Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 10946-10956· 0 citations· 6 references
Abstract
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 information redundancy, motivating a paradigm shift from lossy compression to selective exploration. Building on this insight, we propose 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. Agents learn query strategies via physics-guided reinforcement learning, overcoming early-stage sparsity without expert-annotated trajectories. On PhysQA-Bench, AQUA achieves 72% accuracy on average, outperforming baselines by 15% across all four datasets. Our code is available at https://github.com/gaoch6258/AQUA.git.
Recent vision-and-language navigation (VLN) systems increasingly adopt streaming Video-LLM policies that map egocentric RGB observations and instructions directly to low-level actions. Yet these policies inherit weak 3D geometric priors from 2D pretraining. Existing geometry-aware extensions charge a persistent inferen...
Yi-Xuan Jiang, Wen-Tong Li, An Liu et al.· 0 citations
TTL-SR is proposed, a geometry-aware Test-Time Learning framework for quantitative Spatial Reasoning that leverages geometric consistency constraints and unlabeled test data to adapt models to target domains to boost spatial reasoning performance.
Ge-Ge Zhang, Shuai-Cheng Niu, Gang Dai et al.· 0 citations
Interactive world models must respond quickly to controls while preserving scene consistency. Existing acceleration methods can miss heterogeneous control responses and spatial transport when recovering skipped features. We observe that interaction-induced feature changes correlate with approximation error, while low-f...
Le-Yang Chen, Jun-Yi Wu, Fan-Qing Kong et al.· 0 citations
NavGen is introduced, a text-to-video data generation pipeline that produces diverse vision-language navigation episodes across indoor and outdoor scenes and a style-diversification method that scales up long-tail data that is difficult and costly to collect.
Xi-Jie Huang, Yong-Yang Wan, Cheng-Bin Dong et al.· 1 citation
This work systematically sparsify SparseTalk's semantic embeddings, including the previously underexplored regime below a single image-equivalent block down to 8 visual tokens, and introduces an object-based sparsification method that distributes the token budget across detected object instances while retaining backgro...
Davit Soselia, J. Jaja, Amitabh Varshney· 0 citations
GaussianWAM is proposed, a training-time representation-enhancement framework that organizes geometric and semantic supervision through a 3D Gaussian field and improves performance on standard LIBERO and shows positive transfer trends on RoboTwin and real-world manipulation.
Zi-Jian Zhang, Yu-Qing Jiang, Wei-Tao Zhou et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
