Sessions

Building India’s AI Ecosystem: From Vision to Sovereignty Keynote
Responsible AI in Medical Imaging – A Case Study Keynote
Inclusive AI and Open Challenges Keynote
Evolution of Intelligence & You Keynote
A Visual Guide to Attention Mechanism in LLMs Hack Session
Why GenAI and LLMs Fail and How Fine-Tuning Helps Them Hack Session
Onboarding AI Agents with Human Values PowerTalk
Zero to Million: How GenAI Agents are Changing Performance Marketing PowerTalk
Building Effective Agentic AI Systems: Lessons from the Field Hack Session
Search Query Optimization Using Retrieval-Augmented Generation (RAG) Hack Session
RIP, Data Scientists Hack Session
MassGen: Scaling AI Through Multi-Agent Collaboration Hack Session
Productionizing Agents : An Agent Factory Approach PowerTalk
Building Responsible AI Agents with Guardrails and Safety in Action Hack Session
Red Teaming GenAI: Securing Systems from the Inside Out Hack Session
Vibe Coding Showdown: Building Applications with AI Assistants Hack Panel
How GenAI is Being Leveraged in the Web3 Ecosystems PowerTalk
Building Blocks of Successful AI PowerTalk
Agentic AI Meets Responsible AI: Designing Safe Autonomous Systems PowerTalk
Evaluating GenAI Models: Case Studies in Enterprise and Healthcare PowerTalk
Adaptive Email Agents with DSPy: From Static Prompts to Smart Learning Hack Session
AutoGen vs CrewAI vs LangGraph: Battle of the Agent Frameworks Hack Panel
Empowering Data Insights with Large Language Models Hack Session
Automate Everything: Building Agentic AI Workflows with No-Code Tools Hack Session
From Risk to Retention: The Anatomy of a Customer Saved Hack Session
Agentic AI for Business Users: Building without Code in Cogentiq Hack Session
From LLMs to Agentic AI: Solving New Problems with Multi-Agent Systems Hack Session
LLMs Are Boring. How Can We Make Them More Interesting? Hack Session
Quantifying Our Confidence in Neural Networks and AI Hack Session
Understanding AI Agents with MCP Hack Session
AI Voice Agent: The Future of Human-Computer Interaction Hack Session
Automating Vehicle Inspections with Multimodal AI and Gemini on GCP Hack Session
Deploying GenAI Safely: Strategies for Trustworthy LLMs Hack Session
Beyond PoCs: Building Real-World Agentic Systems Hack Session
Mastering Agentic Workflows with LangGraph Hack Session
Towards Sustainable AI: Effective LLM Compression Techniques Hack Session
From Language to Robotics: Practical Lessons Bridging LLMs, RL, and AI Hack Session
Agentic Knowledge Augmented Generation: The Next Leap After RAG Hack Session
Collaborative Multi-Agent Framework for Robust SEO Content Generation Hack Session
Building Fast & Accurate Conversational Agents Beyond Function Calling Hack Session
Model Context Protocol in Media: Choosing the Right Metrics & Strategy Hack Session
Vibe Coding in Action: Building Real Applications with AI Assistance Hack Session
Full-Stack Agentic AI: Build, Evaluate, and Scale with NVIDIA Tools Hack Session
Measuring Uncertainty in LLMs and Optimal Use of SLMs Hack Session
Agent to Agent Protocol: Benefits and Workflows Hack Session
Bridging the AI Agent Gap: Interoperability with A2A and MCP Protocols Hack Session
Building Real-Time Multi-Agent AI for Public Travel Systems Hack Session
The Promise and Pitfalls of Synthetic Data Generation Hack Session
Creative AI Agents: Open Tools for Collaborative Media Creation Hack Session
Architecting AI: Practical Patterns for Multi-Agentic Workflows Hack Session
Multi-Modal GenAI for Energy Infrastructure Inspection Reports Hack Session
From Vision to Action: Multi-Modal Agentic AI in Real-World Use Hack Session
Aligning Responsible AI with Probabilistic World of LLMs & Agents Hack Session
Post‑Training Is Back: From Prompts to Policies Hack Session
Human-In-The-Loop Agentic Systems Hack Session
Building a Scalable Healthcare Voice AI Contact Center with Pipecat Hack Session
Scaling Test-time Inference Compute & Advent of Reasoning Models Hack Session
The Missing Piece of AI Apps: Evaluation Hack Session
vLLM + llm-d: Scalable, Efficient LLM Inference in Kubernetes PowerTalk
The Future of LLMs may be Agentic but is surely ‘Graph’ic PowerTalk
From Idea to Production with GenAI : Realizing the Art of the Possible Hack Session
Agents at Scale: Engineering Reliable GenAI Systems for Production Hack Session
Detecting and Mitigating Risks in Agentic AI Hack Session
Evolution of Intelligence & You Keynote
Responsible AI in Medical Imaging – A Case Study Keynote
Building India’s AI Ecosystem: From Vision to Sovereignty Keynote
Inclusive AI and Open Challenges Keynote
Productionizing Agents : An Agent Factory Approach PowerTalk
How GenAI is Being Leveraged in the Web3 Ecosystems PowerTalk
Building Blocks of Successful AI PowerTalk
vLLM + llm-d: Scalable, Efficient LLM Inference in Kubernetes PowerTalk
The Future of LLMs may be Agentic but is surely ‘Graph’ic PowerTalk
Agentic AI Meets Responsible AI: Designing Safe Autonomous Systems PowerTalk
Zero to Million: How GenAI Agents are Changing Performance Marketing PowerTalk
Onboarding AI Agents with Human Values PowerTalk
Evaluating GenAI Models: Case Studies in Enterprise and Healthcare PowerTalk
Building Effective Agentic AI Systems: Lessons from the Field Hack Session
RIP, Data Scientists Hack Session
Beyond PoCs: Building Real-World Agentic Systems Hack Session
Mastering Agentic Workflows with LangGraph Hack Session
Towards Sustainable AI: Effective LLM Compression Techniques Hack Session
Agentic AI for Business Users: Building without Code in Cogentiq Hack Session
From Language to Robotics: Practical Lessons Bridging LLMs, RL, and AI Hack Session
Agentic Knowledge Augmented Generation: The Next Leap After RAG Hack Session
The Promise and Pitfalls of Synthetic Data Generation Hack Session
Creative AI Agents: Open Tools for Collaborative Media Creation Hack Session
Multi-Modal GenAI for Energy Infrastructure Inspection Reports Hack Session
Building a Scalable Healthcare Voice AI Contact Center with Pipecat Hack Session
Scaling Test-time Inference Compute & Advent of Reasoning Models Hack Session
Building Responsible AI Agents with Guardrails and Safety in Action Hack Session
The Missing Piece of AI Apps: Evaluation Hack Session
From Idea to Production with GenAI : Realizing the Art of the Possible Hack Session
Collaborative Multi-Agent Framework for Robust SEO Content Generation Hack Session
Building Fast & Accurate Conversational Agents Beyond Function Calling Hack Session
Model Context Protocol in Media: Choosing the Right Metrics & Strategy Hack Session
Vibe Coding in Action: Building Real Applications with AI Assistance Hack Session
Full-Stack Agentic AI: Build, Evaluate, and Scale with NVIDIA Tools Hack Session
Detecting and Mitigating Risks in Agentic AI Hack Session
From Vision to Action: Multi-Modal Agentic AI in Real-World Use Hack Session
Aligning Responsible AI with Probabilistic World of LLMs & Agents Hack Session
Red Teaming GenAI: Securing Systems from the Inside Out Hack Session
Search Query Optimization Using Retrieval-Augmented Generation (RAG) Hack Session
Adaptive Email Agents with DSPy: From Static Prompts to Smart Learning Hack Session
Empowering Data Insights with Large Language Models Hack Session
From LLMs to Agentic AI: Solving New Problems with Multi-Agent Systems Hack Session
LLMs Are Boring. How Can We Make Them More Interesting? Hack Session
Quantifying Our Confidence in Neural Networks and AI Hack Session
From Risk to Retention: The Anatomy of a Customer Saved Hack Session
Agents at Scale: Engineering Reliable GenAI Systems for Production Hack Session
Post‑Training Is Back: From Prompts to Policies Hack Session
A Visual Guide to Attention Mechanism in LLMs Hack Session
Why GenAI and LLMs Fail and How Fine-Tuning Helps Them Hack Session
Automate Everything: Building Agentic AI Workflows with No-Code Tools Hack Session
MassGen: Scaling AI Through Multi-Agent Collaboration Hack Session
Understanding AI Agents with MCP Hack Session
AI Voice Agent: The Future of Human-Computer Interaction Hack Session
Automating Vehicle Inspections with Multimodal AI and Gemini on GCP Hack Session
Deploying GenAI Safely: Strategies for Trustworthy LLMs Hack Session
Measuring Uncertainty in LLMs and Optimal Use of SLMs Hack Session
Agent to Agent Protocol: Benefits and Workflows Hack Session
Bridging the AI Agent Gap: Interoperability with A2A and MCP Protocols Hack Session
Building Real-Time Multi-Agent AI for Public Travel Systems Hack Session
Architecting AI: Practical Patterns for Multi-Agentic Workflows Hack Session
Human-In-The-Loop Agentic Systems Hack Session
Vibe Coding Showdown: Building Applications with AI Assistants Hack Panel
AutoGen vs CrewAI vs LangGraph: Battle of the Agent Frameworks Hack Panel