CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse Paper • 2611.09891 • Published 7 days ago • 11 • 5
LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time Paper • 2611.07025 • Published 8 days ago • 36 • 4
Think Less, Locally: Local Preference Learning for Reasoning Compression Paper • 2611.04814 • Published 10 days ago • 66 • 14
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation Paper • 2611.06498 • Published 8 days ago • 5 • 10
AutoCompress: Automated Hardware-Guided Model Compression Paper • 2611.08290 • Published 7 days ago • 13 • 3
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation Paper • 2611.06498 • Published 8 days ago • 5 • 10
Think Less, Locally: Local Preference Learning for Reasoning Compression Paper • 2611.04814 • Published 10 days ago • 66 • 14
Think Less, Locally: Local Preference Learning for Reasoning Compression Paper • 2611.04814 • Published 10 days ago • 66 • 14
Follow the Gradient: Tracing Safety Degradation Back to Training Data Paper • 2610.37481 • Published 17 days ago • 32 • 3