2 papers
cs.LG2026
When Attribution Patching Lies: Diagnosis and a Second-Order Correction
Luyang Zhang, Jialu Wang
A central goal of mechanistic interpretability is to identify which internal components causally drive a language model's behavior. Because these importance estimates serve as the…
cs.CV2026
PinpointQA: A Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos
Zhiyu Zhou, Peilin Liu, Ruoxuan Zhang +4
Reliable embodied interaction in indoor environments requires agents to precisely localize small everyday objects from visual observations. Yet this fundamental capability remains…