LLM
Variability Modeling Meets LLMs: Tuning Inference Parameters
New research applies software product line variability modeling to systematically optimize LLM inference hyperparameters like temperature and sampling strategies.
Latest
AI Agents
MIRA: Combining Memory Systems with RL for Smarter AI Agents
New research introduces MIRA, a framework that integrates memory architectures with reinforcement learning while minimizing expensive LLM calls, advancing efficient autonomous agent design.
AI Agents
2025 AI Agent Index: Mapping Safety Features Across Deployed Syst
New research systematically documents technical and safety features across deployed agentic AI systems, creating a comprehensive index for understanding how autonomous AI operates in the wild.
LLM Safety
Can Parameter Region Constraints Make LLMs Safer?
New research explores whether constraining specific parameter regions in large language models can ensure safety, examining the theoretical foundations of alignment through architectural constraints.
Machine Unlearning
Agentic Unlearning: Teaching AI Agents to Forget Responsibly
New research explores machine unlearning for LLM agents, addressing how autonomous AI systems can selectively forget data while maintaining tool-use and reasoning capabilities.
AI security
IARPA TrojAI Program: Detecting Hidden Backdoors in AI Models
IARPA's TrojAI program releases final report on detecting trojan attacks in AI systems, covering image classifiers, NLP models, and reinforcement learning with implications for synthetic media security.
World Models
World Models: The Technical Foundation Behind AI Video Generation
From cognitive science mental simulators to Sora's video generation, world models represent AI's ability to predict and simulate reality—the core technology powering synthetic media.
AI Architecture
Memory Injections: The Next Evolution Beyond RAG for AI
RAG has limitations. Memory injection techniques offer AI assistants persistent, contextual memory that transforms how they understand and respond to users over time.
deepfakes
UC Deepfake Threats: 3 Enterprise Attack Vectors Exposed
Enterprise unified communications face growing deepfake threats from voice cloning fraud to video impersonation. Examining three critical attack vectors targeting business communications infrastructure.
AI Agents
OpenPlanter: Open Source Recursive AI Agent for Surveillance
OpenPlanter brings Palantir-style recursive AI agent capabilities to the open-source community, enabling micro surveillance use cases with transparent, auditable AI systems.
Multi-Agent Systems
Supervisor Agents: Orchestrating Multi-Agent AI Systems
Learn how supervisor agents coordinate specialized AI workers in multi-agent systems. This guide covers architectural patterns, LangGraph implementation, and practical orchestration strategies.
AI Agents
How to Build Self-Improving AI Agents Using Langfuse
Learn how to create AI support agents that continuously improve through feedback loops using Langfuse observability. A technical guide to building autonomous systems that learn from interactions.