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
21,634 results for “keyword:"ar"” in ICLR 2027. 5,073 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Hard to Remove, Cheap to Replace: Compact, Transferable Surrogates for Sensitive LLM Layers▲6.0k2.00
[PDF]COPE: Recovering Long-Horizon Coding Tasks through Compression of Pull-Request Evolution▲3352.67
[PDF]Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data▼4.3k2.00
[PDF]-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Labeled QA Data▼4.5k2.25
[PDF]SAIL: Sparse Autoencoders for Interpretable Alignment of Human Vision and Multimodal Large Language Models▲9.3k2.67
[PDF]BEAST: Boundary-aware Semantic Extrapolation with Debiased Topology for Long-Tailed Text-attributed Graph Learning▲3.0k2.50
[PDF]Dy-VoiceBench: Stateful Worlds and Living Users for Evaluating Dynamic Spoken Dialogue Agents▼1431.50
[PDF]SonoArena: Formulating and Benchmarking Agentic Decision-Making in Ultrasound Examination▲6.5k3.33
[PDF]Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning▲3.1k2.33
[PDF]Granularity Gating-Guided Label-Specific Metric Learning for Multi-Label Classification▼1.2k1.67
[PDF]Goodhart’s Law in Performance Benchmarks: Measuring and Mitigating Software Overoptimization▼4.3k2.00
[PDF]Dynamic Reliability Curriculum Guided Reinforcement Learning for Partial Label Disambiguation▼4.5k2.67
[PDF]Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding Agents▼5.9k2.40
[PDF]COMPOSE: Molecular Generation and Optimization with a Reusable Stochastic Rewrite Process▲6.0k2.00
[PDF]SatelliteOpsGym: Benchmarking AI Agents from Fault Diagnosis to Closed-Loop Recovery in Satellite Operations}▼4.3k2.00
[PDF]CRET: Target-Selective Subspace Learning for Concept Erasure in Text-to-Image Diffusion Models▲20k2.67
[PDF]AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization▼4.3k2.00
[PDF]One-Step Consistency-aware Graph Dictionary Learning for Incomplete Multi-View Clustering▼1.2k1.67
[PDF]BrainMamba: A Scalable EEG Foundation Model for Coupled Multi-Channel Spatiotemporal Evolution▲3352.67
[PDF]MosaicRec: Diagnosing Specification Grounding and Set Construction in Recommendation Agents▲3352.67
[PDF]How Much Evaluation Is Enough? Risk-Aware Adaptive Evaluation (RAAE) of LLMs in High-Stakes Financial Applications▼1361.33
[PDF]PLANSPACE: SEPARATING REFERENCE REPRODUCTION, PLAN VALIDITY, AND INTERFACE COMPLIANCE IN SYMBOLIC PLANNING▼1.2k1.67
[PDF]Don't Ignore Them: Scaffold Features Matter for Stable SAE Steering in Diffusion Models▲3352.67
[PDF]ZAPD: Zero-Shot Adaptation via Primal-Dual Updates for Constrained Reinforcement Learning▲6.0k2.00
[PDF]PEPFM-TANRL: FINE-TUNING A MULTI-MANIFOLD FLOW MATCHING MODEL FOR PEPTIDE DESIGN VIA TANGENT-SPACE GRPO▼1.2k1.67
[PDF]Quasimetric Distance with Flow-Based Planning for Offline Hierarchical Goal-Conditioned RL▼4.3k2.00
Withdrawn or desk rejected (5,073)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[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