·
AI & ML interests
Work with agentic systems, agent memory, model fine tuning and unlearning, generative AI, and the development and deployment of open source AI
Recent Activity
Organizations
view article An LLM erases a concept by editing diffusion weights directly, without gradients
view article AtMem routed-v4 on DolphinBench: 479/600, and what the failed actions show
javadtaghia
• • 3
view article AtMem 2.3.10: Bounded Evidence Discovery for Persistent Agent Memory
javadtaghia
• view article AtMem 2.3.9: Shared Memory for Coding Agents, and What Our Benchmarks Actually Showed
javadtaghia
• published an article about 1 month ago view article We Fine-Tuned a Memory Classifier for Our Agent. Here's Why We Didn't Ship It
published an article about 1 month ago view article AtMem From remembering relevant text to assembling usable evidence
published an article about 1 month ago view article RLCD: Are We Moving from AI Models That Generate Answers to Models That Make Calibrated Decisions?
published an article about 2 months ago published an article about 2 months ago view article Governed Agent Memory with Structured Judgment: An AtMem–Jev Retrieval Study
view article AtMem: Governed Memory and a Black Box for AI Agents
view article MAD GRPO: Treating Dr. GRPO that tried to fix GRPO but brought instability and verbosity bias
view article Unified Concept Editing in Text-to-Image Diffusion Models Review check
view article Targeted Unsupervised Machine Unlearning in Latent Diffusion (UNet or Transformer Denoiser)
javadtaghia
• view article Unlearning, practical guide for text-to-image extending "machine unlearning for image-to-image generative models"
javadtaghia
• view article What does all of these mean?
javadtaghia
• • 1
view article Train image-to-image SDXL UNet Finetuning Practical with code (Local Dataset)
javadtaghia
•