🖼️ Dual Coding - minezone · Scour

MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification 🧱Chunking

Hippocampal criticality tracks cognitive demand and shifts with memory impairment 🧠Neuroplasticity

A Parametric Memory Head for Continual Generative Retrieval 🧱Chunking

AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving 📱Edge AI

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers 🧱Chunking

Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model 🧱Chunking

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems 🧱Chunking

BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning 🗂️Vector Databases

ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents 🔧DSPy

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding 📉Model Quantization

SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments 🧱Chunking

StructMem: Structured Memory for Long-Horizon Behavior in LLMs 🧩LLM Integration

ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing 🖼️Lazy Loading

Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning 🧱Chunking

arxiv.org·3d·Hacker News

From graphemic dependence to lexical structure: a Markovian perspective on Dante's Commedia 📝NLP

Insect-inspired modular architectures as inductive biases for reinforcement learning 📱Edge AI

Spatial Metaphors for LLM Memory: A Critical Analysis of the MemPalace Architecture 🧩LLM Integration

EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval 🔍RAG

Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents 🔄Autonomous Agents

SCM: Sleep-Consolidated Memory with Algorithmic Forgetting for Large Language Models 🧱Chunking

Log in to enable infinite scrolling