Researchers have developed a new text-to-speech system called X2Streaming-TTS that can generate speech from uncertain prefixes and maintain perceptual...
Researchers have developed a new method for improving the robustness of natural language understanding models. Their approach, called failure-mode con...
Researchers have developed a new benchmark called AtmosCoder-Bench to evaluate the performance of large language models in environmental science. Unli...
Researchers have developed a new method for training deterministic register automata (DRAs) on data from infinite alphabets. This approach involves us...
Researchers have proposed a defense mechanism called Gradient Mirage to protect large language models from gradient matching attacks. These attacks re...
Researchers have found that large language models (LLMs) can be faithful and useful in simulating survey respondents, but only if they use a specific ...
Researchers have created a new dataset called TextQ-German to evaluate the quality of text generated by natural language processing systems. The datas...
Researchers have developed a system to extract high-quality data from historical newspaper scans. The Institutional Newspapers Pipeline uses a multi-s...
Researchers have investigated whether internal representation statistics can provide useful difficulty signals for adaptive inference in multilingual ...
Researchers have identified a trade-off between detecting hate speech and protecting online users' privacy. They found that some hate speech detection...
Researchers have proposed a new framework for evaluating the effectiveness of verifiers used with large language models (LLMs). The Verification Auton...
Researchers from Harvard University have developed an open-source pipeline called Enriched Text that can handle large collections of digitized books. ...