Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Dynamic Scaling Fails: A Scale-State Feedback Governs Recurrent-State Quantization in Linear-Attention and SSM LLMs
Yuhang Jiang
Linear-attention and state-space LLMs carry long context in a fixed-size recurrent state, and quantizing that state is the natural way to cut its cost during long decode. Unlike a…
cs.LG2026
Refit the Probe: Single-Direction Ablation Is Not a Necessity Test
Yuhang Jiang
Probes are routinely paired with an intervention: ablate the direction the probe found, run the model, and read the change in task accuracy, taking a large drop as evidence that th…