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
1,261 results for “keyword:"interpretability"” in ICLR 2027. 264 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]De-Absorption Reparameterization: Post-hoc Repair of Feature Absorption in Sparse Autoencoders.▲3.0k2.33
[PDF]Structure Before Flexibility: Mechanistically Testable Functional Conductances for Continuous-Time Network Dynamics▼5.8k2.33
[PDF]Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders▼5.8k2.33
[PDF]Knowing Whom to Trust: Reliability States and Information Use in Large Language Models▼5.8k2.33
[PDF]SEAM: Shared-Expert Adaptation Masked by Closed-Loop Scores in Reward Fine-Tuned Diffusion Planners▲3.0k2.33
[PDF]Analyzing Mask-Breaking Mechanisms: A Methodology for Deep Learning Side-channel Analysis▼1.2k1.67
[PDF]Revealing Pathway Interactions in Network Computations with Complete Path Contribution▼4.5k2.67
[PDF]When Do Cross-Modal Gains Warrant a Semantic Role? A Role-Conditioned Audit of Derived Pairing Rules▼4.3k2.00
[PDF]Iterative distillation of Matryoshka sparse autoencoders improves hierarchical feature organization in ESMFold2▲11.00
[PDF]The Right Source Is Not Enough: Understanding History Interference in Speech-LLM Memory▼1.2k1.67
[PDF]ECHO: Emergent Common-Mode Hidden Offsets Drive Vocabulary Collapse in Preference Optimization▲3.0k2.33
[PDF]Early Signatures of Memorization in Diffusion Models via Basin Geometry and Cyclic Denoising▼1.2k3.00
[PDF]Probing the Emergent Global Workspace of Reasoning Models on Structured Reasoning Tasks▲9.2k2.67
[PDF]KV Compression Cannot Double as a Jailbreak Defense: The Harmfulness-then-Refusal Trajectory Guides Token Deletion▼5.8k2.33
[PDF]MetaSteer: Context-Conditioned, Non-linear Steering via Attention-Projection Adaptation▲9.2k2.67
Withdrawn or desk rejected (264)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33