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
7,676 results for “keyword:"ai"” in ICLR 2027. 1,833 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models▼5.9k2.50
[PDF]Where and When: Structure-Grounded Credit Assignment for Cross-Modal Reinforcement Learning▼4.5k2.67
[PDF]FIRE: Fourier-Informed Regime Adaptive Estimation for Non-Stationary Time Series Forecasting▼1.2k1.67
[PDF]When Sparse Reward Meets Dense Distillation: Training Dynamics of On-Policy Distillation▲3.0k2.33
[PDF]Revealing Hidden Intent for Defending Text-to-Image Models against Adversarial Attacks▲3.0k2.33
[PDF]From Reliable Explanations to Better Learning: Bridging the OOD Gap in 3D GNN Explanation▼4.3k2.00
[PDF]When Shared Inputs Prevent Heavy Tails from Slowing Model Selection: A Minimax Separation▼4.5k2.67
[PDF]Continuous Detail-Exposure Control via Latent Skipping for View-Level Privacy in Learned Image Compression▲3.0k2.33
[PDF]What Do Benchmarks Measure? Discovering Benchmark Demands and Grounding System Capabilities▲20k2.67
[PDF]Measuring, Predicting, and Diagnosing Compression-Induced Failures in Vision-Language Models▲3.0k2.33
[PDF]Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy▼4.5k2.25
[PDF]BranchWise: A Path Is Not a Policy — Unfolding Successful Trajectories into Model-Tailored Decision Boundaries▲9.2k2.67
[PDF]Finding Root Causes, Not Symptoms: A Mechanism and Method for Agent Failure Attribution▼5.9k2.33
[PDF]Certify Before You Intervene: Pathwise Intervention-Certified Decoding for Multimodal Generation▼5.9k2.33
[PDF]CETRA: Composable Evidence Certificates for Tool-Adaptive Risk Control of Multimodal Assertions▼4.3k2.00
[PDF]ScaffoldBench: A Dynamic Benchmark for Evaluating Pedagogical Scaffolding and ZPD Alignment in Large Language Models▼4.3k2.00
[PDF]ShopLife-Bench: A Benchmark for Multi-Session Multi-User Agent Interaction in E-Commerce Environments▼1.2k1.67
[PDF]Identity Refinement without Re-Editing: Training-Free Enhancement of Identity Fidelity▼4.3k2.00
Withdrawn or desk rejected (1,833)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected