Latent Compaction with Test-Time Training
Latent Compaction preserves long-context retrieval at 32x KV-cache compression via test-time training.
Stories per day · 30 days
2 RSS
6 stories, newest first · one card per story
Stories tagged #ruler
Latent Compaction with Test-Time Training
Latent Compaction keeps 96.7% RULER accuracy at 32x KV-cache compression via test-time training.
History Replays Itself: Unleashing Long-Context Capability in Linear Attention
NoteBank lifts pretrained linear-attention models to million-token retrieval by replaying sparse episodic memory.
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Hybrid Linear Attention adds query-dependent chunk routing to Gated DeltaNet, lifting long-context scores on Qwen3.5.
FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
FocusVTC adaptively compresses text as images, beating Glyph on RULER at similar compression.
The Sirens' Song: When Proximal Background Context Overshadows Distant Evidence
LYRA realigns long-context attention so distant task evidence is not drowned out by proximal background.