Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention Paper • 2608.23834 • Published 8 days ago
A Practical Tensor-Network Compression Pipeline for Production-Scale Large Language Models Paper • 2602.01613 • Published Feb 2
Social Deduction LLM (AAMAS 2025) Collection Pretrained models for "Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning" (AAMAS 2025 Version) • 3 items • Updated Feb 11, 2025 • 3