ข่าว
Data Augmentation for Spoken Grammatical Error Correction
arXiv:2507.19374v1 Announce Type: new Abstract: While there exist strong benchmark datasets for grammatical error correction...
Data Augmentation for Maltese NLP using Transliterated and Machine Translated Arabic Data
arXiv:2509.12853v1 Announce Type: new Abstract: Maltese is a unique Semitic language that has evolved under...
DanaBot takedown shows how agentic AI cut months of SOC analysis to weeks
Agentic AI played a decisive role in dismantling DanaBot, a Russian malware platform responsible for...
D’ej`a Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation
arXiv:2504.11829v3 Announce Type: replace Abstract: Generation capabilities and language coverage of multilingual large language models...
Customizing Speech Recognition Model with Large Language Model Feedback
arXiv:2506.11091v2 Announce Type: replace Abstract: Automatic speech recognition (ASR) systems have achieved strong performance on...
Curved Inference: Concern-Sensitive Geometry in Large Language Model Residual Streams
arXiv:2507.21107v1 Announce Type: new Abstract: We propose Curved Inference – a geometric Interpretability framework that...
CURE: A Reinforcement Learning Framework for Co-Evolving Code and Unit Test Generation in LLMs
Introduction Large Language Models (LLMs) have shown substantial improvements in reasoning and precision through reinforcement...
CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions
arXiv:2508.01674v1 Announce Type: new Abstract: Personalization of Large Language Models (LLMs) often assumes users hold...
CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations
arXiv:2512.23328v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents, while proficient in the digital...
CTISum: A New Benchmark Dataset For Cyber Threat Intelligence Summarization
arXiv:2408.06576v2 Announce Type: replace Abstract: Cyber Threat Intelligence (CTI) summarization involves generating concise and accurate...
CTGT wins Best Presentation Style award at VB Transform 2025
San Francisco-based CTGT, a startup focused on making AI more trustworthy through feature-level model customization...
CSCBench: A PVC Diagnostic Benchmark for Commodity Supply Chain Reasoning
arXiv:2601.01825v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success in general...
