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
157 results for “keyword:"merging"” in ICLR 2027. 47 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Survives Token Merging? Merge-Invariant Low-Rank Attention for Vision Transformers▼4.3k2.00
[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]Unmasking the Hidden Bias, Fairness, and Safety Costs of Compression with Mixture-of-Expert Models▼1.2k3.00
[PDF]LEMMA: Learned Model Merging for Text-to-Image Generation via Multi-Objective Optimization▼5.8k2.33
[PDF]SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation▲5.7k2.00
[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