A 4B model that uses its own dense metric predictions as object-grounded evidence for language generation and leads the evaluated methods in instance-level metric depth estimation and overall accuracy on both relative and metric reasoning tracks, while broadly preserving general VQA performance and improving spatial un...
Jiang-Ning Wei, Yuan Yao, Miao-Miao Cui et al.· 0 citations
Listen-Write-Speak (LWS), a text-first tri-channel paradigm in which a single autoregressive LLM continuously listens to user audio, writes visible free-form text as its primary output, and speaks a realtime oral response in parallel under a shared causal attention context is proposed.
Luo-Yuan Zhang, Bo-Kai Xu, Jun-Bo Cui et al.· arXiv.org· 1 citation
SimpleMemVLA, a VLA without a dedicated memory module that uses the backbone's native video context directly as memory, achieves state-of-the-art results on four memory benchmarks without loss on general-purpose control, and with the same backbone and training setup it outperforms retrieval, compression and recurrent-s...
C. Yin, Wang Xu, Jun-Peng Yang et al.· 2 citations
DAFS (Dynamic Attention-based Budget-aware Frame Selection), a training-free frame selector that improves over uniform sampling by up to 6.4 points on Video-MME and outperforms prior training-based selectors under matched frame budgets, while generalizing across selector and answerer backbones, and across tasks, withou...
Yilin Wang, Xiangxi Zheng, Dongxing Mao et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
