Cover Image

Features Emerge as Discrete States: The First Application of SAEs to 3D Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Miao, Albert, Zhou, Chenliang, Zhou, Jiawei, Oztireli, Cengiz
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
by: Zhou, Chenliang, et al.
Published: (2022)

RETRO: REthinking Tactile Representation Learning with Material PriOrs
by: Xia, Weihao, et al.
Published: (2025)

FreNBRDF: A Frequency-Rectified Neural Material Representation
by: Zhou, Chenliang, et al.
Published: (2025)

Distribution-Aware Feature Selection for SAEs
by: Oozeer, Narmeen, et al.
Published: (2025)

Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity
by: Hu, Zheyuan, et al.
Published: (2026)

Physically Based Neural Bidirectional Reflectance Distribution Function
by: Zhou, Chenliang, et al.
Published: (2024)

Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance
by: Zhou, Chenliang, et al.
Published: (2026)

SAEs Are Good for Steering -- If You Select the Right Features
by: Arad, Dana, et al.
Published: (2025)

Tokenized SAEs: Disentangling SAE Reconstructions
by: Dooms, Thomas, et al.
Published: (2025)

The Rate-Distortion-Polysemanticity Tradeoff in SAEs
by: Mencattini, Tommaso, et al.
Published: (2026)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
by: Song, Xiangchen, et al.
Published: (2025)

XQSV: A Structurally Variable Network to Imitate Human Play in Xiangqi
by: Zhou, Chenliang
Published: (2024)

Hypernetworks for Generalizable BRDF Representation
by: Gokbudak, Fazilet, et al.
Published: (2023)

Analyzing (In)Abilities of SAEs via Formal Languages
by: Menon, Abhinav, et al.
Published: (2024)

An Information Theoretic Approach to Machine Unlearning
by: Foster, Jack, et al.
Published: (2024)

Residual Stream Analysis with Multi-Layer SAEs
by: Lawson, Tim, et al.
Published: (2024)

Exploring The Visual Feature Space for Multimodal Neural Decoding
by: Xia, Weihao, et al.
Published: (2025)

A Novel Hybrid Approach for Tornado Prediction in the United States: Kalman-Convolutional BiLSTM with Multi-Head Attention
by: Zhou, Jiawei
Published: (2024)

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
by: Korznikov, Anton, et al.
Published: (2026)

Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design
by: Brzozowski, Michał, et al.
Published: (2026)

Resa: Transparent Reasoning Models via SAEs
by: Wang, Shangshang, et al.
Published: (2025)

DREAM: Visual Decoding from Reversing Human Visual System
by: Xia, Weihao, et al.
Published: (2023)

Blue noise for diffusion models
by: Huang, Xingchang, et al.
Published: (2024)

Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
by: Ahsan, Hiba, et al.
Published: (2025)

Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs
by: Lee, Daniel J., et al.
Published: (2024)

Teach Old SAEs New Domain Tricks with Boosting
by: Koriagin, Nikita, et al.
Published: (2025)

M^3ashy: Multi-Modal Material Synthesis via Hyperdiffusion
by: Zhou, Chenliang, et al.
Published: (2024)

CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts
by: Su, Chong, et al.
Published: (2025)

DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning
by: Chen, Xi, et al.
Published: (2024)

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
by: Ayonrinde, Kola, et al.
Published: (2024)

The Optimization Landscape of SGD Across the Feature Learning Strength
by: Atanasov, Alexander, et al.
Published: (2024)

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
by: Simbeck, Katharina, et al.
Published: (2025)

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles
by: Ruben, Benjamin S., et al.
Published: (2023)

Transfer Learning in Infinite Width Feature Learning Networks
by: Lauditi, Clarissa, et al.
Published: (2025)

OSCaR: Object State Captioning and State Change Representation
by: Nguyen, Nguyen, et al.
Published: (2024)

How Feature Learning Can Improve Neural Scaling Laws
by: Bordelon, Blake, et al.
Published: (2024)

Preconditioned Discrete-HAMS: A Second-order Irreversible Discrete Sampler
by: Zhou, Yuze, et al.
Published: (2025)

Beyond State Space Representation: A General Theory for Kernel Packets
by: Ding, Liang, et al.
Published: (2024)

Multigranular Evaluation for Brain Visual Decoding
by: Xia, Weihao, et al.
Published: (2025)

Speech Watermarking with Discrete Intermediate Representations
by: Ji, Shengpeng, et al.
Published: (2024)