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
904 results for “keyword:"ema"” in ICLR 2027. 260 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]A Study of Naturally Occurring Mathematical Errors in Real-World Theoretical Research with Frontier Models▼1611.50
[PDF]Beyond Tool–Raw Comparisons: Matched-Control Attribution of Semantic Assistance for Code Reasoning▼1361.33
[PDF]Geometric Pareto Control: Physics-Supervised Pareto Representation Learning via Riemannian Energy-Gradient Flow▼5.9k2.50
[PDF]Hand Kinematics as an Implicit Physical Sensor for Egocentric Grasp Pressure Estimation▲5103.00
[PDF]LMI: LATENT MEMORY INTERACTION FOR EFFICIENT AND FAITHFUL LONG-CONTEXT COMPRESSION IN LLMS▲3.0k2.50
[PDF]The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision▲3.0k2.33
[PDF]When Words Change but Meaning Remains: Robust Semantic-Stylistic Watermarking for LLMs▼1.2k1.67
[PDF]Shortcut or Semantics? Understanding Conditioning Interfaces for Steerable Generative Retrieval▲3.0k2.33
[PDF]Learning Where to Constrain: Meta-Learned Trust Allocation for Language-Model Reasoning▲20k2.67
[PDF]Item Representations Matter: Bridging Hard Semantic IDs and Soft Prototype Mixtures for Generative Retrieval▼4.3k2.00
[PDF]SemanticBBOBench: A Benchmark for Semantic Black-Box Optimization with Large Language Models▲9.2k2.67
[PDF]Semantic Cooperative Games for Contribution Attribution in LLM-Based Multi-Agent Systems▼1.2k1.67
[PDF]Beyond Average Risk: Diagnosis-Priority Robust Learning for Structured Radiology Report Generation▼1361.33
[PDF]ActiveLang: Active Open-Vocabulary 3D Mapping with Semantic-Uncertainty-Guided Exploration▼4.5k2.67
[PDF]ORION: EXACT CANONICAL-STATE SUPERVISION FOR SYSTEMATIC GENERALIZATION IN TRANSFORMERS▼1.2k1.67
[PDF]Counterfactual Answer Prediction Training: Improving LLMs' Causal Understanding via Input-Perturbation Difference Prediction▼1.2k1.67
[PDF]More Than Correct Answers: Testing, Tracing, and Predicting Multi-Hop Execution in Transformers▲6.1k2.00
[PDF]Adaptive Contrastive Self-Play for Regime-Aware Reinforcement Learning Fine-Tuning of Language Models▼4.3k2.00
[PDF]Order-Marginalized Generation of Semantic and Collaborative IDs for Generative Recommendation▲5103.00
Withdrawn or desk rejected (260)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]From Euclidean to Riemannian: Boundary-Aware Geodesic Oversampling for Class-Imbalanced GraphsWithdrawn2.00
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33