5 papers
Gradient Residual Connections
Yangchen Pan, Qizhen Ying, Philip Torr +1
Existing work has linked properties of a function's gradient to the difficulty of function approximation. Motivated by these insights, we study how gradient information can be leve…
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
Neuromorphic Computing with Multi-Frequency Oscillations: A Bio-Inspired Approach to Artificial Intelligence
Boheng Liu, Ziyu Li, Qing Li +1
Despite remarkable capabilities, artificial neural networks exhibit limited flexible, generalizable intelligence. This limitation stems from their fundamental divergence from biolo…
FairBatching: Fairness-Aware Batch Formation for LLM Inference
Hongtao Lyu, Boyue Liu, Mingyu Wu +1
Large language model (LLM) inference systems face a fundamental tension between minimizing Time-to-First-Token (TTFT) latency for new requests and maintaining a high, steady token…
StreakNet-Arch: An Anti-scattering Network-based Architecture for Underwater Carrier LiDAR-Radar Imaging
Xuelong Li, Hongjun An, Haofei Zhao +6
In this paper, we introduce StreakNet-Arch, a real-time, end-to-end binary-classification framework based on our self-developed Underwater Carrier LiDAR-Radar (UCLR) that embeds Se…