Notizie
Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation
arXiv:2506.00288v3 Announce Type: replace Abstract: Continued pretraining (CPT) is a popular approach to adapt existing...
ElevenLabs debuts Conversational AI 2.0 voice assistants that understand when to pause, speak, and take turns talking
With Conversational AI 2.0, ElevenLabs aims to provide tools and infrastructure for truly intelligent, context-aware...
EG-CFG: Enhancing Code Generation with Real-Time Execution Feedback
LLMs have made impressive strides in generating code for various programming tasks. However, they mostly...
Efficient Trie-based Biasing using K-step Prediction for Rare Word Recognition
arXiv:2509.09196v1 Announce Type: new Abstract: Contextual biasing improves rare word recognition of ASR models by...
Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking
arXiv:2501.18265v2 Announce Type: replace-cross Abstract: Evaluating the truthfulness of online content is critical for combating...
EEG-MedRAG: Enhancing EEG-based Clinical Decision-Making via Hierarchical Hypergraph Retrieval-Augmented Generation
arXiv:2508.13735v1 Announce Type: new Abstract: With the widespread application of electroencephalography (EEG) in neuroscience and...
Echoes of BERT: Do Modern Language Models Rediscover the Classical NLP Pipeline?
arXiv:2506.02132v4 Announce Type: replace Abstract: Large transformer-based language models dominate modern NLP, yet our understanding...
Echoes of Automation: The Increasing Use of LLMs in Newsmaking
arXiv:2508.06445v2 Announce Type: replace Abstract: The rapid rise of Generative AI (GenAI), particularly LLMs, poses...
Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization
arXiv:2505.24229v1 Announce Type: new Abstract: Inverse Text Normalization (ITN) is crucial for converting spoken Automatic...
Dynamic Acoustic Model Architecture Optimization in Training for ASR
arXiv:2506.13180v2 Announce Type: replace Abstract: Architecture design is inherently complex. Existing approaches rely on either...
DVAGen: Dynamic Vocabulary Augmented Generation
arXiv:2510.17115v1 Announce Type: new Abstract: Language models trained with a fixed vocabulary struggle to generalize...
DualDistill and Agentic-R1: How AI Combines Natural Language and Tool Use for Superior Math Problem Solving
Existing long-CoT reasoning models have achieved state-of-the-art performance in mathematical reasoning by generating reasoning trajectories...
