About
News & Current Events
India Launches National Policy Challenge 2025 on Generative AI: Shaping Future Governance
TLDR: The Data Security Council of India (DSCI), in collaboration with Kautilya School of Public Policy (KSPP), has announced the 'National Policy Challenge 2025'...
Research & Development
Generating Realistic Hypergraphs with Large Language Models: The HyperLLM Approach
TLDR: HyperLLM is a novel framework that uses Large Language Models (LLMs) and a multi-agent system to generate realistic, high-order hypergraphs. It overcomes the...
Research & Development
AwareCompiler: A New Approach to Smarter Program Optimization
TLDR: AwareCompiler is an agentic framework for compiler optimization that uses a combined knowledge-data-driven approach to enhance program performance. It addresses challenges like semantic...
Research & Development
AI Models Learn to Prove Theorems by Challenging Themselves
TLDR: GAR (Generative Adversarial Reinforcement Learning) is a new AI training framework that significantly improves formal theorem proving. It works by having an AI...
Research & Development
Curative Prompt Refinement: Improving LLM Accuracy by Fixing User Prompts
TLDR: Curative Prompt Refinement (CPR) is a new plug-and-play framework that uses a fine-tuned small language model (SLM) to mitigate hallucinations in large language...
Research & Development
PACE: A New Way to Measure AI’s Creative Thinking
TLDR: PACE (Parallel Association Chain Evaluation) is a novel, efficient metric for evaluating the creativity of large language models (LLMs). Inspired by human creativity...