Show HN: Fly Language Model
A developer released FLM (Fly Language Model), a language model trained from scratch on a connectome-derived recurrent network built from a modeled subset of fruit-fly brain wiring, with no pretrained…
A developer released FLM (Fly Language Model), a language model trained from scratch on a connectome-derived recurrent network built from a modeled subset of fruit-fly brain wiring, with no pretrained…
Researchers developed a feed-forward attention mechanism integrated with a Long Short-Term Memory network (FAM-LSTM) for multi-step grape berry temperature forecasting, achieving mean absolute errors …
ESET has discovered a Russian state-sponsored hacking group, UAC-0099, embedding a manipulative prompt about nuclear weapons in a malicious VBS script to deliberately trigger AI safety mechanisms and …
Researchers introduced a data-poisoning attack called cross-parameter relinking that creates wrong-physics backdoors in neural PDE operators, making triggered inputs output physically plausible but in…
A new study from arXiv (2608.20343v1) presents a bankruptcy prediction framework using hybrid resampling and stacking ensembles with explainable AI, achieving the best minority-class detection with a …
A new mobile sign language recognition system combines MediaPipe's 21 hand and 468 face landmarks with a GRU/LSTM sequence classifier, achieving real-time 30fps performance on devices via ONNX or Tens…
The Transformer architecture, introduced in the 2017 paper 'Attention Is All You Need,' was designed primarily to reduce training time by enabling parallelization, not to improve translation quality. …
A new arXiv paper (2608.10441v1) introduces Structured Hypothesis Embeddings (SHE), a method where a frozen LLM converts user history into ranked, confidence-scored intent hypotheses for recommender s…
A study by researchers evaluating GRU, LSTM, and Transformer encoder models for classifying Level 2 automated driving systems (Comma Openpilot, Tesla Autopilot, Cadillac Super Cruise) from vehicle tel…
A study using 134,376 hourly weather observations from Ioannina, Greece (2011-2026) found that hybrid CNN-GRU models outperform traditional recurrent networks in weather forecasting, achieving a Weigh…
Researchers applied a Spectral Temporal Graph Neural Network (StemGNN) to predict user equipment scheduling states in 5G networks, recovering 57-73% of sum rate loss caused by backhaul latency. The mo…
Researchers introduced the Integral Transform Network (ITNet), a unified architecture that subsumes convolution, attention, and recurrence as special cases of a learnable integral transform. ITNet mat…
Researchers introduced a hierarchical model for ball action anticipation in football broadcast video, achieving 17.91% mAP on the SoccerNet benchmark. The system uses a GRU and Transformer decoder wit…
AI-driven approach to improve failure detection and diagnosis in Apache Airflow, a tool for orchestrating ETL pipelines. The method combines large language models (LLMs) for classifying log messages, …
Russian state-backed hackers linked to the GRU's military intelligence unit, known as Forest Blizzard or APT28, exploited known vulnerabilities in outdated Internet routers to conduct a large-scale DN…