About
Research & Development
Enhancing AI Creative Writing with Dynamic Mixed Rewards
TLDR: RLMR (Reinforcement Learning with Mixed Rewards) is a new framework that helps large language models balance subjective writing quality (like emotional expression) with...
Research & Development
Measuring AI Smarts: IQ, EQ, and Professional Skills for Language Models
TLDR: A new research paper proposes an anthropomorphic evaluation framework for Large Language Models (LLMs), moving beyond traditional benchmarks. It introduces a novel IQ-EQ-PQ...
Research & Development
AniME: Streamlining Anime Production Through Adaptive AI Planning
TLDR: AniME is a director-oriented multi-agent AI system developed by Bilibili that automates the entire long-form anime production process, from story to final video....
Research & Development
Advancing Mathematical Autoformalization with Unlabeled Data Using FormaRL
TLDR: FormaRL is a new reinforcement learning framework that significantly improves autoformalization accuracy by translating natural language math into formal languages like Lean. It...
Research & Development
AI Tool CTGraph Profiles Student Learning in Online Systems
TLDR: CTGraph is a self-supervised graph-level representation learning approach that profiles student behaviors and performance in curriculum-based online learning systems. It provides a holistic...
Research & Development
Building Intelligent Systems with Concurrent Modular Agents
TLDR: The Concurrent Modular Agent (CMA) is a novel framework for autonomous LLM agents that orchestrates multiple, asynchronously operating LLM-based modules. It fosters flexible,...