FF-TRUST is proposed, a domain-invariant multimodal sleep staging framework with Joint Time-Frequency Early Learning Regularization (JTF-ELR) that improves robustness under noisy supervision by jointly exploiting temporal and spectral consistency together with confidence-diversity regularization.
Kening Wang, Di Wen, Yu-Fan Chen et al.· arXiv.org· 0 citations
Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial distortion warps local image structure, while boundary compression shrinks objects to near-invisible sizes. Full fine-tuning closes mu...
Navigating unfamiliar outdoor environments is one of the most demanding everyday tasks for people with visual impairments (PVI). However, existing navigation systems cannot simultaneously satisfy the needs of informative perception and precise localization during navigation. This paper explores the core navigation dema...
Junwei Zheng, Jia-Le Wei, Di Wen et al.· 0 citations
Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This leaves an important gap between leaderboard performance and realistic long-document retrieval, where the evidence needed to answer a query may span multiple pages or even...
Simon Ott, Yu-Fan Chen, Rui-Ping Liu et al.· 0 citations
Referring scene understanding for embodied robots requires grounding object- and relation-centric language queries from a designated viewpoint. While a local semantic Gaussian map can support such grounding within one agent's observations, cooperative settings require this ability to remain effective after independentl...
Zhi-Kun Zhou, Kun-Yu Peng, Run-Yi Yang et al.· 0 citations
Latent action models infer a code for the transition between two frames of action-free video. Recent methods regularise this code to compose additively and reverse antisymmetrically, and report order-of-magnitude reductions in the resulting errors as a label-free certificate that the code has captured temporal structur...
Di Wen, Ruo-Di Zhang, Kailun Yang et al.· 0 citations
Blind and low-vision users often need to locate a specific personal object rather than an arbitrary instance of the same category. The task calls for a robot that can move through the space and reach viewpoints the user cannot, and for an accessible interface where the user says which object is meant and learns whether...
Rui-Ping Liu, Shaofang Quan, Qian-De Yin et al.· 0 citations
Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Yet existing VFM-based 3D detectors rely on narrow-view monocular images or discrete perspective views, limiting coherent surround perception; equirectangular projection (...
EgoGears, a complementary single- and multi-video benchmark designed to diagnose this transition inodied systems, is introduced and 29 single-video and 31 multi-video MLLM configurations across six model families in the main leaderboard are reported.
Yue-Dong Tan, Lei-Tao Qi, Yu Liu et al.· 0 citations
Recent 4D LiDAR language models aim to reason about objects and their evolving spatial relationships. Yet, in our evaluation, always selecting the same option nearly matches the multiple-choice accuracy of two B4DL-derived configurations. We introduce LiDAR-Hallu, a geometry-referenced benchmark and diagnostic protocol...
Run-Yi Yang, Murat Akkoyun, Di Wen et al.· 0 citations
This work proposes FOCAL-VLA, a framework that combines subtask-guided geometry distillation with implicit world modeling to learn representations of current spatial structure and future interaction dynamics, and shows that FOCAL-VLA outperforms baselines on both simulation benchmarks and real-world manipulation tasks.
Zhi-Yuan Gao, Di Wen, Yan Zhan et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.