Skip to main content
Search

National Tsing Hua University

4 related articles

Subscribe to updates
  1. One pretrained backbone for collider events: 500 million simulated collisions, 7.6σ on CMS open data

    Collider analyses have trained a separate model per task; EVENET instead represents each collision as an unordered particle cloud and pretrains one backbone on 500 million simulated events with self-supervised plus physics-informed objectives, then adapts it through interchangeable task heads. In an anti-isolated ϒ→μ+μ− search on CMS Open Data, the fully pretrained variant reaches a median local significance of 7.6σ after calibration, above the published 6.4σ, and across a heavy-resonance mass grid its maximum SIC averages about 50% above training from scratch.

  2. arXiv

    TT-VidT splits appearance and motion into two pathways: among 24 architecture-objective pairings, only TT3D with Diff Compression leads Jester, SSv2, ARID and Diving48 at once

    The work proposes TT-VidT, which pairs a DINOv3-initialized ViT-B/16 per-frame spatial path with a compact Temporal Transfer Layer and trains it by Diff Compression to reconstruct target frames from a first-frame appearance anchor and frame-specific motion tokens; under a matched recipe at roughly 170M-190M encoder scale on 1.7M OpenVid and Moments-in-Time v2 clips for 8 epochs, a 24-cell architecture-objective sweep shows that only TT3D with Diff Compression enters the strongest motion-sensitive regime, and in the final comparison it leads Jester, Something-Something V2, ARID and Diving48 fine-tuning simultaneously while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA 2.

  3. Microwell platform for single-cell applications and future integration with artificial intelligence (AI)

    This review examines how microwell platforms determine the information obtainable from individual cells through cell-loading strategies, well geometry, platform architecture and material selection, reviews their applications in cellular behaviour and cell-cell interactions, secretome analysis, genomic and transcriptomic profiling, and drug screening and precision medicine, and distinguishes AI approaches directly demonstrated in microwell-based studies from those still prospective, indicating that linking microwell engineering with AI-driven analysis can move microwell-based single-cell research from measurement towards prediction and autonomous discovery.

  4. What Single-Topic Summaries Miss in Hospital Reviews: Aspect-Level Evaluative Structure Using Generative Pretrained Transformer-Based Sentiment Analysis

    Using 5,467 Google Reviews posted in 2024 from all 24 medical centers in Taiwan, this study compared the common LDA dominant-topic assignment with GPT-based aspect-based sentiment analysis (ABSA) on the same corpus, finding that aspect-bearing reviews discussed an average of 2.05 distinct service aspects, that dominant-topic assignment yielded an illustrative 51.2% representational compression, that a soft-assignment LDA baseline reduced count-level compression to 1.7% but left semantic alignment limited (mean set Jaccard=0.33) and carried no aspect-level sentiment polarity, that 11.0% of multiaspect reviews showed cross-aspect mixed sentiment with Technical-Functional Divergence accounting for 61.

You’re all caught up