NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
172 results for “keyword:"sparse autoencoders"” in ICLR 2027. 33 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders▲5.4k3.00
[PDF]Multi-Dimensional Featurizers Yield Fine-Grained Steering and Data Shaping in Robot Foundation Models▼5.1k2.60
[PDF]Sparse Autoencoders vs. Transcoders: Encoder Direction Use and Single-Feature Discrimination▼1361.33
[PDF]Teach the Way It Thinks: Guiding LLM Post-training Data Engineering with Sparse Autoencoders▼5.8k2.33
[PDF]NAMED FROM THE START: CONCEPT-ANCHORED SPARSE AUTOENCODERS FOR INTERPRETABILITY OF VISION-LANGUAGE MODELS▲11k2.00
[PDF]Neural Selectivity as a Compatibility Problem: From Latent Coordinates to Explicit Features▲3972.67
[PDF]Beyond Retraining Stability: Auditing Duplication Dependence in Vision Sparse Autoencoders▼12k1.67
[PDF]SharedSAE: A Unified Sparse Dictionary across U-Net Blocks and Denoising Time for Diffusion Models▼4.3k2.00
[PDF]Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability▼4.3k2.00
[PDF]Dictionary Size and Dead Latents Handling Jointly Set the Recovery-Optimal Sparsity of Top-K Sparse Autoencoders▼1361.33
[PDF]Frozen Input-Harm Probes under Compression: Retained AUROC Does Not Mean Retained Refusal▼1.2k1.67
[PDF]Mechanistic Interpretability Findings That Generalize: Chaperone-Dependent Folding in ESMFold2▼4.3k2.00
[PDF]Before the Refusal: Pre-Response Activation Signatures of False Refusal in Safety-Aligned Language Models▼1.2k1.67
[PDF]What Remains After Concept Erasure? Sparse Autoencoder Probes for Auditing Diffusion Model▼4.3k2.00
[PDF]From Tokens to Policy: Causal and Interpretable Heterogeneous Treatment Effects Identification▲43.67
[PDF]Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features▲5103.00
[PDF]Where Features Are Written and Read: Localizing Native Transformer Channels for Residual Directions▼4.3k2.00
[PDF]Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models▲3.0k2.33
[PDF]FoGConcept: Identifying Interpretable Movement Concepts for Freezing-of-Gait Detection from Multi-Scale IMU Signals▲3.0k2.33
[PDF]TRACE: Transparent Reasoning through Aligned Concept Explanations in Clinical Reinforcement Learning▼1.2k1.67
[PDF]SAE-Locked LoRA: Edit-Specific Sparse-Feature Gradient Routing for Low-Interference Knowledge Editing▼4.5k2.67
Withdrawn or desk rejected (33)
[PDF]SN-ABSTOPK: AN UNROLLED SPATIAL-NORMATIVE SPARSE AUTOENCODER FOR MEDICAL FOUNDATION MODELSWithdrawn1.00