Vision-language-action (VLA) models perform versatile manipulation tasks from language instructions, but their inference cost limits how fast a robot can respond in closed-loop control. Visual token pruning reduces this cost; however, prior methods estimate token redundancy from encoded visual embeddings or attention,...
Sungwon Moon, Minji Kim, Hyemin Boo et al.· 0 citations
Extended reasoning has substantially improved multimodal large language models (MLLMs) on tasks requiring compositional and relational inference. However, multimodal grounding imposes a distinct requirement: reasoning must ultimately converge on a target-specific compact representation that supports precise localizatio...
J. Seo, Hyeongjun Kwon, Jiyoung Lee et al.· 0 citations
TiTok is presented, an audio-visual large language model (AV-LLM) that localizes an arbitrary number of temporal event segments for each query, and the Time Token Interleaving (TTI) method is introduced, which explicitly injects special time tokens into the audio-visual stream to align input-side temporal perception wi...
Eunji Shin, Dahyun Choi, Seungyeon Jo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.