12 papers
Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve
Denys Pushkin, Albert Q. Jiang, Aryo Lotfi +3
Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to elicit step-by-step reasonin…
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +274
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
Jinho Choo, JunSeung Lee, Jimyeong Kim +3
Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known…
Voxtral Realtime
Mistral-AI, :, Alexander H. Liu +166
We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adap…
SounDiT: Geo-Contextual Soundscape-to-Landscape Generation
Junbo Wang, Haofeng Tan, Bowen Liao +7
Recent audio-to-image models have shown impressive performance in generating images of specific objects conditioned on their corresponding sounds. However, these models fail to rec…
Towards Artwork Explanation in Large-scale Vision Language Models
Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito +2
Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating capabilities in text generation and comprehension. However, it has not been clari…