About
Research & Development
Smarter Jailbreak Attacks: How AutoDAN-Reasoning Enhances LLM Vulnerability Discovery
TLDR: AutoDAN-Reasoning is a new framework that significantly improves the effectiveness of LLM jailbreak attacks by enhancing the existing AutoDAN-Turbo. It introduces two test-time...
Research & Development
Beyond Retrieval: How Input Length Alone Challenges Large Language Models
TLDR: A new study reveals that Large Language Models (LLMs) experience significant performance degradation on long-context tasks, even when they perfectly retrieve all necessary...
Research & Development
AI Agents Tackle Legacy Code Testing with Formal Verification
TLDR: UnitTenX is an open-source AI multi-agent system that combines AI agents, Large Language Models (LLMs), and formal verification to automatically generate unit tests...
Research & Development
Advancing Synthetic ECG Generation for Personalized Cardiac AI
TLDR: A new framework, MIDT-ECG, generates high-fidelity, personalized, and privacy-preserving synthetic ECG data. It uses mel-spectrogram informed training for realistic morphology and multi-modal demographic...
Research & Development
Intelligent Feature Selection: A Unified Approach for Robust and Privacy-Preserving Data Analysis
TLDR: This research introduces CAPS, a framework for automated feature selection that uses permutation-invariant embeddings and reinforcement learning to find optimal feature subsets, overcoming...
Research & Development
Unlocking Human-Object Interaction Detection with Language Models
TLDR: HOI-R1 is a new framework that uses Multimodal Large Language Models (MLLMs) to detect human-object interactions (HOID) directly through natural language reasoning, eliminating...