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
33,054 results for “keyword:"r"” in ICLR 2027. 8,246 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information▲9.3k2.67
[PDF]High Reward, Wrong Sequences: Reward-Hacking Resistant Discrete Diffusion for 5’UTR Design▼1351.33
[PDF]RouteTS: Budgeted Spectral Component Routing across Time and Frequency Domains for Time Series Forecasting▼4.3k2.00
[PDF]Fine-grained Credit Assignment for Multi-turn Critic-free LLM Reinforcement Learning with Sequential Equilibrium Optimization▲3.0k2.50
[PDF]Symbolic Music Reasoning Needs Checkers That Survive Rewording: What a High Score Covers▼1.2k1.67
[PDF]BudgetCMT: Joint Allocation of Teacher Compute and Student Supervision Budgets in Consistency Mid-Training▼4.3k2.00
[PDF]Off-Diagonal Hessian Sensitivity for Post-Training Quantization of Large Language Models▼4.3k2.00
[PDF]AutoSkillDrain: Resource Amplification Attacks on LLM Agents via Malicious Skill Optimization▲3.1k2.33
[PDF]Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data▲3.1k2.33
[PDF]FRITES: Provable Diffusion Posterior Sampling via Forward-Reverse Iterations of Tilted SDEs▲6.0k2.00
[PDF]Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models▲3232.67
[PDF]OmniShowcase: Omnidirectional Subject-Consistent Video Generation From Multi-View Images▲3232.67
[PDF]What CLIP Sees When Structure Breaks: Patch-Shuffle Response as a Generalizable Cue for AI-Generated Image Detection▲3232.67
[PDF]MATCHA: Bridging the Gap between Sample and Wall-Clock Efficiency in Model-Based Multi-Agent Reinforcement Learning▲3232.67
[PDF]Thresholds, Not Normalization: A Homeostatic Spiking Layer at Parity Without the Overhead▲6.5k3.33
Withdrawn or desk rejected (8,246)
[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