Generative AI
How This Agentic Memory Study Compares Long- and Short-Term Memory for LLM Agents
January 12, 2026
How This Agentic Memory Study Compares Long- and Short-Term Memory for LLM Agents
How to design an LLM agent that determines itself what to keep in long-term memory, what to keep in short-term…
Coding Guide to Demonstration of Targeted Data Poisoning Attacks in Deep Learning with Label Browsing in CIFAR-10 with PyTorch
January 11, 2026
Coding Guide to Demonstration of Targeted Data Poisoning Attacks in Deep Learning with Label Browsing in CIFAR-10 with PyTorch
In this tutorial, we demonstrate a practical data poisoning attack by manipulating labels in the CIFAR-10 dataset and seeing its…
Meta and Harvard Researchers Introduce Confucius Code Agent (CCA): A Software Engineering Agent That Can Work on Large Codebases
January 9, 2026
Meta and Harvard Researchers Introduce Confucius Code Agent (CCA): A Software Engineering Agent That Can Work on Large Codebases
How far can the centralized language model go if real innovation moves from the core to the agent framework and…
How to Build Portable, In-Data Pipelines for Engineering Features with Ibis Using Lazy Python APIs and DuckDB Releases
January 9, 2026
How to Build Portable, In-Data Pipelines for Engineering Features with Ibis Using Lazy Python APIs and DuckDB Releases
In this tutorial, we show how we use it Ibis building a portable, in-domain engineering feature pipeline that looks and…
Stanford Researchers Build Sleep ClinicFM: Multimodal Sleep Foundation's AI Model for 130+ Disease Predictions
January 8, 2026
Stanford Researchers Build Sleep ClinicFM: Multimodal Sleep Foundation's AI Model for 130+ Disease Predictions
A team of Stanford Medicine researchers has launched SleepFM Clinical, a sleep-based multivariate model that learns from clinical polysomnography and…
Code Implementation of an Integrated Apache Beam Pipeline Showing Batch and Stream Processing with Event Time Windowing Using DirectRunner
January 7, 2026
Code Implementation of an Integrated Apache Beam Pipeline Showing Batch and Stream Processing with Event Time Windowing Using DirectRunner
In this lesson, we show how to build unity Apache Beam A pipeline that works seamlessly in both batch and…
TII Abu-Dhabi Releases Falcon H1R-7B: A New Mathematical-Efficient Reference Model with Only 7B Params and 256k Context Window
January 7, 2026
TII Abu-Dhabi Releases Falcon H1R-7B: A New Mathematical-Efficient Reference Model with Only 7B Params and 256k Context Window
The Technology Innovation Institute (TII), Abu Dhabi, has released the Falcon-H1R-7B, a special 7B-parameter imaging model that matches or surpasses…
Implementing Softmax From Scratch: Avoiding the Numerical Stability Trap
January 7, 2026
Implementing Softmax From Scratch: Avoiding the Numerical Stability Trap
In deep learning, classification models don't just need to make predictions—they need to express confidence. This is where Softmax's activation…
How to Design an Agenttic AI Architecture with LangGraph and OpenAI Using Adaptive Deliberation, Memory Graph, and Reflection Loops
January 6, 2026
How to Design an Agenttic AI Architecture with LangGraph and OpenAI Using Adaptive Deliberation, Memory Graph, and Reflection Loops
In this tutorial, we build a truly advanced Agentic AI system using LangGraph and OpenAI models by bypassing simple scheduler,…
Liquid AI Releases LFM2.5: A Unified Family Model for Real AI on Device Agents
January 6, 2026
Liquid AI Releases LFM2.5: A Unified Family Model for Real AI on Device Agents
Liquid AI has introduced the LFM2.5, a new generation of basic micromodels built on the LFM2 architecture and focused on…