Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain. We propose a structured vis...
Yu-Song Zhao, Edgar Y. Walker, Hao Wang et al.· 0 citations
This work proposes SAUCE (Sequential Agent Uncertainty through Consensus Evolution), a lightweight, training-free uncertainty estimator that formulates MAS uncertainty as sequential inference over a latent system-level belief.
Tun-Yu Zhang, Zi-Hao Zhao, Yu-Song Zhao et al.· 0 citations
Under a matched budget, ResemBrick surpasses existing voxel selectors in perceptual fidelity while uniquely reaching zero floating and zero unstable bricks on unfiltered held-out objects; as a complete pipeline, it attains the best perceptual fidelity among prior brick-construction systems.
Xilun Chen, Hanwen Wan, Yu-Song Zhao et al.· 1 citation
This work reports interpretability experiments for a tokenized autoregressive Transformer agent in the Game of Hidden Rules (GOHR), a compact two-rule task in which both hidden rules map object shapes to target buckets, but with different permutations.