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
11,749 results for “keyword:"models"” in ICLR 2027. 2,922 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]FieldDrive: Field-Guided One-Step Trajectory Generation and Reward Optimization for Autonomous Driving▲4.6k3.00
[PDF]When Agents Learn the Wrong Lesson: Credit-Assignment Poisoning in Reflective LLM Agents▲5083.00
[PDF]Small Language Models for Large Speech Models: Latent Acoustic Arbitration for ASR Correction▼1.2k1.67
[PDF]QCache-VLA: Quantization and Diffusion Cache for Efficient Vision-Language-Action Policy Inference▲9.2k2.67
[PDF]PTPO: Progressive Theorem-Guided Policy Optimization for LLM-Based Mathematical Reasoning▲3.0k2.33
[PDF]Correct While Verifying: Intermediate Target Predictions for Speculative Draft Correction▼1351.33
[PDF]RoboStressBench: A Diagnostic Benchmark for Visual Stress in Embodied Scene Understanding▲5083.00
[PDF]Beyond Global Thresholds: Token-Level Calibrated Adaptive Parallel Decoding for Diffusion Language Models▲3812.67
[PDF]Nucleus Speculative Decoding: Plausibility-Aware Verification Beyond Exact Distribution▼1.3k1.75
[PDF]Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval▼5.9k2.33
[PDF]Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models▼1351.33
[PDF]Efficiency of Diffusion Models for Infinite-dimensional Data Generation: Dimension Independent Approximation and Estimation Errors▲3812.67
[PDF]Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models▲3812.67
[PDF]MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability▲3.0k2.33
[PDF]When Representation Change Misleads: Evaluating Encoder Adaptation in Time-Series Foundation Models▼1351.33
[PDF]HOW ERASED IS ERASED? QUANTIFYING AND IMPROVING THE RECOVERABILITY OF CONCEPT REMOVAL IN CLIP▼61.25
[PDF]Learning What Actions Change: Action Effect Matching for Dynamics-Faithful World Models▲3812.67
Withdrawn or desk rejected (2,922)
[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]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected