Tech Times

Baidu OCR Breaks Long-Document Memory Wall: New Architecture Beats DeepSeek

Open-source OCR from Baidu eliminates the GPU memory wall that limits long-document parsing. Unlimited OCR uses a constant KV ...
IEEE

Interpretable Merging-Vehicle Acceleration Prediction via a Decoder-Only Transformer and Attention Map Clustering

Abstract: This paper proposes a decoder-only Transformer model for analyzing and clustering vehicle-to-vehicle interactions in highway merge zones. Leveraging deep learning, the model captures complex ...
GitHub

2026-06-16-decode-only-transformer.md

For agentic workers: REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (- [ ]) syntax ...
IEEE

Multi-Appliance Adaptive Non-Intrusive Load Monitoring System with Encoder-Decoder Architecture and Self-Adaptive Loss Weighting

Abstract: Non-Intrusive Load Monitoring (NILM) refers to as the technology of identifying the operation status and power consumption of individual electrical devices (typically household appliances) ...
digitalengineering247

NVIDIA Debuts Cosmos 3 Foundation Model for Physical AI

NVIDIA has launched NVIDIA Cosmos 3, an open world foundation model for physical AI built on a mixture-of-transformers architecture that combines vision reasoning, world generation, and action ...
GitHub

GitHub - OssiLehtinen/channel-encoder-audit: Empirical audit of input encoders for multi-channel signal transformers — nn.Linear (C, d_model) matches every alternative. · GitHub

Six of the eight are encoder swaps that share the I/O signature $\mathbb {R}^ {B\times T\times C} \to \mathbb {R}^ {B\times T\times d_ {\text {model}}}$ and feed into the same causal transformer ...