Ankit S.

🚀 While many studies highlight LLMs' success in answering medical questions, research from Yanjun Gao, PhD, and colleagues takes it a step further. They evaluated LLMs on real-world EHR datasets for clinical prediction, comparing them directly against classical machine learning models—widely regarded as state-of-the-art in this field. By examining tasks like mortality prediction and hospital length-of-stay prediction, which greatly influence clinical workflows, the findings demonstrate that LLMs have significant potential to advance clinical predictive modeling.

7

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

Amidst a range of commercial black box LLMs from large enterprises, we are also seeing Open-Source Machine Learning Frameworks for Advancing Large Language Models in Healthcare. Check out Hippocrates, an open-source LLM framework specifically developed for the medical domain https://lnkd.in/gw5xHdUD

1

📢 #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

156

4 Comments

Our #icra2024 paper is now available from #ieee dl. We proposed a new Inverse Reinforcement Learning based method for hand trajectory prediction. Mukund Mitra Gyanig K. Partha Pratim Chakrabarti

18

2 Comments

❓ Struggling to keep up with generative AI’s rapid evolution—or wondering how to turn research into real-world impact? Join me and Ravin Kumar, Senior Research Data Scientist at Google Labs, for a live podcast recording where we’ll tackle these questions and more. 🎙 What we’ll cover: 📚 Generative AI at Google: How tools like Notebook LM bridge cutting-edge research with practical applications for technical and non-technical users alike. 🌍 Democratizing AI: The shift from training models to API-driven solutions, and the trade-offs between open-source and hosted tools. 🧩 Cultural & Practical Challenges: How to adapt generative AI tools for diverse global audiences and improve their user experience. 🛠 AI Roles & Personas: The evolving landscape of AI—from researchers fine-tuning models to developers building with APIs—and how to get started. 🏁 The Competitive Landscape: How companies like Google are pushing the boundaries of generative AI with new tools and features. This is your chance to hear from someone working on the frontlines of AI research and products—don’t miss it! Sign up here: https://lnkd.in/gwmzHunh

11

📣 📣 📣 We have extended the deadline for AAAI workshop on Planning in the Era of LLMs (LM4Plan @ AAAI 2025) past Thanksgiving! 📣 📣 📣 https://lnkd.in/eP5yQHkf The new and final deadline is *November 29* AOE! Large Language Models (LLMs) are a disruptive force, changing how research was done in many sub-areas of AI. Planning is one of the last bastions that remain standing. The focus of this workshop is on the questions in the intersection of these areas. Some of the specific areas we would like to gain a better understanding in include: what LLMs can contribute to planning, how LLMs can/should be used, what are the pitfalls of using LLMs, what are the guarantees that can be obtained. #planning #LLM #agents Sarath Sreedharan Jiayuan Mao Subbarao Kambhampati Wenlong Huang

9

1 Comment

Predictions based on Machine Learning and Statistics often rely on maximal likelihood, which can trap LLMs in biases inherited from the majority opinions of training data. This problem has been substantially addressed through conditional statistics, allowing for mitigation of biases and preventing the cancellation of minority perspectives. https://lnkd.in/gMXKqwyB

7

Please join with us for this interesting event on 5th May, the link is in mentioned in the post as below

4

**Arxiv paper alert** We are excited to release our survey paper, "Direct Speech-to-Speech Neural Machine Translation: A Survey." This paper delves into the challenges of speech-to-speech translation (aka audio dubbing). The day is not far when AI will dub videos on the fly and make the content universally available in any language thus transforming education, entertainment, etc. Abstract: Speech-to-Speech Translation (S2ST) models transform speech from one language to another target language with the same linguistic information. S2ST is important for bridging the communication gap among communities and has diverse applications. In recent years, researchers have introduced direct S2ST models, which have the potential to translate speech without relying on intermediate text generation, have better decoding latency, and the ability to preserve paralinguistic and non-linguistic features. However, direct S2ST has yet to achieve quality performance for seamless communication and still lags behind the cascade models in terms of performance, especially in real-world translation. To the best of our knowledge, no comprehensive survey is available on the direct S2ST system, which beginners and advanced researchers can look upon for a quick survey. The present work provides a comprehensive review of direct S2ST models, data and application issues, and performance metrics. We critically analyze the models' performance over the benchmark datasets and provide research challenges and future directions. Link: https://lnkd.in/duY59bR7 Mahendra Gupta #AIatIITI #NLP, #AI, #NLP, #speechTranslation

20

On Thursday, 6/13 at 9 AM PT, learn about the game-changing benefits of #AI quantization. Qualcomm AI Research experts Mart van Baalen and Abhijit Khobare will share how state-of-the-art LLM quantization techniques like vector quantization address the challenges of implementing on-device AI efficiently and accurately. https://bit.ly/3KvJzs1

75

1 Comment

📢 We encouraged you to read the published paper "Why Grid Cells Function as a Metric for Space" 📝 Authored by: Suogui Dang, Yining Wu, Rui Yan, and Huajin Tang. Published in Neural Networks, volume 142, pp. 128-137, October 2021. This paper investigates the role of grid cells in spatial navigation. Drawing on neurophysiology and machine learning, it proposes a theoretical framework for grid cells as a metric for space. The model demonstrates efficient encoding of spatial relationships and paves the way for applications in navigation, machine learning, and understanding spatial cognition. 🔗Read the paper: https://lnkd.in/eAWvhy-d 🔗Become a member of the INNS today and be part of the community that explores the human brain/mind and related applications: https://lnkd.in/e-hhAYyD #INNS #AI #MachineLearning

3

Thrilled to collaborate with Prof. Gang Xu on accelerating the computation of isogeometric analysis (IGA) for topology-consistent models - a rewarding partnership that began during his visit to Delft in 2016. In this recent paper accepted by Journal of Computational Physics, we present IGA-Graph-Net, an innovative isogeometric analysis framework that leverages Graph Neural Networks and introduces a custom loss function to address Dirichlet boundary conditions, achieving significantly improved accuracy over traditional CNN-based methods for isogeometric analysis on complex geometries. By integrating ResNetV2 and PointTransformer, the framework effectively handles B-spline data and complex boundary conditions, demonstrating enhanced performance on partial differential equation datasets. "IGA-Graph-Net: Isogeometric analysis-reuse method based on graph neural networks for topology-consistent models", Journal of Computational Physics, 2024 (https://lnkd.in/erS5q6ZF) "IGA-Reuse-NET: A deep-learning-based isogeometric analysis-reuse approach with topology-consistent parameterization", Computer Aided Geometric Design (https://lnkd.in/e_WiJzFt) "Isogeometric computation reuse method for complex objects with topology-consistent volumetric parameterization", Computer-Aided Design (https://lnkd.in/eZKDsip4) #isogeometricanalysis #machinelearning

66

1 Comment

Confounding? Detect it! A brand new paper on detecting and measuring confounding using causal mechanism shifts (presented this week at NeurIPS) In their new NeurIPS 2024 paper, Abbavaram Gowtham Reddy and Vineeth N. Balasubramanian (IIT Hyderabad) propose a framework for detecting and measuring confounding in a number of scenarios, based on shifts in causal mechanisms. The authors propose three complementary measures of confounding (with conditional and multivariate variants), designed to assess relative strengths of confounding in a variety of settings. The proposed measures complement one another depending on the available contextual information and offer a unified way to study confounding across diverse scenarios where data from different contexts is available. The authors generously shared Python implementation of their solution on GitHub. 💡 Paper: https://lnkd.in/dGXbnqAy 💡 Code: https://lnkd.in/dpczZvcU

142

7 Comments

🚀 NVIDIA is at the forefront of revolutionizing artificial intelligence and high performance computing, and their latest research on generative AI is nothing short of groundbreaking! 🌟 A recent paper published on arXiv showcases NVIDIA’s innovative approach to enhancing generative models, crucial for applications ranging from image synthesis to natural language processing. By integrating advanced neural architectures and cutting-edge training methodologies, NVIDIA is making these models more efficient and scalable than ever before. What truly stands out is NVIDIA's commitment to accessibility and collaboration. Their advancements not only improve the performance of generative models but also significantly reduce computational costs, making high-quality AI accessible to a broader range of applications and industries. This democratization of AI technology is a game-changer! Moreover, NVIDIA’s dedication to open science and sharing knowledge with the broader AI community fosters an environment of collective progress and innovation. Their collaborative spirit accelerates advancements and ensures that AI technology benefits everyone. NVIDIA’s pioneering work continues to push the boundaries of what’s possible in AI, setting new standards for the industry. It’s exciting to witness how these innovations will shape the future of technology and transform various sectors, driving us toward a more intelligent and efficient world. Kudos to the NVIDIA team for leading the charge in AI research and development! 👏 https://lnkd.in/gRGq5y8D #NVIDIA #ArtificialIntelligence #AI #MachineLearning #GenerativeAI #Innovation #TechLeadership

1

Optimizing large language model inference cost is arguably one of the most important factors in increasing the adoption of #GenerativeAI. Speculative decoding is an optimization technique for inference that makes educated guesses about future tokens while generating the current token, all within a single forward pass. 🔥 Learn more in “A Hitchhiker’s Guide to Speculative Decoding” from the PyTorch blog: https://lnkd.in/ekCBhQ4q

5

Researchers at CMU Introduce TriForce: A Hierarchical Speculative Decoding AI System that is Scalable to Long Sequence Generation Quick read: https://lnkd.in/gr_he4kw Researchers from Carnegie Mellon University and Meta AI (FAIR) Introduce TriForce, a hierarchical speculative decoding system designed for scalable long sequence generation. TriForce utilizes the original model weights and dynamic sparse KV cache via retrieval as a draft model, serving as an intermediate layer in the hierarchy. Maintaining the full cache allows for superior KV cache selection using retrieval-based drafting, characterized as lossless compared to eviction-based methods like StreamingLLM and H2O. The hierarchical system addresses dual memory bottlenecks, pairing a lightweight model with a StreamingLLM cache for initial speculations to reduce drafting latency and accelerate end-to-end inference. TriForce introduces a hierarchical speculative decoding system with retrieval-based KV cache selection. The hierarchical system addresses dual bottlenecks, enhancing speed-up. Retrieval-based drafting segments the KV cache, highlighting relevant information. Lightweight models with StreamingLLM cache accelerate initial speculations, reducing drafting latency. TriForce utilizes model weights and KV cache to enhance LLM inference speed for long sequences. The implementation utilizes Transformers, FlashAttention, and PyTorch CUDA graphs, maintaining full layer sparsity while minimizing kernel launching overhead. Paper: https://lnkd.in/ga45hspw Machine Learning Department at CMU

26

Mixture-of-Agents as an Event-Driven System 🤖☎️ This paper by Wang et al. shows you how to ensemble smaller LLMs to create a system that can outperform state-of-the-art larger models. We’ve implemented this paper in a fully async, event-driven workflow system thanks to Ravi Theja Desetty - treat each “small LLM” as an event-driven step that can process incoming events and respond to it, independently and in parallel. ✅ Take full advantage of processing an entire batch of requests  ✅ Cleaner, readable code LlamaPack: https://lnkd.in/gRuqQGk2 Learn more about workflows: https://lnkd.in/gqWwz7Xs

311

9 Comments