More The TWIML AI Podcast episodes
Published 8 Jan 2026
Duration: 3997
Advances in legged robotics are hindered by challenges such as sim-to-real translation, perception, and reliability in complex environments.
Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion Robotics to discuss the gap between current robotic capabilities and whats required...
The discussion outlines the current state and future potential of legged robotics, emphasizing significant advancements in teaching robots to walk and navigate challenging environments through simulation and reinforcement learning. However, challenges remain in achieving high reliability and adaptability in real-world settings, primarily due to the sim-to-real gap and complex perception-based navigation. Researchers are exploring both end-to-end deep learning models and modular control approaches, with the latter showing greater practicality in the short term. The conversation highlights the difficulties in translating simulation-based learning to real-world environments, stressing the need for robust reward functions and semantic understanding. It also addresses the challenges of deploying robots in industrial vs. home settings, the role of imitation learning and reinforcement learning, and the use of large vision-language models in complex task orchestration. Despite rapid progress, translating laboratory success to reliable real-world applications remains a key challenge in robotics development.
9 Jun 2026 Is RAG Dead? Lessons from Building AI for Tax Law with Alex Bowcut
The podcast examines Retrieval-Augmented Generation's evolving role in AI-driven tax compliance, focusing on Spheres AI's TRAM model, challenges in processing fragmented legal data, and the need for accurate citations, taxonomy integration, and real-time compliance automation via a global tax legislation index.
21 May 2026 Relational Foundation Models for Enterprise Data with Jure Leskovec
Relational foundation models and graph-based machine learning, like GNNs, enable accurate predictions on structured data across biomedical research and industries by capturing complex relationships, integrating multi-scale data, and overcoming traditional limitations through automated feature extraction and hybrid modeling.
7 May 2026 How to Find the Agent Failures Your Evals Miss with Scott Clark
Distributional employs post-production analytics, unsupervised learning, and LLMs to analyze agent traces, detect patterns and anti-patterns like hallucinations, address distributional shifts, and generate actionable insights for AI system refinement in security and enterprise settings, emphasizing adaptive analytics and domain expertise.
30 Apr 2026 How to Engineer AI Inference Systems with Philip Kiely
AI inference deployment is accelerating, emphasizing inference engineering's critical role in optimizing generative models with advanced hardware and complex systems, while addressing challenges like latency, scalability, and modality-specific optimizations amid evolving industry trends and fragmented yet open-source-driven markets.
16 Apr 2026 How Capital One Delivers Multi-Agent Systems with Rashmi Shetty
Capital One's *Chat Concierge* multi-agentic AI system streamlines car-buying through self-reflection, real-time APIs, and LLM-driven workflows, addressing enterprise AI challenges like governance, scalability, and legacy system integration while prioritizing compliance, observability, and flexible platform adoption.