Machine Learning

AI Safety

Formal Verification Breakthrough for Early-Exit Neural Networks

New research bridges efficiency and safety by developing formal verification methods for neural networks with early exits, enabling mathematically proven safety guarantees for adaptive AI systems.

LLM Agents

GenEnv: Co-Evolving LLM Agents with Adaptive Environment Simulato

New research introduces GenEnv, a framework where LLM agents and environment simulators co-evolve through difficulty-aligned training, enabling more robust agent capabilities.

AI Agents

Inside AI Coding Agents: Architecture, Tools, and Agentic Loops

A technical deep dive into how AI coding agents work, from tool-calling mechanisms and agentic loops to planning systems and memory architectures that enable autonomous code generation.

AI Security

Adversarial Attacks on LLM Resume Screeners Reveal AI Security Ga

New research exposes how adversarial techniques can manipulate LLM-based resume screening systems, revealing fundamental security vulnerabilities in specialized AI applications.

LLM Agents

ABBEL: Language-Based Belief Bottlenecks Improve LLM Agents

New research introduces ABBEL, an architecture that constrains LLM agents to act through explicit belief states expressed in natural language, improving interpretability and decision-making in complex environments.

LLM Research

Behavioral RL Method Tackles LLM Hallucinations Head-On

New research introduces Behaviorally Calibrated Reinforcement Learning to reduce AI hallucinations by aligning model confidence with actual accuracy, improving reliability in language models.

LLM Training

How ChatGPT, Claude, and Gemini Are Trained: The 3-Stage Pipeline

Modern LLMs undergo three critical training stages: pretraining on massive text corpora, supervised fine-tuning for instruction following, and RLHF for alignment. Here's how the pipeline works.

Neural Networks

Training Neural Networks Without Backpropagation

New research proposes training graph-based neural networks using few-shot learning without traditional backpropagation, potentially revolutionizing how AI models are trained.

MLOps

When Should You Switch ML Models for New Data Sources?

New research tackles a critical MLOps question: determining when incoming data sources justify replacing your production model with a retrained challenger.

LLM Research

Researchers Discover Hidden MoE Architecture Inside Dense LLMs

New research reveals that standard dense language models contain secret Mixture-of-Experts structures, challenging our understanding of neural network architectures and opening paths to more efficient AI.

Neural Networks

Guided Descent: Scaling Neural Network Training Optimization

New research explores optimization algorithms for large-scale neural network training, examining gradient descent variants and convergence strategies critical to modern AI systems.

AMD

AMD's AIE4ML Framework: Compiling Neural Networks for NPUs

AMD researchers unveil AIE4ML, an end-to-end compiler framework that maps neural networks to next-gen AI Engines, achieving significant speedups over CPU implementations for ML workloads.