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
208 results for “keyword:"architectures"” in ICLR 2027. 44 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SphereJEPA: Learning Spherical Video Representations From Perspective Video via Self-Supervision▲3.0k2.40
[PDF]AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving▼4.3k2.00
[PDF]W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition▼4.3k2.00
[PDF]WeatherJEPA: Joint Embedding of Observational and Atmospheric State Representations for Weather Forecasting▲3.8k2.50
[PDF]Temporal Context Needs the Right Target: Projected Latent Prediction for End-to-End Driving▼4.2k2.20
[PDF]Computation Persists, Routing Degrades: A Mechanistic Analysis of Transformer Length Extrapolation▼4.3k2.00
[PDF]Designing Better Transformers: Using Amorphous Network Proxies to Engineer the Unified Highway Transformer▲11.00
[PDF]Where Does the Recurrence Help? Retrieval-Distance Attribution in Hybrid Sequence Models▼1.2k1.67
[PDF]ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory▼1361.33
[PDF]Motion Chain of Thought: Disentangling Motion Semantics from Visual Appearance for Robotic Manipulation▲5103.00
[PDF]Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design▲3.0k2.33
[PDF]Feedback-gated weight modulation enables state-dependent computation in recurrent neural networks▲6.1k2.00
[PDF]Lower Loss by Forgetting: How Trainable Targets Suppress Information in JEPA World Models▲3.0k2.33
[PDF]The Circle Was Hiding a Helix: Helical Reduced Representations for Exact Vector Symbolic Binding▼71.25
[PDF]CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer-Use Agent with Decoupled Reinforcement Learning▼5.8k2.33
Withdrawn or desk rejected (44)
[PDF]Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous DrivingWithdrawn1.67
[PDF]Predicting the Predictable: Feature Suppression in Joint-Embedding Predictive ArchitecturesDesk rejected
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00
[PDF]TopoJEPA: Topology-Grounded Joint-Embedding Prediction for EEG Foundation ModelsDesk rejected2.33
[PDF]What Data Makes World Models Better Manipulation Planners? Beyond Successful Demonstrations with Diverse Action ExperienceWithdrawn1.00