Vishrav Chaudhary

📢 #NewPaperAlert Can explicitly modeling group interactions reduce spurious correlations in graph explanations? We're thrilled to share our new preprint, "Higher Order Structures For Graph Explanations," with 🚀 Akshit Sinha*, Sreeram Vennam*, & Charu Sharma In many real-world applications, post-hoc graph explainers tend to recognize spurious correlations. We hypothesize that this issue arises because traditional graphs only model pairwise interactions. To tackle this problem, we introduce FORGE, a method that incorporates higher-order structures to explicitly model group interactions. FORGE utilizes cell complexes from algebraic topology to model these higher-order interactions. The process involves two steps: 1) lifting the graph into the domain of cell complexes, and 2) transferring the importance scores back to the original graph. By adding these group interactions, we significantly improve the accuracy of graph explanations. Our work highlights the importance of explicitly modeling higher order structures for tasks requiring interpretability. 📜 Preprint: https://lnkd.in/dwhB7yMJ 🐙 GitHub: https://lnkd.in/dbUcAqcR Findings 🧵 on X: https://lnkd.in/dNSy9e5F

153

4 Comments

I remember when this all started. Faris - invited me to catch up at our favorite spot around Blok M. I had no idea he’d just wrapped up a procedure at Pondok Indah Hospital! (He really knows how to add drama to our catch-ups.) We’d been on separate paths and projects since "the winding down project", but there he was, reminding me of our dream to ride this AI wave together again. It was a plan we’d hatched with Sahal Zain & Gurnoor Dhillon when the world of AI was still mostly theoretical and jargon-heavy. Somehow, the conversation continued with Gurnoor Dhillon while he was waiting for his meeting with someone who would eventually become one of CalvinBall’s key early adopters. It felt like everything was coming together, like a series of seemingly random dots connecting to form a bigger picture. Seeing how far we’ve come as a team at CalvinBall Technologies is truly exciting. What started as theoretical discussions has now evolved into practical Gen AI solutions that are solving everyday problems and hold endless possibilities to shape the industry. 👨‍🚀 👩‍🚀 Here’s to pushing boundaries and achieving new milestones together! Gurnoor Dhillon, Sandeep Ramesh, Faris -, Sahal Zain, Eva Zuliya, Ratu Nadiah Khairunnisa 🚀 #GenAI #AIInnovation #TechJourney #ArtificialIntelligence #TechTransformation #CalvinballTech #Calvinballers

55

2 Comments

What a great talk from Swapnil Sayan Saha, on Physics-Aware Tiny Machine Learning! https://lnkd.in/g9g4YWs4 There's exciting times ahead as Physics-aware TinyML is becoming increasingly important in merging the power of machine learning with operating in the physical world. By integrating real-world physics models into ultra-low-power devices, this approach dramatically enhances the accuracy and efficiency of TinyML applications. From improving energy efficiency in smart sensors to enabling more accurate anomaly detection in industrial applications, this approach to machine learning at the edge helps machines better understand their environment - without sacrificing power or performance. As we explore the possibilities, this combination of physics and Edge AI opens up new opportunities in fields like healthcare, environmental monitoring, and autonomous systems. It's a huge leap toward making AI more sustainable and impactful, and allows us to build more useful AI-enabled systems that operate in (and on!) the physical world. #TinyML #EdgeAI #PhysicsAwareAI #AIInnovation #Sustainability #MachineLearning

4

IndicGenBench Google Research India recently released IndicGenBench, a multilingual benchmark to evaluate generation capabilities of LLMs on 29 Indic languages spanning 13 writing scripts and 4 language families. Extended the datasets in Cross-lingual Summarization, Machine Translation, Multi-lingual Question Answering, and Cross-lingual Question Answering, the team has collected human translations for English examples into target Indic languages, thereby extending the scope and applicability of evaluation metrics in this domain. One of the key insights from their study is the analysis of token fertility across all Indic languages within IndicGenBench. Token fertility, representing the average number of sub-words that a word is broken down into by the tokenizer, varies significantly across languages Some languages have simple breakdowns, while others are more complex. Now, why does this matter? Well, it affects how well the language models work. Languages with more complex breakdowns might struggle because they can't use as many examples to learn from. They found that languages with simpler breakdowns can use more examples effectively compared to those with complex breakdowns. #LLMs #GenAI #IndicGenBench #AI #IndicLanguages #IndicDatasets #multilingual

15

1 Comment

EMNLP 2024 results are out, we got in three papers, congrats to students :) First paper of many, Vatsal, Pranshu, Suyash, Janit, Kunal, Srija and Adnan, Congrats 🎉 🎊 🍾 🎈 Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets (main) - Vatsal Gupta, PRANSHU PANDYA, Tushar Kataria, Vivek Gupta, Dan Roth tldr: make models robust on multiple adversarial challenge set simultaneously  arxiv: https://lnkd.in/ei-65Y6g Knowledge-Aware Reasoning over Multimodal Semi-structured Tables (finding) Suyash Vardhan Mathur, Jainit Bafna, Kunal Kartik, Harshita Khandelwal, Manish Shrivastava, Vivek Gupta, Mohit Bansal, Dan Roth tldr: introduce the novel task of reasoning on multimodal tabular data, text + images in a structure (first of a kind) arxiv: https://lnkd.in/e5ycusfn   Unraveling the Truth: Do LLMs really Understand Charts? A Deep Dive into Consistency and Robustness (finding) Srija Mukhopadhyay, Adnan Qidwai, Aparna Garimella, Pritika Ramu, Vivek Gupta, Dan Roth           tldr: VLM although seem very accurate on chart, are not all robust and consistent in performance arxiv: https://lnkd.in/eFFA-sVX We also got an workshop paper, at BlockBoxNLP 2024 @EMNLP, here the details Enhancing Question Answering on Charts Through Effective Pre-training Tasks Ashim Gupta, Vivek Gupta, Shuo Zhang, Yujie He, Ning Zhang , Shalin Shah, Ph.D. tldr: models is not robust & consistent on charts, can we use pre-training on simple auxiliary tasks to enhance model robustness arxiv: https://lnkd.in/egbRHm-4

385

12 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

🚀 Making LLMs work for you - A Guide to Become 10x Programmer/MLE/DS I am sure many of you use LLMs for your day-to-day work. Mostly, I have seen people use LLMs while writing code (Copilot), or as an alternative to Copilot to catch bugs, but they have become much more useful than that, provided you know how to use them well. Here are a few ways I have been using LLMs in my daily work that are helping me increase my productivity: 📚 1. Quick Paper Assessment with ELI5 Summaries - Paper abstracts are called abstracts for a reason. Asking an LLM for an ELI5 summary makes it much easier to know if I want to read a paper. 💻 2. Implementing Research Papers in Code - Try giving an LLM like Claude/ChatGPT a research paper and ask to code it. You would be surprised. Tip: Claude performs much better for this task. 🔄 3. Upgrading Code Structure and Readability - Do you want to add typing hints when writing your Python code, or do you need comments in your code, or do you have a big function that you want to be converted to classes in your code? LLMs can do it all, and you would be amazed at the code-conversion power they have. ⚡ 4. Optimizing Code Performance - The thing with LLMs is that if you tell them what to do, they can do it well. For example, if you give them a non-optimized piece of code that runs correctly, they will be able to write it in a much-optimized way. For example, I just used an LLM to convert a matrix multiplication in PyTorch to sparse MM as I was getting an OOM memory error because one of the matrices became too large. I am not even joking, but that would have taken at least 1-2 hours for me to come up with. 📝 5. Automated Documentation - Got bored of writing documentation for what you did but have the code? LLMs also work the other way around. Want to write a summary of what you did in a week, you can use an LLM for that. Saves so much time that gets wasted in formatting. 🧪 6. Streamlined Test Framework Creation - Let LLMs handle the boilerplate for Unit tests & Integration tests while you focus on core logic. 🌐 7. Language-Agnostic Development - You can paste a function in Python and ask for its equivalent in Rust, complete with language-specific best practices and error handling. This dramatically reduces the learning curve when working with new languages and helps maintain productivity during language transitions. 🤝 Apart from all of the above, LLMs work well as mentors as well as interns. LLMs are great when you just need someone to bounce ideas with. I sometimes just talk to an LLM as I would to a colleague talking about the problems I have and how I can solve them. And they come up with the right ideas or send me in the right direction a lot of times. They also act as a personal assistant for free, who can deal with writing messages, creating charts, and doing all sorts of uninteresting work for you. 💭 What's your favorite way to use LLMs? Let me know in the comments! #MachineLearning #AI #Programming

47

Many of ML practitioners might have heard the term "Extending context length" for LLMs. In case if you want to dive deeper into this topic along with its code implementation, give this blog a read. I have described about Position Interpolation, NTK aware and Dynamic NTK method, which are widely used for extending context length.

68

With Sarath Shekkizhar, we are exploring the geometric structures behind LLM reasoning capabilities. So far, our findings suggest: 1. Higher density in self-attention graphs implies higher intrinsic dimension. 2. Higher intrinsic dimension induces more expressive power/reasoning with MLPs. 3. Longer context and more attention heads can boost intrinsic dimension. This geometric lens offers new insights into LLM performance and potential improvement strategies. Early days, but we believe it is a promising direction! Stay tuned for more as we dive deeper into the geometry of AI reasoning. Read our pre-print: https://lnkd.in/gcekSWYD #AI #MachineLearning #LLM

25

I've recently been replicating some of our released work on LLM with MLX. I enjoy MLX for a variety of reasons. Minimalist is one of them. MLX's API is a subset of numpy and much less than PyTorch's. There was a moment when I thought the API was insufficient to support beam search and tree attention. However, as I moved along, I realized that this simple API is just as powerful as the ones on stage. Rethinking how to rewrite our PyTorch programs in MLX often resulted in simpler, more readable code. For example, the following two lines generate attention bias in PyTorch (https://lnkd.in/gszdymfE):   attn_bias = torch.zeros(causal_mask.shape, dtype=dtype, device=causal_mask.device)   return attn_bias.masked_fill_(causal_mask.logical_not(), LOG_0) MLX lacks masked_fill_. So I rewrote the above as a single line:   return mx.logical_not(causal_mask) * LOG_0 Yes. It takes time to rethink and rewrite code. However, if this work helps to keep MLX's API simple, it eases the learning process for others. I appreciate a small set of primitives. We would benefit from higher layers of APIs built on top of it, rather than a large flat set of primitives.

82

2 Comments

Over last few months, I am increasingly leveraging LLMs to write code. From 10% to nearly 78% currently (based on lines of code) of my code is from LLMs. I have my own pipeline to fine tuned LLMs to augment my needs. Observations - 1. I am producing more code --> MORE IMPACT (approx 2.3X) 2. I am reading more code --> MORE MAINTAINABLE CODE 3. I am learning more as now I can start from concept and expand out ---> MORE LEARNING 4. I am incorporating best practices --> BETTER CODE 5. Lesser typing --> LOWER REPETITIVE STRAIN INJURY #AIBUDDY

76

8 Comments

📊 The Power of High-Quality, Diverse, Real-World Data Fine-Tuning LLMs 🌍 When it comes to training Large Language Models (LLMs), the mantra isn’t just “more data”—it’s better data. While having more data can be beneficial, it’s the quality, diversity, and real-world relevance of the data that truly drive impactful results. Here’s why: 1️⃣ Higher Quality: clean, well-curated data improves model accuracy and reduces noise, making the model more reliable and stable. Poor-quality data often leads to inconsistent responses and increased hallucinations. Unbiased labeling consistency is key. 2️⃣ Diversity: it ensures the model can generalize across different contexts and user scenarios. This makes the model more robust, safe and inclusive, which is especially important in NLP for avoiding bias and ensuring representation. 3️⃣ Real-World Datasets: training on real datasets helps models perform better in real-world applications, as it learns from actual patterns and usage scenarios, making the model more practical and effective. For LLMs, there’s a general playbook to prepare data effectively: (1) Collect Instruction-Response Pairs: gather examples of how tasks should be answered, covering various domains and complexity levels. (2) Concatenate Pairs: organize the data into structured sequences, allowing the model to learn from end-to-end interactions. (3) Tokenize: process the data into tokens, using padding and/ or truncation as needed to maintain uniform length. I particularly love 🤗 transformers library's AutoTokenizer to identify which tokenizer to use on every model. (4) Split into Train/Dev/Test Sets: partition your data into training, validation, and testing sets to ensure proper model evaluation and tuning. Ultimately, data quality prevails over quantity, specially as we live in the LLMs era when models have been pre-trained with almost all the public data available in the 🌎 . A well-prepared dataset tailored to your application will make all the difference in the performance and reliability of your model. #AI #MachineLearning #DataQuality #LLM #NLP #ModelTraining #DataPreparation

5

Prof. Rao's post is a good starting point for LLM practitioners to become familiar with classic (i.e., predating LLMs) AI concepts and theories, for two reasons: 📌 To understand that some things are theoretically beyond the reach of LLMs and not waste resources chasing them. 📌 To hedge against the possibility that LLMs may be replaced by other technologies and/or undergo fundamental technological revamps, which would render all existing investments in LLMs obsolete. #artificialintelligence #machinelearning #deeplearning

41

3 Comments

As a passionate Machine Learning enthusiast and practitioner, I am constantly amazed by the profound impact that optimization algorithms have on our ability to train models efficiently and effectively. One such fundamental algorithm that stands out is Gradient Descent. 🔍 What is Gradient Descent? Gradient Descent is an iterative optimization algorithm used to minimize the cost function in machine learning models. By iteratively adjusting the parameters of our models, it helps us find the optimal solution, leading to better predictions and improved performance. 🔧 How Does It Work? Initialization: Start with an initial guess of the model parameters. Compute the Gradient: Calculate the gradient of the cost function with respect to each parameter. Update the Parameters: Adjust the parameters in the opposite direction of the gradient. Repeat: Continue this process until convergence is achieved. ✨ Why It Matters? Gradient Descent is the backbone of many machine learning algorithms. Its simplicity and efficiency make it an indispensable tool for training models, from linear regression to deep neural networks. 🔍 Types of Gradient Descent: Batch Gradient Descent: Uses the entire dataset to compute the gradient. Stochastic Gradient Descent (SGD): Uses one random sample from the dataset at a time. Mini-Batch Gradient Descent: Uses a small batch of samples to compute the gradient. 🌟 My Experience: Having worked extensively with machine learning models, I’ve seen firsthand the power of Gradient Descent. Whether it’s tuning hyperparameters or fine-tuning neural networks, understanding and leveraging this algorithm has been key to achieving high accuracy and robust models. 📈 Key Takeaways: Gradient Descent helps in optimizing and fine-tuning machine learning models. It’s essential to choose the right variant (Batch, SGD, Mini-Batch) based on your specific use case. Properly tuning the learning rate is crucial for the success of the algorithm. Let’s continue exploring and pushing the boundaries of what’s possible with machine learning! If you have experiences or insights related to Gradient Descent, I’d love to hear them in the comments. Important Note: Mohammad Anwar Khan and Hassan Syed along with iCodeGuru also help many like me to understand these concepts easily by organizing daily Gen AI workshops at 7:00 PM Pak time. I am also updating my GitHub repository with all these concepts https://lnkd.in/d6vVhpHZ Feel free to fork and star this repo. #GenerativeAI #MachineLearning #ArtificialIntelligence #OpenSource #GitHub #AIResearch #Collaboration #Innovation #TechCommunity #AITraining #ProfessionalGrowth #PakAngels #AspirePakistan #iCodeGuru #TheEngineersPakistan #4Brothers #Hackathon #TechEducation #SoftwareEngineer #LeetCode #GenAIDeveloper #MachineLearning #GradientDescent #AI #DataScience #Optimization #DeepLearning

18

1 Comment

Small Language Models (SLMs) like OpenAI's GPT-4o mini are shaking things up. They pack the punch of their larger counterparts but are way faster and cheaper. This means more practical AI applications without the usual lag or high costs. It's game-changing for developers and businesses alike. Definitely looking forward to using this for AI appilications🚀 #AI #TechInnovation #SLMs #generativeAI #LLM

21

1 Comment

𝗟𝗹𝗮𝗺𝗮 𝟯 𝘂𝗻𝘃𝗲𝗶𝗹 𝗮 𝗳𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹 𝗰𝗼𝗺𝗽𝘂𝘁𝗶𝗻𝗴 𝘁𝗿𝗮𝗱𝗲𝗼𝗳𝗳 𝘁𝗵𝗮𝘁 𝗳𝗲𝘄 𝗮𝗿𝗲 𝘀𝗲𝗲𝗶𝗻𝗴⬇️ 🦙Llama 3 just came out and to the surprise of many people, the L3-8B version can match the L2-70B one on several benchmarks. Several people also argued that the chinchilla paper (https://lnkd.in/dXaRqyea) was wrong because the llama 3 scaling is very far from chinchilla-optimal. 🤔 In my opinion, this is due to a misunderstanding of what the chinchilla paper is about and more generally of the effects of scale in deep learning. The bitter lesson (https://lnkd.in/d3sVYYgp) has become common knowledge in the field thanks to the GPT family that popularized it. We hear everywhere that "bigger models are better": Yes it's true, but in what sense? Many people have a mental model along the lines of "bigger models are more capable" meaning they would be able to achieve levels of performance that smaller models can't. ❌ This is not true with LLMs and is mainly because we train only once on tokens (most of them at least) and therefore overfitting is not possible. The 𝘳𝘦𝘢𝘭 advantage of bigger models over smaller ones is that they converge *faster*. In other words, you can reach a given level of NLL (modeling performance) with fewer training iterations. ❔ Then a natural question arises: Should I train a smaller model with more or a bigger model with fewer iterations? That's where the chinchilla paper brings a response. They say that the question they are answering is: "Given a fixed FLOPs budget, how should one trade-off model size and the number of training tokens?" (implying "to achieve the best possible NLL"). 🧐 Coming back to Llama 3, it's obvious that the Llama team is aware of this work and there is a reason why they didn't follow this recipe. My guess is that they are taking into account the inference cost in the balance (which is completely out of the scope of the chinchilla paper). When one "overtrains" an 8B model, one ends up with a worse "NLL to training compute" ratio, but also with a better "NLL to inference compute" ratio. ✅ Now if we think about it from a business perspective, it's a very powerful tradeoff because you can choose to buy performance either at a fixed cost (training) or at a variable one (inference). Hope this post helped you! #Llama3 #Meta #LLM #AI

9

3 Comments

⏫ Leveled up my understanding of retrieval systems (R+AG) 🔍 and put those learnings to work by improving GitHub Issues management! Here’s a breakdown of what I explored: ✨ Embedding-based Retrievals – How embeddings drive more meaningful search by mapping concepts into vector spaces. ⚠️ Pitfalls of Simple Vector Search – Identified common issues like irrelevant results and learned how to tackle them effectively. 🔍 Query Expansion with LLMs – Used Large Language Models to broaden search coverage and uncover deeper insights. ⚖️ Cross-Encoder Re-Ranking – Tuned result rankings with cross-encoders to bring the best matches to the top. 🛠️ Embedding Adaptors – Learned how to tweak embeddings for different tasks to keep retrieval systems flexible and efficient. Super excited to apply these concepts further! If you're working on retrieval systems, let’s connect and exchange ideas! 🚀 #AI #ChromaDB #Retrieval #LLMs #GitHub

15

5 Comments

📝 Exciting news! My latest blog post on Medium is now live! In this multi-series blog, I explore anomaly detection in any system. I share my experiences in designing and implementing an end-to-end solution for anomaly detection patterns in user access patterns. This series will cover a variety of topics, including understanding application events, optimizing data in Snowflake, developing machine learning models, and integrating with external applications. In the first blog post, I dive into everything about events and how they should be handled in a distributed system. Check out the full article here to learn more: https://lnkd.in/g8mjARdd I would love to hear your thoughts and insights in the comments section! Let's start a conversation. #events #eventing #outboxpattern #anomalydetection #machinelearning #dataoptimization #AWS #Snowflake

63

5 Comments

Good folks from Carnegie Mellon University's WAVLab have released XEUS - A Cross-lingual Encoder for Universal Speech 🌐🗣️ Simple speech representation is hindered by a lack of labelled data. That's where Self-supervised learning (SSL) comes in! 🔍📚 XEUS is a SoTA speech encoder trained in 4000+ languages! 🏆🌍 Before this, I did not even know that there are 4000+ languages. But the paper says this is a small dent in the world's 7000+ languages. 🌐🗺️ More details: - 577M parameters 📊 - 1M+ hours of speech training data across 4057 languages 🗣️⏳ - Uses the E-Branchformer architecture and is trained using HuBERT-style masked prediction of discrete speech tokens 🏗️🔠 - For robustness, the input speech is also augmented with acoustic noise and reverberation 🎙️🔊 Beats both MMS 1B and w2v-BERT v2 2.0 🥇🏆 It requires fine-tuning to be used in downstream tasks such as Speech Recognition or Translation. 🛠️🌐 Its hidden states can also be used with k-means for semantic Speech Tokenization. 🗣️🔑 Release: https://lnkd.in/gqrfvsRF

11