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
123 results for “keyword:"model merging"” in ICLR 2027. 38 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Unified Merging of Heterogeneous Pretrained Models: From Layer Selection to Semantic Alignment▼4.5k2.67
[PDF]Feature Core Preservation: Protecting Task-Sensitive Parameter Subspaces for Model Merging▲3952.67
[PDF]Same Delta, Different Effects: Reusing Post-Training Updates after Continual Pretraining▼13k2.00
[PDF]LEMMA: Learned Model Merging for Text-to-Image Generation via Multi-Objective Optimization▼5.8k2.33
[PDF]When the Whole Exceeds the Parts: Constructing Multi-Ability LLMs via Component-wise Weighted Fusion▼1.2k1.67
[PDF]Back to the Weights: Training-Free Model Enhancement via Training Trajectory Extrapolation▼1.2k1.67
[PDF]Beyond the Merged Vector: Fixed-Budget Directional Memory for Data-Free Continual Model Merging▲5103.00
[PDF]When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy▼4.5k2.67
[PDF]Gated Task Arithmetic: Controlling Task-Specific Input Information Flow in Model Merging▼4.3k2.75
[PDF]When Does Orthogonal Training Help Model Merging? Operator-Relative Disentanglement in Task Arithmetic▼1361.33
Withdrawn or desk rejected (38)
[PDF]Dynamic Merging Mutually-Distilled Multi-View Teacher Network for RGB-Event based Representation LearningWithdrawn2.00
[PDF]UniMergeTrack: Hierarchical Model Merging for General RGB-X Visual Object TrackingWithdrawn2.00
[PDF]Erasing the Non-Additive Residue Is Insufficient to Repair Over-Scaled Model MergingDesk rejected