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
753 results for “keyword:"fine tuning"” in ICLR 2027. 158 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning Where to Adapt: Target-Aware Parameter-Efficient Fine-Tuning for Neural Operators▲3.0k2.33
[PDF]PRISM: Spectral Analysis Aided Nested Manifold Learning for Efficient Multimodal Large Language Model Adaptation on Edge▼1361.33
[PDF]Learning What vs. Learning How: Decomposing Task and Interface Competence in Agentic Training▲5103.00
[PDF]A DEAFENING SILENCE: CATASTROPHIC FORGETTING LIVES IN THE OUTPUT EMBEDDINGS OF TOKENS THE DATA NEVER SPEAKS▼4.5k2.67
[PDF]A GPU Environment for Chinese Standard Mahjong with a Judge-Replay Fidelity Contract and Reference RL Workloads▼1361.33
[PDF]Bidirectional Transfer, Asymmetric Expression: Math Fine-Tuning Conceals the Code Gains It Carries▲13k2.33
[PDF]CenWrite: Support-Centered LoRA with Boundary Updates for Cross-Domain Few-Shot Learning▼1.2k1.67
[PDF]SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise▼1.2k1.67
[PDF]Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity▲3952.67
[PDF]SEAM: Shared-Expert Adaptation Masked by Closed-Loop Scores in Reward Fine-Tuned Diffusion Planners▲3.0k2.33
[PDF]Same Target, Different Paths: Learning from Multiple Reasoning Trajectories for Generative Recommendation▼1.2k1.67
[PDF]Beyond Coordinate Sparsity: Controlling Module Exposure Against Gradient Reconstruction in Federated LoRA▼1.2k1.67
[PDF]Synth-Ethics: Synthetic Training Data for LLM Constitutions Grounded in Ethical Traditions▼5.8k2.33
[PDF]UaRA: Uncertainty-aware Rank Allocation for Parameter-Efficient Fine-Tuning of Diffusion Large Language Models▼5.8k2.33
[PDF]Removing Sequentially Trained Modules: Effects on Retained Sources and Subsequent Learning▼1611.50
[PDF]Fine-Tuned Judgment Lives in the Weights: In-Context Examples Help Untrained Models and Override Trained Ones▼1361.33
Withdrawn or desk rejected (158)
[PDF]DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution StrategiesWithdrawn1.67
[PDF]Signs Beat Floats: Low-Rank Double-Binary Adaptation for Storage-Efficient DeploymentWithdrawn1.67
[PDF]PathoField: Capacity-Controlled Feature-Space Residual Adaptation for Few-Shot Healthy-to-Pathological 3T-to-7T MRI SynthesisWithdrawn1.33