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
33,085 results for “keyword:"r"” in ICLR 2027. 8,215 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LatentSpec: Two-Stage Thinker–Drafter Parallel Drafting with Shared Latent Reasoning for Speculative Decoding▲9.2k2.67
[PDF]BRACE: Adversarial and Contrastive Endpoint Regularization for Schrödinger-Bridge Image Enhancement▼4.3k2.00
[PDF]ProtoLoRA: Visual-Prototype-Guided LoRA Backdoor Attack against Vision–Language Models▼5.9k2.33
[PDF]A Harmful Request Is Still a Request: Benign Fine-Tuning Rewrites How Aligned Models Begin to Answer▲3912.67
[PDF]General Post-Training 3DGS Compression: Coordinating Quantization and Search for Quality-Constrained Size Minimization▲5.4k3.00
[PDF]Rethinking Exploration in Generative Recommendation: From More Candidates to Better Candidate Sets▼1.2k1.67
[PDF]From Global to Dense Representational Convergence: Shared Semantic Geometry Simplifies Vision-Language Connection▲3.0k2.33
[PDF]Towards All-Atom Protein World Models: Learning and Diagnosing Predictive Latent Representations▼4.3k2.00
[PDF]ASNER: Adaptive Semantic Neighborhoods and Evidence-Grounded Refinement for Software Architecture Recovery▼4.3k2.00
[PDF]TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models▼4.3k2.00
[PDF]BKBAgent: A Battery Parameter Identification Agent with Bayesian Experimental Design and Knowledge Graph▼4.3k2.00
[PDF]The Loss Floor of Denoising Score Matching: Fisher Geometry from Schr\"odinger Bridges▼4.3k2.00
[PDF]Learning Style-Invariant Temporal Semantics for Source-Free Time-Series Domain Adaptation▲5103.00
[PDF]Diffusion Additive Models: Interpretable Generative Prediction through Feature-Wise Contributions▼1361.33
Withdrawn or desk rejected (8,215)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Pulse2View: Same-Sensor Cross-View Pre-Training for Patient-Level Multi-Disease Classification from Wearable PPGWithdrawn1.67