FILT3R, a training-free latent filtering layer that casts recurrent state updates as stochastic state estimation in token space, is proposed, and it is demonstrated that gains shrink in stable regimes as uncertainty contracts with accumulated evidence, and rise when genuine scene change increases process uncertainty.
Seonghyun Jin, Jong Chul Ye· arXiv.org· 3 citations
This work proposes AtomicVLA, a unified planning-and-execution framework that jointly generates task-level plans, atomic skill abstractions, and fine-grained actions, and introduces a flexible routing encoder that automatically assigns dedicated atomic experts to new skills, enabling continual learning.
Likui Zhang, Tao Tang, Zhihao Zhan et al.· arXiv.org· 19 citations· ⚡3
This work proposes US-JEPA, a self-supervised framework that adopts the Static-teacher Asymmetric Latent Training (SALT) objective and demonstrates that masked latent prediction provides a stable and efficient path toward robust ultrasound representations.
Ashwath Radhachandran, Vedrana Ivezi'c, S. Athreya et al.· 0 citations
TimeBlind is presented, a diagnostic benchmark for compositional spatio-temporal understanding that demonstrates that even frontier models rely heavily on static visual shortcuts rather than genuine temporal logic, positioning TimeBlind as a vital diagnostic tool for next-generation video understanding.
Baiqi Li, Kangyi Zhao, Ce Zhang et al.· arXiv.org· 11 citations· ⚡4
This work designs and studies a simple yet natural operator named 1S-DAug, which comprises geometric perturbations with controlled noise injection and image-conditioned denoising, and obtains positive results on well-established image-classification benchmarks across four datasets and multiple models.
Yun-Wei Bai, Yao Shu, Ying Kiat Tan et al.· 0 citations
A central problem in self-supervised learning is preventing representation collapse. Most methods avoid it through global mechanisms, such as contrastive expansion, variance constraints, decorrelating dimensions, or enforcing certain output distributions. In this work, we study a different design: short-range repulsion...
Esteban Rodr\'iguez-Betancourt, Edgar Casasola-Murillo· 0 citations
TangramPuzzle is introduced, a benchmark comprising 668 validated configurations and 1,336 instances for evaluating compositional spatial reasoning under geometric constraints, and the Tangram Construction Expression is formulated to encode tangram configurations with machine-verifiable geometric specifications.
Daixian Liu, Jiayi Kuang, Ying-Hui Li et al.· arXiv.org· 4 citations
This work introduces an Entity-Attention Kullback-Leibler (KL) regularizer that aligns the detector's cross-attention with scientific entities annotated for each panel, providing a stable conditioning signal that also improves localization and applies Group Relative Policy Optimization (GRPO) with a panel-level Entity-...
Ji-Feng Song, Arun Das, Pan Wang et al.· arXiv.org· 0 citations
This work highlights MedGround as a scalable, data-driven approach to anchor medical language to verifiable visual evidence and presents MedGround-35K, a novel multimodal medical dataset.
Meng-Meng Zhang, Xiao-Ping Wu, Hao Luo et al.· arXiv.org· 5 citations
This study shows that combining DL with LLMs can produce useful clinical narratives, but current LLMs remain unreliable for high-stakes medical decisions and provides a clearer view of their limits and a path for building safer reasoning systems.
Md Najib Hasan, I. Ahmad, Sourav Basak Shuvo et al.· 0 citations
MedSegLatDiff is proposed, a diffusion based framework that combines a variational autoencoder (VAE) with a latent diffusion model for efficient medical image segmentation that provides enhanced interpretability and reliability compared to deterministic baselines, making the model particularly suitable for clinical dep...
Ngoc Huynh Trinh, H. Nguyen, S. B. Lương et al.· arXiv.org· 0 citations
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.
