127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “context”

14,981 results

Local Ai

Language Models Need Sleep

DGX agent

arXiv:2605.26099v1 Announce Type: cross Abstract: Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context le

local-aiarxiv-cs-ai

26 May 2026

Agents

Latent Cache Flow: Model-to-Model Communication Without Text

DGX agent

arXiv:2605.22863v1 Announce Type: new Abstract: LLM agents today communicate via text, which incurs considerable latency and information loss due to the need to autoregressively decode the sharer mode

Search: “context”

Language Models Need Sleep

Latent Cache Flow: Model-to-Model Communication Without Text

Sparser Block-Sparse Attention via Token Permutation

EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments

Runtime-Certified Bounded-Error Quantized Attention

LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

Mitigating Conversational Inertia in Multi-Turn Agents

State Contamination in Memory-Augmented LLM Agents

GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective

MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models

OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention

Finite Sentence-Interface Control for Learning Bounded-Fan-Out Linear MCFGs under Fixed Monoid Typing

The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested

Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology

CLEF: EEG Foundation Model for Learning Clinical Semantics

Kaczmarz Linear Attention

MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation

Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents

RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation

RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation

S2M-Net: Spectral-Spatial Mixing for Medical Image Segmentation with Morphology-Aware Adaptive Loss

WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems

Deep neural networks with Fisher vector encoding for medical image classification

Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast

HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination

Cross-Course Generalizability of SRL-Aligned Predictive Models Using Digital Learning Traces

MIMIC: A Generative Multimodal Foundation Model for Biomolecules

When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models

Learning Evidence Highlighting for Frozen LLMs

Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts

Intersectional Fairness in Large Language Models

EgoSelf: From Memory to Personalized Egocentric Assistant

Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring

SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion

DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion

FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage

POLAR: Online Learning for LoRA Adapter Caching and Routing in Edge LLM Serving

RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation

Sessa: Selective State Space Attention

Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation

Compressing Sequences in the Latent Embedding Space: K-Token Merging for Large Language Models

SiLVR: A Simple Language-based Video Reasoning Framework