Free Registration (with a Zoom account; you can get one for free if you don't already have it. This requirement is to avoid Zoom bombing. Please sign in using the email address tied to your Zoom account — not necessarily the one you used to register for the event.): https://sjsu.zoom.us/webinar/register/WN_DIDfdbkgRFeEd3JbzURIUQ Synopsis: How are machine learning algorithms able to answer questions from any nook and corner of the World Wide Web? How are trending hashtags from the near infinite microblog posts, unique visitors and other distinct counts in the near infinite website traffic determined? How do blogging websites avoid recommending articles a user has previously read? In general, how can we answer complex queries about enormous data streams without storing them entirely, in real-time? The answer often lies in clever approximation algorithms and data "sketches" that capture essential properties using vastly reduced space. The relentless flow of data in modern systems indeed presents significant challenges. These data streams are often too large to store and too fast to process exhaustively with traditional methods. This talk introduces key sketching and approximation techniques that help generate real-time data insights by processing data streams. --------------------------------------------------------------- By registering for this event, you agree that IEEE and the organizers are not liable to you for any loss, damage, injury, or any incidental, indirect, special, consequential, or economic loss or damage (including loss of opportunity, exemplary or punitive damages). The event will be recorded and will be made available for public viewing. Speaker(s): Dr. Vishnu S. Pendyala Virtual: https://events.vtools.ieee.org/m/482936

IEEE SCV WIE AI Summit 2025 In an era where AI technologies are rapidly transforming industries and redefining possibilities, it is crucial to explore both the innovations driving this change and the responsibilities that come with it. Today, we will delve into a diverse array of topics that highlight the multifaceted nature of AI and its profound impact on our lives. Our sessions will cover the latest developments in Large Language Models and Foundation Models, exploring efficient fine-tuning, multilingual adaptation, and the role of LLMs as knowledge bases. We will also examine the evolution of AI agents, focusing on autonomous task completion, multi-agent collaboration, and the integration of external knowledge for robust decision-making. In the realm of Vision and Multimodality, we will explore the integration of text, image, and video understanding, as well as advanced techniques like zero-shot learning and self-supervised learning. Our discussions on MLOps for LLMs will provide insights into best practices for training, deploying, and evaluating large models. We will also address the critical areas of Knowledge-Grounded Reasoning, On-Device Learning, and the ethical dimensions of AI, including bias mitigation, privacy preservation, and the detection of misinformation. Talk tracks are broadly classified but not limited to, 1. Large Language Models (LLMs) & Foundation Models Efficient Fine-tuning of LLMs for Low-Resource Languages, LLM Alignment & Instruction-Tuning: Challenges and Advances, Scaling Laws: Understanding Model Size vs. Performance, Multilingual and Cross-Lingual LLM Adaptation, Memory-Augmented LLMs: Enhancing Long-Term Context Understanding, LLMs as Knowledge Bases: Reasoning and Fact-Checking 2. AI Agents Autonomous AI Agents: Leveraging LLMs for Task Completion, Multi-Agent Communication & Collaboration in NLP, Self-Reflective AI: Reflexion and Self-Improvement in Language Models, Hierarchical & Modular AI Agents: Towards Scalable Systems, LLMs as Orchestrators: AI Workflows with Task-Specific Agents, Grounding LLMs in External Knowledge for Robust Decision-Making 3. Vision & Multimodality Vision-Language Models (VLMs): From CLIP to GPT-4V, Multimodal Agents: Integrating Text, Image, and Video Understanding, Spatial and Temporal Reasoning in Vision-Language Models, Zero-Shot and Few-Shot Learning in Multimodal AI, Self-Supervised Learning for Multimodal Representations, Evaluating Multimodal Models: Metrics & Benchmarks, Neurosymbolic Approaches for Language and Vision Tasks 4. MLOps for LLMs LLMOps: Best Practices for Training & Deploying LLMs, Efficient Inference for Large Models: Pruning, Quantization & Distillation, Retrieval-Augmented Generation (RAG): Enhancing Context Awareness, Memory and Context Window Expansion: Architectures & Trade-offs, Evaluation Metrics for LLMs & Conversational Agents 5. Knowledge-Grounded & Reasoning LLMs for Automated Theorem Proving & Scientific Discovery, Commonsense Reasoning in AI Agents, Symbolic vs. Neural Reasoning, Interpretable Models: Improving Explainability in LLMs, Unifying Knowledge Graphs and LLMs for Structured Reasoning 6. On-Device Learning for LLMs and Multi-Modal AI On-Device LLMs & Edge AI for Language Processing and Multimodal Applications, Security, Privacy & Ethical Considerations for On-Device LLMs 7. Ethics, Bias & Fairness Bias Mitigation in Large Language Models, Hallucination Detection & Control in LLMs, Privacy-Preserving NLP: Federated Learning & Differential Privacy, AI and Misinformation: Detecting Deepfakes & Generated Content, Ethical Considerations in Deploying NLP for Real-World Applications Speaker(s): Chloe Ma Agenda: 3:00-3:30 Registration 4:00-4:15 IEEE SCV WIE Welcome Message 4:15-4:30 Keynote Message 4:30-5:30 Sessions 5:30-6:00 Networking and Refreshments 6:00-6:30 Multimodal and Physical AI and their application in Embodied and Robotics Space by Chloe MA 6:30-7:50 Lightning Talks 7:50-8:00 Networking and Wrap-up Bldg: SC9, Intel, 2250 Mission College Blvd, Santa Clara, California, United States, 95054, Virtual: https://events.vtools.ieee.org/m/479108