About
Research & Development
LoReUn: A Smarter Approach to Machine Unlearning Through Data Loss Cues
TLDR: LoReUn is a new machine unlearning method that improves efficiency and effectiveness by reweighting data based on its "loss" (how well the model...
Research & Development
Optimizing LLM Privacy with Dynamic Reinforcement Learning
TLDR: RLDP is a new framework that uses reinforcement learning to dynamically adjust privacy parameters (gradient clipping and noise) during the fine-tuning of large...
Research & Development
RePaCA: Boosting Automated Bug Fix Assessment with Reasoning AI
TLDR: RePaCA is a new static Automated Patch Correctness Assessment (APCA) technique that uses Large Language Models (LLMs) specialized in reasoning to identify 'overfitting...
Research & Development
VL-Cogito: Advancing Multimodal Reasoning Through Structured Learning
TLDR: VL-Cogito is a new multimodal reasoning model trained with a Progressive Curriculum Reinforcement Learning (PCuRL) framework. This framework systematically guides the model through...
Research & Development
Enhancing Industrial Process Control with Safe Offline Reinforcement Learning
TLDR: This research introduces a method to safely deploy offline reinforcement learning (RL) in chemical process systems, specifically for controlling a polymerization reactor. It...
Research & Development
Unpacking AI’s Role in Software Security: A Deep Dive into Vulnerability Detection
TLDR: This systematic review examines 227 studies from 2020-2025 on using Large Language Models (LLMs) for software vulnerability detection. It categorizes existing methods by...