llm-based

Tag

Cards List
#llm-based

@rohanpaul_ai: Voice agents should consume speech incrementally but only act on committed text, because a fast transcript that mutates…

X AI KOLs Following · 4d ago Cached

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.

0 favorites 0 likes
#llm-based

Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning

arXiv cs.CL · 2026-09-14 Cached

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.

0 favorites 0 likes
#llm-based

SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic Simulation

arXiv cs.AI · 2026-09-04 Cached

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.

0 favorites 0 likes
#llm-based

VibeVoice-ASR-Streaming Technical Report

Hugging Face Daily Papers · 2026-09-02 Cached

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.

0 favorites 0 likes
#llm-based

EditPPT: Faithful Long-Deck Slide Editing via Structured Tool-Using Multi-Agent with Dual-Modal Validators

arXiv cs.CL · 2026-08-24 Cached

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.

0 favorites 0 likes
#llm-based

Wordle meets Clippy in this new word game

The Verge · 2026-08-17 Cached

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.

0 favorites 0 likes
#llm-based

LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation

arXiv cs.AI · 2026-05-27 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback