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
380 results for “keyword:"encoder"” in ICLR 2027. 90 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reconstruction, Not Localization: A Mechanistic Account of Sparse-Feature OOD Detection in Vision Transformers▼1361.33
[PDF]LEARNING HIERARCHICAL FUSION OF INTERMEDIATE REPRESENTATIONS ACROSS VISION FOUNDATION MODELS▼1.2k1.67
[PDF]Integrated PU Learning and Deep Generative VAEs for Indication-Driven Missingness to Improve MNAR Imputation and Prediction▲3.0k2.33
[PDF]MechLeash-FL: Mechanistic Leashing of Latent Features for Federated Learning under Feature Skew▲402.80
[PDF]SkillComp: Internalizing Skill Relations in Dense Retrievers for Complete Skill-Set Retrieval from Large-Scale Libraries▼5.8k2.33
[PDF]SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise▼1.2k1.67
[PDF]De-Absorption Reparameterization: Post-hoc Repair of Feature Absorption in Sparse Autoencoders.▲3.0k2.33
[PDF]Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders▼5.8k2.33
[PDF]Contrastive Label-Embedding Alignment: Adapting Dual Encoders for Text Classification from Label Descriptions▼5.8k2.33
[PDF]Iterative distillation of Matryoshka sparse autoencoders improves hierarchical feature organization in ESMFold2▲11.00
[PDF]HyperRoGMAE: Multi-Scale Semantic Hypergraphs for Robust Graph Masked Autoencoder against Structural Attacks▲5.4k3.00
[PDF]Adapt Part of the Way: Class Text as a Prior for Few-Shot Self-Supervised Vision Models▼1.2k3.00
[PDF]Exploring Divergence Between Brain Responses and Language Model Representations Using Crosscoders▲9.2k2.67
[PDF]Chain2Parallel: Post-Hoc Parallelization of T5 Classifier Chains for Few-Shot Multi-Label Classification▼5.8k2.33
[PDF]MemJEPA: Erasure-Trained Memory Lets Latent World-Model Planners See Through Occlusion▼1.2k1.67
[PDF]SHADOW ANCHORING: GROUNDING HUMAN- INTERPRETABLE CONCEPTS IN TRANSFORMERS VIA SPARSE AUTOENCODERS▼1361.33
[PDF]Pinning Visual Paths:Preserving Visual Structure for Ultra-Low-Bit Vision Encoders with Task-Informed Reconstruction▼4.3k2.00
Withdrawn or desk rejected (90)
[PDF]PARSE: An Autonomous Algorithm for Mechanistic Interpretability Based on Dynamic, Adaptive Sparse AutoencodersWithdrawn1.00
[PDF]TotiCell: Structured Masking over Full-Coverage Gene Blocks for Single-Cell Representation LearningDesk rejected2.33
[PDF]DC-Gen 2.0: Efficient and High-Fidelity Image Generation in Deeply Compressed Latent SpacesDesk rejected2.67