About
Research & Development
Unveiling PianoVAM: A New Multimodal Dataset for Piano Performance Analysis
TLDR: PianoVAM is a new, comprehensive multimodal dataset for piano performance research, featuring synchronized videos, audio, MIDI, hand landmarks, fingering labels, and metadata. Collected...
Research & Development
Bridging Morphological Gaps: MoVoC for Ge’ez Script NLP
TLDR: A new tokenization method called MoVoC (Morpheme-aware Subword Vocabulary Construction) is introduced for Ge'ez script languages. It combines morpheme-based analysis with subword encoding...
Research & Development
EnvX: Transforming Open-Source Repositories into Intelligent AI Agents
TLDR: EnvX is a novel framework that uses Agentic AI to convert GitHub repositories into intelligent, autonomous agents. It streamlines software reuse by automating...
Research & Development
Boosting Embodied AI Decisions with Thought-Centric Optimization
TLDR: A new research paper introduces Thought-Centric Preference Optimization (TCPO), an algorithmic framework designed to improve how Vision Language Models (VLMs) make decisions in...
Research & Development
No-Knowledge Alarms: How Logical Consistency Reveals Misaligned AI Evaluators
TLDR: This paper introduces 'no-knowledge alarms' to detect misaligned LLM judges without needing ground truth. By analyzing how LLM judges agree and disagree, the...
Research & Development
Causal Inference Unlocks Automated Debugging for Multi-Agent Systems
TLDR: A new research paper introduces the first failure attribution framework for Multi-Agent Systems (MAS) based on multi-granularity causal inference. It addresses the limitations...