Neural Network Optimization

DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal Object Re-Identification WACV 2025 Do Deep Neural Network Solutions Form a Star Domain? ICLR 2025 DoDS-IITPKD:Submissions to the WMT25 Low-Resource Indic Language Translation Task EMNLP 2025 Does Self-Attention Need Separate Weights in Transformers? NAACL 2025 Does SGD really happen in tiny subspaces? ICLR 2025 Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild CVPR 2025 Do Your Best and Get Enough Rest for Continual Learning CVPR 2025 DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle ICLR 2025 DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization ACL 2025 Drawing Developmental Trajectory from Cortical Surface Reconstruction ICCV 2025 Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models ACL 2025 Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model ACL 2025 Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Training RSS 2025 DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution CVPR 2025 E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning EMNLP 2025 Early Alignment in Two-Layer Networks Training is a Two-Edged Sword JMLR 2025 ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training EMNLP 2025 EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference EMNLP 2025 EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback JMLR 2025 Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks AAAI 2025 Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product NAACL 2025 Efficient Bisection Projection to Ensure Neural-Network Solution Feasibility for Optimization over General Set ICML 2025 Efficient Diffusion as Low Light Enhancer CVPR 2025 Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction EMNLP 2025 Efficiently Escaping Saddle Points in Bilevel Optimization JMLR 2025