣 [CFP; MRR 2024 Workshop @ SIGIR 2024 Conference]We're excited to invite researchers and practitioners across the spectrum of multimodal modeling, representation learning, and retrieval  to participate in our workshop on "Multimodal Representation and Retrieval." This event is proudly organized in association with SIGIR 2024. Multimodal data is available in many applications like e-commerce production listings, social media posts and short videos. However, existing algorithms dealing with those types of data still focus on uni-modal representation learning by vision-language alignment and cross-modal retrieval. In this workshop, we target to bring a new retrieval problem where both queries and documents are multimodal. With the popularity of vision language modeling,  large language models (LLMs), retrieval augmented generation (RAG), and multimodal LLM, we see a lot of new opportunities for multimodal representation and retrieval tasks. This event will be a comprehensive half-day workshop focusing on the subject of multimodal representation and retrieval. The agenda includes keynote speeches, oral presentations, and an interactive panel discussion. Our objective with this workshop is to capture the interest of researchers in this emerging challenge. By highlighting the novelty and significance of the problem, we aim to attract researchers who are eager to explore and contribute to this field. Join us as we welcome esteemed speakers including Tat-Seng Chua (National University of Singapore), and Dinesh Manocha (University of Maryland), who will share their invaluable insights and expertise. We invite original research & industrial application papers that present research on multimodal data representation and retrieval. 🔗 Workshop website: https://lnkd.in/gcpZtrdc 📅 Submission Deadline: May 5, 2024 (11:59 pm, AOE) 📅 Workshop Date: July 18th, 2024 🌆 Workshop Location: Washington D.C., USA Join us to shape the future of multimodal representation, retrieval, and related applications! ☀ My co-organizers Arnab Dhua (Amazon), Douglas Gray (Amazon), I. Zeki Yalniz (Meta), Tan Yu (Nvidia), Mohamed Elhoseiny (KAUST), Bryan A. Plummer (Boston University) and I look forward to hosting you.

73

4 Comments

I still remember the early days of my career as a Machine Learning engineer, navigating various sites looking for data -- Github, Kaggle, UCI, you name it. One particular project comes to mind—a predictive analytics tool for early diagnosis of diabetic retinopathy. Despite the importance and potential impact of the project, we hit a major roadblock: insufficient data. The patient data we had was not only limited but also fraught with privacy concerns. This challenge was an eye-opener, underscoring the critical need for synthetic data in healthcare. Now, that I see multiple services are offering synthetic data. Synthetic data is artificially generated rather than obtained by direct measurement. It mirrors the statistical properties of real-world data, making it a powerful tool in scenarios where data is scarce, sensitive, or difficult to collect. Today we have LLMs, especially GPT-4 that can generate domain-specific (textual) data. Many LLMs are even finetuned and benchmarked using synthetic data generated from GPT-4. But, how can you start and what are some of the best practices? Here are some of the key points that you must consider: 1. Define Clear Objectives: Understand the purpose of generating synthetic data. Whether it's for augmenting training datasets, finetuning like I mentioned preserving privacy, or creating data for underrepresented scenarios, clarity in objectives is crucial. 2. Choose the Right Model: Today, there are various LLMs, according to your budget choose them wisely. GPT-4, Claude, Mistral, LLaMA, etc all good but some are expensive and others are free. If you are low on budget and low on requirements then an open-source model with free Kaggle or Colab support will do. But if you are required to generate a huge amount of data then you might need to spend a little on storage. Keep in mind that running open-source LLMs might require you to spend money because they are very large and require extra storage and computing power. 3. Ensure Data Quality: This is where your model will be tested. Synthetic data should mirror the statistical properties of real-world data. Regular validation against real data ensures the synthetic data’s utility and realism. 4. Maintain Privacy: One of the primary benefits of synthetic data is enhanced privacy. Ensure that the generation process and the synthetic data itself do not inadvertently expose sensitive information. In any case research thoroughly and choose the model according to your requirements. I have attached a code snippet that might help you understand how to generate synthetic and also how to design a productive prompt. The link to the original code can be found in the comment section.

19

7 Comments

Master Advanced Information Retrieval: Cutting-edge Techniques to Optimize the Selection of Relevant Documents with Langchain to Create Excellent RAGs #llm #llmops #chstgpt4 #gemini #mlops #aiml https://lnkd.in/dSsjgsX5

10

Chip Huyen on Twitter today below. I 100% agree. Metric hygiene is system hygiene. LLM-Generated metrics require a higher standard of care than they're currently receiving, and much more scrutiny. Mind the compasses. 🐦  A big issue I see with AI systems is that people aren't spending enough time evaluating their evaluation pipeline. 1. Most teams use more than one metrics (3-7 metrics in general) to evaluate their applications, which is a good practice. However, very few are measuring the correlation between these metrics.If two metrics are perfectly correlated, you probably don't need both of them. If two metrics strongly disagree with each other, either this reveals something important about your system, or your metrics just aren't trustworthy.2. Many (I estimate 60 - 70%?) use AI to evaluate AI responses, with common criteria being conciseness, relevance, coherence, faithfulness, etc. I find AI-as-a-judge very promising, and expect to see more of this approach in the future.AI-as-a-judge scores aren’t deterministic the way classification F1 scores or accuracy are. They depend on the judge's model, the judge's prompt, and the use case. Many AI judges are good, but many are bad.Yet, very few are doing experiments to evaluate their AI judges. Are good responses given better scores? How reproducible the scores are -- if you ask the judge twice, do you get the same score? Is the judge's prompt optimal? Some aren’t even aware of the prompts their applications are using, because they use prompts created by eval tools or by other teams.Also fun fact I learned from a (small) poll yesterday: some teams are spending more money on evaluating responses than on generating responses 🤯 https://lnkd.in/gYnTRZW3

2

I just published Vol. 52 of "Top Information Retrieval Papers of the Week" on Substack. My Substack newsletter features the 7-10 most notable research papers on information retrieval (including recommender systems, search & ranking, etc.) from each week, with a brief summary, and links to the paper/codebase. This week’s newsletter highlights the following research work: 📚 A Comprehensive Survey of Retrieval-Augmented Large Language Models: Architectures, Training, and Applications, from PolyU 📚 An Analysis Framework for Benchmarking Retrieval-Augmented Generation Systems, from Tu et al. 📚 Distilling Cross-Encoders from Large Language Models for Efficient Passage Re-ranking, from Schlatt et al. 📚 A Comprehensive Benchmark for Assessing Retrieval-Augmented Language Models in Biomedicine, from UMTC 📚 Improving Factual Accuracy of Large Language Models for Healthcare using Targeted Knowledge Graph Retrieval, from Huawei 📚 Identifying Shopping Product Questions in Voice Assistants via Graph Attention Networks, from Amazon 📚 A Learnable Tokenizer for Generative Recommendations, from NUS 📚 An Enhanced Retrieval-Augmented Generation Framework for Accurate, Efficient, and Personalized Language Models, from UTS 📚 Constructing Synthetic Test Collections Using Large Language Models for IR Evaluation, from Rahmani et al. 📚 Enhancing Sequential Recommendation with Soft Contrastive Learning, from Renmin University #InformationRetrieval #ResearchPapers #CuratedContent #Newsletter  #substack

70

2 Comments

Collaborative AI is gaining momentum at both MNC and Startups, they are investing into this EvolutionNext Robotics AI Transformative Experiential Learning Journey. I am extremely glad to put Singapore on the World map, by anchoring Robotics AI companies here, creating Jobs of the FutureNow as Roboticist. Do support my Leadership Initiative for Singapore as National Interest; help me enable our next-generation Singaporeans to take on Science, Technology, Engineering and Mathematics STEM Education and longer-term Career Practice into Industry 5.0 as Machine Intelligence of Human-Robot Collaborative, Human-centric Autonomy. * My STEM OneCareer Pinnacle and Finale as a 55-years old, always just another very ordinary Singapore-born Singaporean Scientist Engineer in Singapore, essentially a Nobody here 🌸

13

2 Comments

I wanted to share some insights from a recent paper from Amazon Science in which authors tackled an important challenge in language modeling: minimizing sequence truncation. In language models, truncating input sequences might lead to a loss of crucial information, especially when the models are dealing with long-context tasks such as document summarization or story generation. The authors introduce a clever solution by leveraging a heuristic from the Best Fit Bin Packing problem, an NP-hard problem, to reorder input documents and reduce truncation. The proposed approach helps retain more information compared to other strategies by optimizing how sequences are packed into the model's context window. Authors show that the bin packing solution had biggest performance gain reading comprehension (+4.7%), natural-language inference (+9.3%), context following (+16.8%), and program synthesis. They also found that best-fit packing helped prevent closed-domain hallucination. Authors claim that while the experiments primarily focused on LLM pretraining, best-fit packing is broadly applicable to fine tuning as well. https://lnkd.in/gWquw3ud

28

3 Comments