SpeechGym is presented, an audio-native agentic environment in which two omni-modal models converse in native audio, with no external ASR or TTS and no API boundary, over the unmodified tasks, tools and success check of an established text agentic benchmark, so that the interaction modality is the only variable and the...
A novel evaluation framework called Image2Text2Image is proposed, which leverages diffusion models, such as Stable Diffusion or DALL-E, for text-to-image generation, and does not rely on human-annotated reference cap-tions, making it a valuable tool for assessing image captioning models.
Jia-Hong Huang, Hongyi Zhu, Yixian Shen et al.· 0 citations
MMArt is introduced, a large-scale dataset of 74,234 WikiArt paintings, each annotated with four independently annotated perspectives plus a harmonized unified caption, produced by specialized vision-language models or human annotation and validated through complementary quality evaluations.
Shuai Wang, Wang-Yuan Ding, Yixian Shen et al.· 0 citations
Reading a base Qwen3-Omni with a logit lens at the audio-token positions, it is found that the answer to a spoken question becomes legible - in words - in the model's middle layers, before it emits any token.
