AI
TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation
Researchers have created a collection of open-source machine translation resources for 19 Sub-Sahara...
AI
X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance
Researchers have developed a new text-to-speech system called X2Streaming-TTS that can generate spee...
AI
Learning What to Fail On: Failure-Mode Contextual Bandits for Adversarial Data Curation
Researchers have developed a new method for improving the robustness of natural language understandi...
AI
Execution-grounded evaluation reveals hidden failures in language-model calculations for environmental science
Researchers have developed a new benchmark called AtmosCoder-Bench to evaluate the performance of la...
AI
Learning Canonical Register Automata over Ordered Data Domains
Researchers have developed a new method for training deterministic register auto...
AI
Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning
Researchers have proposed a defense mechanism called Gradient Mirage to protect ...
AI
Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model
Researchers have found that large language models (LLMs) can be faithful and use...
AI
Assessing Quality of Experience in Natural Language Generation of German Text
Researchers have created a new dataset called TextQ-German to evaluate the quali...