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
19 results for “keyword:"gradient conflict"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Does Gradient Conflict Predict the Understanding–Generation Trade-off? A Controlled Audit of Conflict-Metric Validity in Unified Multimodal Models▼4.3k2.00
[PDF]Rotation-Based Gradient Balancing: Reconciling Alignment and Fidelity in Multi-Task Learning▼1.2k3.00
[PDF]Auditing Gradient Retention under Hidden Conditions: Exact Cancellation, Objective-Dependent Alignment, and the Limits of Kappa▼1.2k1.67
[PDF]ProjOPD: Conflict Projection for On-Policy Distillation in Agentic Reinforcement Learning▼1351.33
[PDF]TRIDA: Tri-modal Residual-aware Inter-modal Divergence Arbitration for Multi-spectral Object Re-identification▼1351.33
[PDF]Structure Follows Causality: Causally-Aligned Representation Separation Breaks Orthogonal Bullying in Multi-Task Learning▼1351.33
[PDF]When Sparse Reward Meets Dense Distillation: Training Dynamics of On-Policy Distillation▲3.0k2.33
[PDF]Not All Frequencies Are Harmonious: Conflict-Aware Multi-Task Spectral Training for Time-Series Forecasting▼1.2k1.67
Withdrawn or desk rejected (7)
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00
[PDF]TGPO: Tracked-Gradient Policy Optimization for Multi-Reward Reinforcement LearningDesk rejected
[PDF]The Forecast–Reconstruction Tradeoff Is an Artifact of Coupling a Single Latent to Both ObjectivesWithdrawn1.33
[PDF]CONGR-WAM: DIAGNOSING LOCAL CONFLICTS FOR SPARSE GRADIENT ROUTING IN WORLD ACTION MODELSDesk rejected