← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3648 directly classified papers

Papers per year

Papers

Cold Starts and Hard Cases: A Two-Stage SFT-RLVR Approach for Legal Machine Translation (Just-NLP L-MT shared task) IJCNLP 2025
Early Alignment in Two-Layer Networks Training is a Two-Edged Sword JMLR 2025
Efficiently Escaping Saddle Points in Bilevel Optimization JMLR 2025
Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration JMLR 2025
Equivariant Manifold Neural ODEs and Differential Invariants JMLR 2025
Neural Operators Can Play Dynamic Stackelberg Games JMLR 2025
depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers JMLR 2025
Delta-NAS: Difference of Architecture Encoding for Predictor-Based Evolutionary Neural Architecture Search WACV 2025
YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model ACL 2025
ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations EMNLP 2025
MT2ST: Adaptive Multi-Task to Single-Task Learning ACL 2025
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs EMNLP 2025
LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization EMNLP 2025
DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal Object Re-Identification WACV 2025
Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers EMNLP 2025
A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation EMNLP 2025
Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence EMNLP 2025
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time EMNLP 2025
CLaSp: In-Context Layer Skip for Self-Speculative Decoding ACL 2025
CoMMIT: Coordinated Multimodal Instruction Tuning EMNLP 2025
Exploring the Limitations of Mamba in COPY and CoT Reasoning EMNLP 2025
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning EMNLP 2025
Answer Convergence as a Signal for Early Stopping in Reasoning EMNLP 2025
s1: Simple test-time scaling EMNLP 2025
SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data WACV 2025