Recovering Model Weights Exactly Post-LoRA: New Discovery - AI Dynamics

Skip to content

AI Dynamics

Global AI News Aggregator

Rechercher

Recovering Model Weights Exactly Post-LoRA: New Discovery

By

–

15 August 2025 17h49

just learned that under certain conditions you actually CAN recover model weights *exactly*, post-LORA pretty crazy

→ View original post on X — @jxmnop

15 August 2025

AI CODE GENERATIVE AI MACHINE LEARNING RESEARCH SAFETY SECURITY

←AI Transforms 2D Images into Editable 3D Sculptures

New Vulnerability Enables Pre-Fine-Tuning Weight Recovery Attack→

MORE ARTICLES

Paper praised for executing Gato idea with humanoid; more work desired

28 June 2026
Skild Brain AI enables robots to handle unfamiliar environments

28 June 2026
Proposal to replace Google Search with Gemini

28 June 2026
Using video to learn control representations, touch important

28 June 2026

INNOVATION GENERATIVE AI RESEARCH LLMS TOOLS MACHINE LEARNING CODE MARKET TRENDS TECHNOLOGY BUSINESS BIG TECH ETHICS ENTERPRISE AI SOFTWARE AGENTS AUTOMATION APPS COMPUTING DATA POLICY OPEN SOURCE MULTIMODAL AI REGULATION CULTURE CREATIVE AI PROMPT ENGINEERING SOCIETY ECONOMY SAFETY EDUCATION INVESTMENT AI HARDWARE AGI HARDWARE JOBS STARTUPS INDUSTRY ROBOTICS WORKFORCE SECURITY CYBERSECURITY HEALTHCARE AI SYSTEMS SUSTAINABILITY WEB3 DECENTRALIZED AI

AI Dynamics

Global AI News Aggregator

About
Archives
Contact

Rechercher