OriginBlame: A Record-Level Data Provenance System for Precise AI Training Data Removal
When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require a forget set, yet no tool can locate which training records belong to a given author…
Read the full articleYou might also wanna read
Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
arXiv:2607.09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving al
OpenAI strengthens content provenance with multi-layered verification approach for AI-generated media
OpenAI advances AI content provenance with Content Credentials, SynthID, and a verification tool to help people identify and trust AI-genera
openai.com·1mo ago
DataSTORM: An LLM Agent System for Deep Research on Large-Scale Structured Databases
Deep research with Large Language Model (LLM) agents is emerging as a powerful paradigm for multi-step information discovery, synthesis, and
arxiv.org·8d ago
Large Language Models Enable Effective Deanonymization of Pseudonymous Online Users
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hac
arxiv.org·4mo agoUltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
arXiv:2607.08646v1 Announce Type: new Abstract: As available training data approaches its physical limit, gains from Scaling Laws have begun
(PR) Bosgame Demonstrates Scalable Private AI with 7-Node AI MAX+ 395 Cluster
Bosgame, a technology-based electronic product brand, has demonstrated distributed inference of the DeepSeek-V3.1 671B-parameter model on it
Comments
Sign in to join the conversation.
No comments yet. Be the first.