This work proposes AQUA, which trains agents to actively query information-rich regions through Gaussian Splatting environments, transforming global lossy compression into local lossless localization with targeted spatial queries.
Chonghan Gao, Haoyi Zhou, Zhemeng Luo et al.· Proceedings of the 32nd ACM...· 0 citations
LatentFlow is proposed, a novel framework that treats channel dependency evolution as a latent continuous dynamic process using an Ornstein-Uhlenbeck (O-U) process, allowing the model to capture smooth dependency shifts while maintaining robustness against structural noise.
Lijun Sun, Shuai Zhang, Xin Xue et al.· Proceedings of the 32nd ACM...· 0 citations
StructInf, a structure-aware influence estimation framework that addresses the Fidelity Gap from coarse curvature approximations and the I/O bottleneck from materializing per-example gradients, is proposed, suggesting that practical IF for LoRA-tuned LLMs benefits from joint optimization of curvature modeling, memory m...
Mengyi Yan, Yaoshu Wang, Guangyi Zhang et al.· Proceedings of the 32nd ACM...· 0 citations
Recent advances enable LLMs to generate simulation code from natural language, yet interpreting 3D physical field outputs remains unsolved. Existing 3D scene compression methods fail on physical fields due to absent semantic grounding and information loss. We discover that typical physical fields exhibit extreme inform...
Chonghan Gao, Haoyi Zhou, Zhemeng Luo et al.· Proceedings of the 32nd ACM...· 0 citations
Influence functions provide a principled framework for tracing model predictions back to training data, yet existing methods remain impractical for large language models due to prohibitive storage and I/O costs. Prior approaches face two critical barriers: the Fidelity Gap from coarse curvature approximations, and the...
Mengyi Yan, Yaoshu Wang, Guangyi Zhang et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
