Author

Jiajun Bu

h-index 9 View on Semantic Scholar

We have 2 of 56 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

CoANeRV: Coordinate-Aware Token-Space Neural Video Representation

Experiments on diverse video datasets show that CoANeRV consistently improves reconstruction quality over prior feed-forward NeRV and INR baselines, reduces peak memory compared with attention-based coordinate decoders, and provides efficient amortized encoding without per-video optimization.

Jialong Guo, Ke Liu, Meng-Xuan Li et al. · 0 citations

Jul 2026

CAER: Conflict-Aware Evidence Routing with Dual Prefix Experts for Multimodal Large Language Models

CAER introduces a span-grounded evidence router that transforms claim representations into soft textual queries and retrieves corresponding evidence from frozen visual tokens, enabling fine-grained conflict estimation and design a dual-prefix expert routing mechanism that learns separate experts for visually supported...

Zi-Xuan Liu, Juntao Cai, Xiaoxu Cai et al. · arXiv.org · 0 citations