Browsing: Hugging Face
Large reasoning models achieve strong performance through test-time scaling but incur substantial computational overhead, particularly from excessive token generation when…
When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs – Takara TLDR
As large language models become increasingly integrated into daily life, audio has emerged as a key interface for human-AI interaction.…
Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering…
Large Multimodal Models (LMMs) have witnessed remarkable growth, showcasing formidable capabilitiesin handling intricate multimodal tasks with exceptional performance. Recent research…
A structured framework and datasets for training customer service agents using well-defined support strategies improve the quality of customer support…
Research investigates reasoning failures in language models for multi-hop question answering, introducing a framework to categorize errors and improve model…
MOSEv2, a more challenging dataset, highlights the limitations of current VOS methods in real-world scenarios with increased complexity and diverse…
Paper page – PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
PRvL presents the first comprehensive, open-source benchmark and toolkit for evaluating and deploying LLM-based PII redaction, systematically comparing architectures, training…
Recently, Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks.…
Simultaneous Speech Translation (SimulST) systems stream in audio while simultaneously emitting translated text or speech. Such systems face the significant…