activity
20232026
most citedFlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.SEShow all

1 paper · 1 filter

cs.SE2026

Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research

Lezhi Yu, Xiaogang Xu, Yuhua Zhou +2

LLM agents used for scientific experimentation must do more than generate executable code: they must implement the reference method faithfully, design experiments that test the pap…