fine tuning

Graph Generative Pre-trained Transformer ICML 2025 How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence ICML 2025 H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models ICML 2025 Idiosyncrasies in Large Language Models ICML 2025 Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens ICML 2025 InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective ICML 2025 Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning ICML 2025 Large Language Models are Demonstration Pre-Selectors for Themselves ICML 2025 Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning ICML 2025 Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models ICML 2025 Leveraging Per-Instance Privacy for Machine Unlearning ICML 2025 LongRoPE2: Near-Lossless LLM Context Window Scaling ICML 2025 LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits ICML 2025 MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition ICML 2025 Neural Palate Kueh NeurIPS 2025 Not All Wrong is Bad: Using Adversarial Examples for Unlearning ICML 2025 Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference ICML 2025 Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization ICLR 2025 Optimizing Test-Time Compute via Meta Reinforcement Finetuning ICML 2025 Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models ICML 2025 Overtrained Language Models Are Harder to Fine-Tune ICML 2025 Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models ICML 2025 Position: LLM Social Simulations Are a Promising Research Method ICML 2025 Provable unlearning in topic modeling and downstream tasks ICLR 2025 Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting ICML 2025