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
1,547 results for “keyword:"ir"” in ICLR 2027. 379 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]EnvAudit: Auditing the Training Utility of Synthetic Agent Environments under a Fixed Budget▼1361.33
[PDF]Depth-Aware Visual Manipulation Relationship Reasoning with Gated Decoder-Layer Aggregation▼4.3k2.00
[PDF]ClockBridge: Partial Identification of Cross-Modal Disease Timing across Unpaired Cohorts▼1361.33
[PDF]CausalExoFormer: End-to-End Lag-Aware Causal Structure Learning for Exogenous Time-Series Forecasting▼1.2k1.67
[PDF]Beyond Aggregate Accuracy: A Deployment-Aware Dataset and Benchmark for Mixed-Defect Wafer-Map VQA▼1.2k1.67
[PDF]Learning to Repair the Learner: Evaluating Recursive Improvement in Neuro-Symbolic World Models▼4.5k2.67
[PDF]When Is Self-Repair No Longer Possible? Certifying Irrecoverable Turning Points in Tool-Using Agents▼1361.33
[PDF]ConGRets: Low-Resource, Low-Latency Co-Speech Gesture Synthesis via Contrastive Latent Prediction▼1361.33
[PDF]Shared-Factor Distribution Shift in Multi-Task Learning: Identification and Adaptation▼4.5k2.67
[PDF]VasoDPO: Aligning Treatment Actions with Patient States through State-Fixed Preference Construction▼4.5k2.25
[PDF]ECHO: Emergent Common-Mode Hidden Offsets Drive Vocabulary Collapse in Preference Optimization▲3.0k2.33
[PDF]Statistical guarantees for robust deep learning under heavy-tailed noise and covariates▼4.3k2.00
[PDF]LINC: Label-Free In-Context Network Reconfiguration under Unobserved Failure-Mode Switches▲3.0k2.33
[PDF]KV Compression Cannot Double as a Jailbreak Defense: The Harmfulness-then-Refusal Trajectory Guides Token Deletion▼5.8k2.33
[PDF]Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent▼4.3k2.00
[PDF]The Implicit Bias of Mirror Descent on Multiclass Separable Data: Stochasticity and Momentum▼1.1k3.25
[PDF]LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Live Financial Markets▼4.3k2.00
[PDF]Poisoning Cross-View Correspondence in Vertical Federated Learning via Consistent Latent-Cluster Reassignment▲3.0k2.50
[PDF]Same Error, Different Consequences: Information Interfaces between Deterministic Completion and Stochastic Time-Series Generation▲11.00
[PDF]When Does a Memory Descendant Need Repair? Structural Lineage vs. Stale State in Persistent Agent Memory▲432.75
Withdrawn or desk rejected (379)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67