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
73 results for “keyword:"representation alignment"” in ICLR 2027. 21 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ProteinREPA: Structure Predictors as Representation Teachers for Generative Protein Design▲6.1k2.00
[PDF]MAPP: Cross-Lingual Transfer through Representation Alignment with Performance-Gap Probing▲3.0k2.33
[PDF]Graph-Parameterized Capacity for Latent Multi-Hop Recall: Usage, Compression, and Composition▼13k2.00
[PDF]When Alignment Becomes an Interface: Deployment-Dependent Interoperability of Text Embeddings▼5.8k2.33
[PDF]Receiver State Shapes Functional Compatibility: Internal Message Adaptation for Model Stitching▲5.4k3.00
[PDF]Population Similarity Enables Statistically Grounded Comparisons of Representation Alignment▼4.3k2.00
[PDF]GeoProtoFL: Are Class Prototypes Geometrically Aggregatable in Heterogeneous Federated Learning?▲5103.00
[PDF]SS-REPA: Spectral-Spatial Representation Alignment for Onboard Sparse Physical Field Reconstruction▲3.0k2.50
[PDF]NaviVLN:Learning Task-Centric Hierarchical Representations via Embodied Alignment for Dual-System Vision-Language Navigation▲14k3.00
[PDF]Where Models Diverge: Linear Predictability Trace the Direction of Representational Change▼5.8k2.33
[PDF]Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation▲4.6k3.00
[PDF]Attract to Align, Repel to Differentiate: Contrastive Representation Alignment for Diffusion Models▼5.8k2.33
[PDF]What and When to Align: Hierarchy-Decoupled Representation Alignment for Pixel-Space Diffusion▲5.4k3.00
[PDF]Where to Refine and What to Recover: Disentangled Cross-modal Semantic Alignment for CT-to-PET Generation▼1.2k1.67
[PDF]TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons▼5.8k2.33
[PDF]A Patchwise Aggregation Encoder for EEG-to-Image Retrieval: An Analysis of What Image Features Matter▼4.3k2.00
[PDF]Mind the Modality Gap: From Constitutional AI to Contextual Policy-Alignment Through Language Bridging▲13k2.33
[PDF]Align What Forms the Update: Bilinear Factor Alignment for Cross-Model Task-Vector Transfer▲4012.67
Withdrawn or desk rejected (21)
[PDF]dREPA: Difficulty-Aware Representation Alignment Accelerates Diffusion TrainingDesk rejected2.00
[PDF]Cross-Model KV Cache Construction in LLM Familiies: Residual-Stream Mapping Without Matched Head GeometryDesk rejected
[PDF]SynOphsis: Unified Ophthalmic Image and Volume Generation Across Modalities and DimensionsDesk rejected2.33
[PDF]Don’t Retrain—Align: Adapting Autoregressive LMs to Diffusion LMs via Representation AlignmentWithdrawn1.67