Gradient-aware allocation and sliding windows for low-bit GDN states
On Qwen3.5-4B and 9B, GGA plus PW-S8 beats STEPQuant@4 by 38.39 and 41.21 points on seven-task averages.
Stories per day · 30 days
Relatedanomaly-detection1linear-attention1long-context1quantization1qwen1source-manipulation1telemetry1tranad1
2 stories, newest first · one card per story
Stories tagged #gdn
Score ranks stealthy source manipulation of anomaly detectors
On a 17-channel telemetry benchmark, a detector blind to 64.7% of audited task and subset pairs still caught 82.8% of random single-channel corruption.