📶 LoRa - Velocifyer · Scour

gerritsxd/chatforge: Drag two conversations together. Local LLM chat with merge, persistent memory, and LoRA compilation. 🐘Mastodon

github.com·5d·Hacker News

$\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding ⚡Parallel Computing

LightInk – An ESP32-based, solar-powered E-ink smartwatch with up to 10 months of battery life 📄E-ink Displays

cnx-software.com·4d·Hacker News

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation ⚙️Compression Benchmarking

ShadowLLM/shadow-peft: ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning 👻Spectre

github.com·5d·Hacker News

Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation 🌈HDR

CRC-SAM: SAM-Based Multi-Modal Segmentation and Quantification of Colorectal Cancer in CT, Colonoscopy, and Histology Images 🌈HDR

Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression ⚙️Compression Benchmarking

Generalized Two-Dimensional Index Modulation in the Code-Spatial Domain for LPWAN 🕸️Network Topology

Where Should LoRA Go? Component-Type Placement in Hybrid Language Models ⚙️Compilers

Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies 🔒Digital Privacy

Low-Rank Adaptation Redux for Large Models 🗜️Zstd

GiVA: Gradient-Informed Bases for Vector-Based Adaptation 🗜️Zstd

Log in to enable infinite scrolling