Entity · benchmark

L-Eval

benchmarkactiveprovisionall-eval-49b45833·1 events·first seen 45h ago

Aliases: L-Eval

Co-occurring entities

DepthWeave-KV Needle-in-a-Haystack LongBench v2

More like this (12)

G-Eval T-Eval ParaEval ValueEval STAGE-Eval IFEval Verilog-Eval CharacterEval olmo-eval Every Eval Ever Claw-Eval SummEval

Recent events (1)

5arXiv · cs.AI·45h ago·source ↗

DepthWeave-KV: Token-adaptive cross-layer KV cache compression for long-context inference

A new arXiv preprint introduces DepthWeave-KV, a KV cache compression method that factorizes key-value states across neighboring transformer layers using shared low-rank channel bases while retaining token-specific residuals for attention-sensitive positions. A token-conditional depth router allocates higher reconstruction rank to instruction-bearing and retrieval-critical tokens, with calibration-free online error tracking during generation. The method achieves 8.3x KV memory reduction at 64K context while maintaining near-full-cache quality on LongBench, Needle-in-a-Haystack, and L-Eval benchmarks. The work addresses a practical bottleneck in long-context inference without requiring base model retraining.

Long Context Evolution Inference Economics DepthWeave-KV L-Eval Needle-in-a-Haystack +1 more