🧠 Large Language Models (LLMs) - pleto · Scour

Beyond Compaction: Structured Context Eviction for Long-Horizon Agents

🤖Agents using LLMs Academic

Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

✨Model optimizations in LLMs Academic

arxiv.org··Hacker News

ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL

🔍Retrieval-augmented generation Academic

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

⚡Real-time AI Systems Academic

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

🔧Systems-level optimizations for LLM serving Academic

TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management

🔧Systems-level optimizations for LLM serving Academic

Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning

🔧Systems-level optimizations for LLM serving Academic

The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model

🔍Retrieval-augmented generation Academic

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

🔍Retrieval-augmented generation Academic

SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices

🔢Quantization of LLMs Academic

Automated IEP Generation from Traditional Chinese Parent-Teacher Interviews via Corpus-Grounded Feature Diffusion

✨Model optimizations in LLMs Academic

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

🤖Agents using LLMs Academic

Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

📊AI Performance Profiling Academic

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

🔍Retrieval-augmented generation Academic

Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison

🔍Retrieval-augmented generation Academic

SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation

⚡Real-time AI Systems Academic

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

🔧Systems-level optimizations for LLM serving Academic

PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training

✨Model optimizations in LLMs Academic

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

🔍Retrieval-augmented generation Academic

A Regret Minimization Framework on Preference Learning in Large Language Models

✨Model optimizations in LLMs Academic

Log in to enable infinite scrolling