Beyond one-on-one: Authoring, simulating, and testing dynamic human-AI group conversations
Human-Computer Interaction and Visualization
-
-
-
How to Build a Matryoshka-Optimized Sentence Embedding Model for Ultra-Fast Retrieval with 64-Dimension Truncation
In this tutorial, we fine-tune a Sentence-Transformers embedding model using Matryoshka Representation Learning so that the earliest dimensions of the vector carry the most useful semantic signal. We train with MatryoshkaLoss on triplet data and then validate the key promise of MRL by benchmarking retrieval quality after truncating embeddings to 64, 128, and 256 dimensions….
-
How to Build an Atomic-Agents RAG Pipeline with Typed Schemas, Dynamic Context Injection, and Agent Chaining
In this tutorial, we build an advanced, end-to-end learning pipeline around Atomic-Agents by wiring together typed agent interfaces, structured prompting, and a compact retrieval layer that grounds outputs in real project documentation. Also, we demonstrate how to plan retrieval, retrieve relevant context, inject it dynamically into an answering agent, and run an interactive loop that…
-
NVIDIA Researchers Introduce KVTC Transform Coding Pipeline to Compress Key-Value Caches by 20x for Efficient LLM Serving
Serving Large Language Models (LLMs) at scale is a massive engineering challenge because of Key-Value (KV) cache management. As models grow in size and reasoning capability, the KV cache footprint increases and becomes a major bottleneck for throughput and latency. For modern Transformers, this cache can occupy multiple gigabytes. NVIDIA researchers have introduced KVTC (KV…
-
AI-powered procurement: Turning messy data into strategic advantage
In today’s digital economy, procurement teams have to deal with large volumes of unstructured spend data, such as free-text invoices and broken ERP entries. AI is becoming a powerful tool for cleaning, combining, and analyzing this information. Companies that use AI-driven procurement are seeing major real-world benefits. For example, an IBM study found that costs…
-
Google AI Introduces Natively Adaptive Interfaces (NAI): An Agentic Multimodal Accessibility Framework Built on Gemini for Adaptive UI Design
Google Research is proposing a new way to build accessible software with Natively Adaptive Interfaces (NAI), an agentic framework where a multimodal AI agent becomes the primary user interface and adapts the application in real time to each user’s abilities and context. Instead of shipping a fixed UI and adding accessibility as a separate layer,…
-
How to Design Complex Deep Learning Tensor Pipelines Using Einops with Vision, Attention, and Multimodal Examples
In this tutorial, we walk through advanced usage of Einops to express complex tensor transformations in a clear, readable, and mathematically precise way. We demonstrate how rearrange, reduce, repeat, einsum, and pack/unpack let us reshape, aggregate, and combine tensors without relying on error-prone manual dimension handling. We focus on real deep-learning patterns, such as vision…
-
Alibaba Open-Sources Zvec: An Embedded Vector Database Bringing SQLite-like Simplicity and High-Performance On-Device RAG to Edge Applications
Alibaba Tongyi Lab research team released ‘Zvec’, an open source, in-process vector database that targets edge and on-device retrieval workloads. It is positioned as ‘the SQLite of vector databases’ because it runs as a library inside your application and does not require any external service or daemon. It is designed for retrieval augmented generation (RAG),…
-
Data pipeline design playbook 2026
What’s inside the playbook? This isn’t just theory. It’s a tactical guide to the 7 frameworks that are defining the 2026 data landscape: The kappa shift: Learn why treating everything as a stream is the secret to 100% data consistency. ELT vs. ETL: Why the transform-last approach is saving engineers 20+ hours of maintenance a week. Modern data lakes: Practical…
