Temporally-Grounded Language Generation: Towards Real-Time Vision-Language Models

The paper introduces Temporally-Grounded Language Generation (TGLG), a benchmark that tests vision‑language models on their ability to produce semantically accurate and temporally precise utterances in real‑time settings. It identifies perceptual updating and contingency awareness as key capabilities, curates datasets from sports broadcasting and egocentric interactions, and proposes the TRACE metric to jointly evaluate semantic similarity and temporal alignment. The authors also present VLM‑TSI, a model that interleaves visual and linguistic tokens in a time‑synchronized manner, achieving better performance than a strong baseline yet still showing modest overall results, underscoring the challenge of real‑time VLMs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• nlp
• multimodal
• benchmarks
• safety