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
120 results for “keyword:"jepa"” in ICLR 2027. 30 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Extracting Behavior from Frozen Latent World Models: Experience-Anchored Proposals with Offline Verifier Alignment▼1351.33
[PDF]MemJEPA: Erasure-Trained Memory Lets Latent World-Model Planners See Through Occlusion▼1.2k1.67
[PDF]Spectral Unit Tests for Predictive Representation Models: A Fault Atlas and Its Scope Conditions▲4002.67
[PDF]Representational Collapse and Spectral Recovery in Koopman-Structured Time-Series JEPAs▼1.2k1.67
[PDF]Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning▲11.00
[PDF]LeDreamer: Bridging the Understanding of Representation Collapse Between JEPA and Sample-Efficient World Models▼5.8k2.33
[PDF]LeGramJEPA: Negative-Free Multimodal Graph Foundation Models in Latent Space with Volumetric Alignment and SIGReg▼1.2k1.67
[PDF]Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control.▲153.33
[PDF]MedJEPA: Latent Cross-Modal Prediction for Medical Vision-Language Reasoning under Missing Images▼1601.50
[PDF]Pretrained Features as Teachers, Not States: Compact Latent World Models for Visual Planning▲3.0k2.33
[PDF]JOINT-EMBEDDING PREDICTIVE LEARNING CLOSES THE UNIMODAL–MULTIMODAL GAP IN ECG PRE- TRAINING▼5.8k2.33
[PDF]Learning World Models with Joint-Embedding Prediction for Single- and Multi-Agent Reinforcement Learning▼1351.33
[PDF]AGR-JEPA: Action-Grounded Residual Joint-Embedding Predictive Architecture for Planning▼1.2k1.67
[PDF]ST-JEPA: JEPA-Enhanced Temporal Scene–Trajectory Representation Learning for End-to-End Autonomous Driving▲5.4k3.00
[PDF]MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space▼1.2k3.00
[PDF]UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models▲482.75
[PDF]Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning▼1351.33
[PDF]4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting▼4.3k2.00
Withdrawn or desk rejected (30)
[PDF]VeriVLA: Adaptive Test-Time Verification for Flow-Based VLAs with Latent World ModelsWithdrawn2.00
[PDF]A Perfect Model Is Not Enough: A case study on long horizon planning in LeWorldModelWithdrawn1.33
[PDF]What Data Makes World Models Better Manipulation Planners? Beyond Successful Demonstrations with Diverse Action ExperienceWithdrawn1.00
[PDF]Does Surprise Measure Intuitive Physics? The Score Depends on How the Model Is ReadWithdrawn1.00
[PDF]EquiJEPA: Learning Action Representations for Effect Prediction and Action GenerationWithdrawn1.67