About
Research & Development
Unmasking and Crafting Hidden Promotions in AI Conversations
TLDR: This paper from JU-NLP presents a comprehensive framework for both generating and detecting covert advertisements within conversational AI systems. For generation, they fine-tune...
Research & Development
SCoRe: Enabling Smaller LLM Agents to Match Large Model Performance Through Targeted Correction and Reinforcement Learning
TLDR: SCoRe is a novel framework for distilling Large Language Model (LLM) agents, allowing smaller student models to achieve performance comparable to much larger...
Research & Development
AI System Uncovers New Mathematical Theorems Through In-Context Learning
TLDR: A new AI system called "Conjecturing-Proving Loop" uses Large Language Models (LLMs) to automatically generate and prove novel mathematical theorems in Lean 4....
Research & Development
SCoGen: A New Framework for Generating Realistic Code Problems for AI Models
TLDR: SCoGen is a novel framework that synthesizes real-world coding problems to train large language models (LLMs). It extracts domain knowledge, domain skills, coding...
Research & Development
FlowDrive: Enhancing Autonomous Driving with Energy Flow Fields
TLDR: FlowDrive is a new end-to-end autonomous driving framework that introduces physically interpretable energy-based flow fields (risk potential and lane attraction fields) into the...
Research & Development
The Coreference Conundrum: Why LLMs Struggle to Balance Accuracy and Ambiguity Detection
TLDR: A new research paper, "CORRECT-DETECT," reveals a fundamental trade-off in Large Language Models (LLMs): they struggle to simultaneously achieve high accuracy in coreference...