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380 results for “keyword:"encoder"” in ICLR 2027. 90 withdrawn or desk rejected listed apart.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]Disentangling Latent Representations by Groups, not Dimensions, via Group-wise Total Correlation▼5.9k2.50
[PDF]SAE Interventions Can Be Unreliable: Post-Intervention Recovery of Suppressed Behavior▼4.3k2.00
[PDF]A Domain-Aligned Encoder Evaluation Framework for FID-like Quality Metrics on Synthetic 3D Medical Imaging▼1.2k1.67
[PDF]When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders▼1.2k3.00
[PDF]PACO-SAE: Evaluating Concept Grounding and Feature Splitting in Vision Sparse Autoencoders▼4.5k2.67
[PDF]Weight-Dictionary Decomposition: Reading a Transformer's Residual Stream with Its Own Writes▼1361.33
[PDF]Slice Selection Matters: Structured and Adaptive Directions for Sliced Latent Regularization▼1361.33
[PDF]ACA: COUPLING RELATIONAL ALIGNMENT AND COMPLEMENTARY REGULARIZATION FOR VISION ENCODER FUSION▼1.2k1.67
[PDF]When More Foundation Models Mean Less: Diagnosing and Addressing Multi-View Fusion Failure▼13k2.00
[PDF]IWCAE: Importance-Weighted Conditional Autoencoders for Domain-Adaptive Generative Modeling▲9.7k2.75
[PDF]Retrieval Gains, Similarity Losses: Controllable Specialisation for Entity-Specific Few-Shot Adaptation▲6.1k2.00
[PDF]Don't Mind the Gap: Interpretable Vision-Language Models via Independent Sparse Autoencoders▲3.0k2.33
[PDF]QuMUSE: Generative Pretraining from Local Measurements for Characterizing Quantum Many-Body Ground States▼4.3k2.00
[PDF]Ladder Transformer: Unified Self-Supervised Learning for Continuous Time Multimodal Streams▲14k3.00
Withdrawn or desk rejected (90)
[PDF]X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale DistillationWithdrawn1.33