51 citations · 75 across the 13 of their papers we have counts for
7 papers · 1 filter
VANDAM: Viewing a nucleotide sequence with DNA molecular priors
Jeremy Levy, Ariel Larey, Yury Nahshan +18
Contemporary Genomic Foundation Models (GFMs) rely on a DNA-as-a-string paradigm that employs masked token prediction objectives for pretraining. However, this abstraction does not…
WinoTS: Wavelet-based Self-Distillation for Time Series Models
Noam Major, Kathy Razmadze, Yoli Shavit
Self-supervised pre-training of time series models is currently dominated by next-token prediction and reconstruction objectives. In continuous-valued domains, these paradigms ofte…
Cross-Entropy Guided Routing in Mixture-of-Experts Large Language Models
Yury Nahshan, Nati Daniel, Jacob Goldberger +1
Sparse mixture-of-experts (MoE) large language models scale model capacity by routing each token to a small subset of experts. Their routers are regularized with load balancing ter…
When Does Self-Supervised Learning Transfer to Time-Series Tasks?
Noam Major, Kathy Razmadze, Yoli Shavit
Self-supervised learning (SSL) assumes that solving pretext tasks on unlabeled data yields representations that transfer effectively across downstream applications via linear probi…
KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision
Maya Yanko, Yoli Shavit
Visual Place Recognition (VPR) is critical for autonomous navigation, yet state-of-the-art methods lack well-calibrated uncertainty estimation. Standard pipelines cannot reliably s…
JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures
Ariel Larey, Elay Dahan, Amit Bleiweiss +15
Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the "Laws of Nature". While effective at capturing local s…
LaVPR: Benchmarking Language and Vision for Place Recognition
Ofer Idan, Dan Badur, Yosi Keller +1
Visual Place Recognition (VPR) often fails under extreme environmental changes and perceptual aliasing. Beyond these limitations, standard systems cannot perform 'blind' localizati…