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
268 results for “keyword:"efficient fine tuning"” in ICLR 2027. 74 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RAC-LoRA: Router-Aware Combinatorial LoRA for Adaptive Parameter-Efficient Fine-Tuning▼4.3k2.00
[PDF]FoRA: Forward-Only Residual Adaptation for Federated Fine-Tuning of Large Language Models▲3952.67
[PDF]Stabilizing Zeroth-Order Fine-Tuning of Mixture-of-Experts via One-Sided Estimation and Expert Replay▲5103.00
[PDF]Two-Phase Caching and Activation for Input-Efficient Fine-Tuning of Vision Transformers▼5.8k2.33
[PDF]FARMerge: Learning Functional Task Representations for Source-Data-Free Adapter Merging▼4.5k2.67
[PDF]Rethinking Quantized LLM Fine-Tuning: An Adaptive-Grouping Alternating Zeroth-Order Algorithm in Continuous Mapping Space▼4.3k2.00
[PDF]RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning▲13k2.33
[PDF]JEP-VGP: Learning Vision Graph Prompts via Joint-Embedding Prediction of Prompt Residuals▲1.7k3.33
[PDF]From Uniform Capacity to Functional Roles: Efficient Visual LoRA for Source-Free Cross-Domain Few-Shot Learning▼1.2k1.67
[PDF]Auditing Permanence: Exact Write Accounting and a Matched-Volume Control for Optimizer-State Gates▼4.3k2.00
[PDF]SVDoRA: Spectral Verification-Aware Direction-Oriented Rank Adaptation via Outcome-Guided Spectral Annealing▼4.3k2.00
[PDF]Reward-Proportional Routing of LoRA Experts for Continual Learning in Large Language Models▼1.2k1.67
[PDF]DualMem-Evo: Dual-Memory Evolution for Replay-Free Continual Adaptation of Vision-Language Models▼5.8k2.33
[PDF]Fast and Accurate: Improving Personalized LLM Performance by Semantic Concentration Inspired Workload Split between RAG and Fine-Tuning▲9.2k2.67
[PDF]VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts▼4.3k2.75
[PDF]Your “Pro” LLM Subscription May Actually Be “Free”: Exposing Fingerprint Spoofing Risks in LLM Inference Services▼1.2k1.67
[PDF]Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition▲5.4k3.00
[PDF]Water-Filling LoRA: Data-Free Rank Allocation via Conditional Estimation–Approximation Bounds▼5.8k2.33
Withdrawn or desk rejected (74)
[PDF]Most of the Gain Is Not Video: Taking Apart a Fine-Tuned Video Question-Answering ScoreWithdrawn1.67
[PDF]Fed3DLoRA: Cross-Layer Tensor Consensus for Heterogeneous Federated Fine-TuningDesk rejected2.67