Tag
NetEase Youdao open-sourced Confucius4-R2T2, a streaming ASR model for voice agents that incrementally processes speech and emits only committed text to prevent state corruption.
The paper proposes Kraken, an LLM-based speech-to-speech translation model using low-bitrate vector quantization and dual-path source conditioning to enhance translation quality and preserve speaker prosody, built on Qwen3-8B.
SimSkill is a lifelong learning AI agent that autonomously masters traffic simulation by identifying capability gaps, generating tasks, and using memory systems to improve performance, showing up to 25% improvement in task completion on benchmarks.
VibeVoice-ASR-Streaming is an LLM-based end-to-end model for streaming speaker-attributed speech recognition, achieving state-of-the-art performance with released 1.5B and 7B model weights.
EditPPT introduces a multi-agent framework for accurate and faithful slide editing in long decks, using structured tool-using and dual-modal validators, and presents the DeckEdit-Bench benchmark.
Dartwords is a new daily word game that uses a local LLM for conversational hints, inspired by Wordle and Clippy, and has launched today on the web.
LELA is an LLM-based entity linking framework that combines zero-shot NER and entity disambiguation into an end-to-end Python library, validated across diverse settings.