Episodes

EP25 - GPQA: A Graduate-Level Google-Proof Q&A Benchmark

EP24 - ProAgent: From Robotic Process Automation to Agentic Process Automation

EP23 - GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration

EP22 - MultiLoRA: Democratizing LoRA for Better Multi-Task Learning

EP21 - ToolTalk: Evaluating Tool-Usage in a Conversational Setting

EP20 - Memory Augmented Language Models through Mixture of Word Experts

EP19 - VideoCon: Robust Video-Language Alignment via Contrast Captions

EP18 - I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization

EP17 - Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers

EP16 - Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning