← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3648 directly classified papers

Papers per year

Papers

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information IJCAI 2025
Uncertainty-Aware Gradient Stabilization for Small Object Detection ICCV 2025
Slamming: Training a Speech Language Model on One GPU in a Day ACL 2025
TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding ICCV 2025
PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation AAAI 2025
HVAdam: A Full-Dimension Adaptive Optimizer AAAI 2025
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning ACL 2025
Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff ACL 2025
The Surprising Effectiveness of Infinite-Width NTKs for Characterizing and Improving Model Training AAAI 2025
Optimized Random Features for the Neural Tangent Kernel (Student Abstract) AAAI 2025
Monitoring Primitive Interactions During the Training of DNNs AAAI 2025
YNU-HPCC at SemEval-2025 Task 6: Using BERT Model with R-drop for Promise Verification SEMEVAL 2025
Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction EMNLP 2025
Optimizing RLHF Training for Large Language Models with Stage Fusion NSDI 2025
A Layer Selection Approach to Test Time Adaptation AAAI 2025
On Local Overfitting and Forgetting in Deep Neural Networks AAAI 2025
SSE-SAM: Balancing Head and Tail Classes Gradually Through Stage-Wise SAM AAAI 2025
Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning NAACL 2025
PowerMLP: An Efficient Version of KAN AAAI 2025
ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection AAAI 2025
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference AAAI 2025
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025
Pruning Large Language Models with Semi-Structural Adaptive Sparse Training AAAI 2025
From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025
Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review ACL 2025