About
Research & Development
Think2Sing: Advancing Expressive 3D Head Animation for Singers
TLDR: Think2Sing is a new AI framework that generates highly expressive and temporally coherent 3D head animations for singing. It uses "motion subtitles," derived...
Research & Development
DCPO: Enhancing LLM Reasoning Through Adaptive Clipping and Smoothed Reward Standardization
TLDR: DCPO (Dynamic Clipping Policy Optimization) is a new reinforcement learning method for large language models (LLMs) that improves their reasoning capabilities. It addresses...
Research & Development
Unveiling the Silent Thought Processes of Large Language Models
TLDR: This survey explores implicit reasoning in Large Language Models (LLMs), where models solve problems internally without showing intermediate steps. It introduces a taxonomy...
Research & Development
Beyond the Black Box: LLMs and the Evolution of AI Agents
TLDR: This paper provides a comprehensive reflection on the evolving field of agent technology, contrasting advancements driven by Large Language Models (LLMs) with classic...
Research & Development
Self-Organizing AI: HiV A’s Breakthrough in Agentic Workflow Evolution
TLDR: HiV A (Hierarchical Variable Agent) is a novel AI framework that enables autonomous agents to learn and adapt by simultaneously evolving their individual...
Research & Development
Connecting the Dots: How AI is Unifying Urban Data for Smarter City Management
TLDR: SIGMUS is an innovative system that uses Large Language Models (LLMs) to integrate and reason over fragmented multimodal urban data, including text, images,...