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
770 results for “keyword:"foundation models"” in ICLR 2027. 170 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LEARNING HIERARCHICAL FUSION OF INTERMEDIATE REPRESENTATIONS ACROSS VISION FOUNDATION MODELS▼1.2k1.67
[PDF]Patchwise 3D Context Embedding: Equipping Efficient 2D Foundation Models With 3D Perception For Brain Hemorrhage Segmentation▼1.2k1.67
[PDF]P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning▲143.33
[PDF]Earth-JEPA:Toward efficient and transferable Earth-system latent representation learning▲3.0k2.33
[PDF]Latent Jacobian Steer: Eliciting Complex Contact-Rich Behaviors from Pretrained Humanoid Controllers▼5.8k2.33
[PDF]Right Values, Wrong Records: Benchmarking and Improving Record Formation in Prompt-to-Data Systems▼5.8k2.33
[PDF]One Score Term Too Many: The Apparent Cost of Normalizing Frozen ViT Tokens Is Largely an Anomaly-Score Artifact▼1.2k1.67
[PDF]TSRouter: Training-Free Capability Landscape Discovery and Routing for Growing Time-Series Foundation Model Zoos▲3952.67
[PDF]Same Knowledge, Different Graph: Knowledge-Graph Foundation Models Are Not Schema-Invariant▼4.5k2.67
[PDF]Auditing Tabular Foundation Models for Wildfire Forecasting: Transfer, Local Adaptation, and Weather-Response Stability▼1.2k1.67
[PDF]Beyond Angular Error: Global and Local Geometry of Failure in Monocular Surface-Normal Models▼4.3k2.00
[PDF]Beyond Source-Domain Accuracy: Controlled Study on Adaptation Granularity for Imaging Sonar Representation Transfer▲3952.67
[PDF]Vec2DNA: Feature-Consistent Genomic Embedding Inversion Attacks and Task-Aligned Defense▲6.3k2.25
[PDF]BoundaryWarp: Revealing and Exploiting Patch-End Vulnerabilities in Time-Series Foundation Models▼11k2.33
[PDF]DC-XPIFM: An Explainable Physics-Informed Foundation Model for AI Data-Center Power Forecasting▲3.0k2.33
[PDF]HiLO: Hierarchical Label-Aware Optimal Transport for Cross-Domain Alignment of Pathology Foundation Model Embeddings▼1.2k1.67
[PDF]One Model, Three Views: Input-Condition Integration for Probabilistic Time Series Foundation Models▲11.00
[PDF]DINOv3 Beats Specialized Detectors: Revisiting Image Manipulation Localization from a Foundation Model Perspective▲5.4k3.00
[PDF]Don't Discard, Repair: A Repair-First Paradigm for Recovering Training Utility from Imperfect Pre-training Corpora▼4.3k2.00
[PDF]Preserving Unique Concepts in Different Modalities for Contrastive Learning: Improvements to Contrastive Audio-Visual Masked Autoencoder▲11.00
[PDF]STAGE: Deciphering Tissue Organization and Predicting Perturbation Responses through Transferable Spatial Representations▼1.2k1.67
Withdrawn or desk rejected (170)
[PDF]GLSC: Global-Local Semantic-Structural Collaboration for Semi-Supervised Remote Sensing SegmentationWithdrawn1.67
[PDF]CHRF-SAM3: Constrained Heterogeneous Representation Fusion for Cross-Domain Few-Shot AdaptationWithdrawn2.00
[PDF]Beyond One-Step Residuals: Trajectory-Aware Manifold Projection for Few-Shot Medical Anomaly DetectionWithdrawn2.00
[PDF]EGODEPTH: A RESIDUAL-BASED STEREO VIDEO DEPTH PREDICTION METHOD WITH 4D SPATIOTEMPORAL FEATURE FUSIONWithdrawn2.00
[PDF]Training-Free Cross-Domain Few-Shot Segmentation via Preserve-Relative Counterfactual RefinementWithdrawn2.00
[PDF]RVHomo: Unsupervised Cross-Modal Homography Estimation with Geometry-Aware VFM FeaturesWithdrawn2.33
[PDF]Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot PoliciesDesk rejected2.33