Brain-SAD is proposed, a brain-inspired safe autonomous driving control framework with dynamic fear-oriented constraints that outperforms existing methods, achieving higher success rate in shorter task-completion and collision-recovery time, and exhibits stronger reliability across continuous intersections of fluctuati...
Huan Rong, Chao Yin, Anouar Imel et al.· 0 citations
Video-RSI is introduced, a framework for recursive self-improvement in which a video understanding agent uses its own language model to revise its harness, and the evolved agent improves accuracy while processing fewer frames and achieves competitive accuracy-efficiency trade-offs against existing video understanding a...
Per-action evaluation and failure analysis highlight ambiguities from camera motion, delayed effects and imbalanced key-press frequencies that call for explicit modeling of 3D scene structure, long-term state and the adoption of proper losses in future implementations.
Abhishek Pillai, Ekta Prashnani, Joohwan Kim et al.· 0 citations
This work introduces MeanFlowAdvantage, a signed advantage-weighted least-squares objective for average-velocity generators, and uses a shared, detached MeanFlow derivative correction to express the reward objective in prediction space while making rollout and reference regularization exact penalties on the average-vel...
Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each network has its own weights, trains independently on the same heterogeneous data, and can ask another agent for help through a forward pass. Unlike mixtures of experts,...
Aram Davtyan, Pablo Acuaviva, Sebastian Stapf et al.· 0 citations
Dual active galactic nuclei (DAGN) mark a critical phase in the evolution of merging galaxies and the pairing of supermassive black holes, yet they remain difficult to identify in large imaging surveys because of projection effects and limited spatial resolution. Compact foreground stars and unresolved substructure can...
Bhavesh Mukheja, S. Saha, Anwesh Bhattacharya et al.· 0 citations
Current multi-view gaze estimation remains limited by existing datasets, insufficient exploitation of complementary cross-view information, and evaluation focused primarily on average gaze error. We address these limitations through a more systematic study of multi-view gaze estimation. First, we introduce PrismGaze, a...
Chang Liu, Jia-Qi Liu, Cheng-Wen Zhang et al.· 1 citation
The proposed system establishes a new operating point in the accuracy-latency-compute trade-off for latency- and resource-constrained gaze tracking, and highlights the potential of task-driven optical sensing for ultra-low-latency, computationally efficient human-computer interaction systems.
Yidan Zheng, Matheus Souza, Kaizhang Kang et al.· arXiv.org· 0 citations
MILE, a teleoperation-based data-collection system comprising the wearable MILE exoskeleton and the mechanically corresponding MILE-Tac robotic hand, and trained paired ACT and DP policies with and without tactile input on MILE-collected demonstrations for downstream imitation learning.
Jinda Du, Jie-Ji Ren, Qiao-Jun Yu et al.· 6 citations
HAGI++ is presented, a multi-modal diffusion-based imputation method that, for the first time, leverages integrated head-orientation sensors to exploit the natural correlation between head and eye movements and enables more complete, accurate eye-gaze recordings in real-world contexts, enhancing gaze-based analysis and...
Chu-Han Jiao, Zhi-Ming Hu, Andreas Bulling· IEEE Transactions on Visuali...· 1 citation
The channel-gated model is the most accurate of the authors' learned fusion arms on clean data and its gates suppress the natively biased foot-orientation channels on clean real data without test-time supervision and flag dropout bursts at 0.92-0.999 AUROC.
Zhi-Lin Guo, Bo-Qiao Zhang, O. Urbán et al.· 0 citations
A multimodal capture pipeline is built that records four-view RGB-D video together with an AirPods head IMU and two Striv insole IMUs, synchronize the streams post-hoc, and generate pseudo-ground-truth with SAM 3D Body, yielding a 35-take single-subject benchmark spanning gait, turning, vertical, everyday, and clinical...
Zhi-Lin Guo, Bo-Qiao Zhang, O. Urbán et al.· 1 citation
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
