← 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
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration ACL 2025
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models ACL 2025
Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic ACL 2025
NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model ACL 2025
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering ACL 2025
Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values EMNLP 2025
Time-LlaMA: Adapting Large Language Models for Time Series Modeling via Dynamic Low-rank Adaptation ACL 2025
CLaSp: In-Context Layer Skip for Self-Speculative Decoding ACL 2025
Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models ACL 2025
TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding ACL 2025
Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking ACL 2025
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering ACL 2025
Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding ACL 2025
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion ACL 2025
LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization EMNLP 2025
Better Embeddings with Coupled Adam ACL 2025
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning ACL 2025
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking ACL 2025
Value Residual Learning ACL 2025
Language Fusion for Parameter-Efficient Cross-lingual Transfer ACL 2025
Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks OSDI 2025
LESA: Learnable LLM Layer Scaling-Up ACL 2025
HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation ACL 2025
Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up ACL 2025