Optimization

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training EMNLP 2025 Beyond Autoregression: Fast LLMs via Self-Distillation Through Time ICLR 2025 Beyond Binary Preferences: Semi-Online Label-Free GRACE-KTO with Group-Wise Adaptive Calibration for High-Quality Long-Text Generation EMNLP 2025 Beyond Blur: A Fluid Perspective on Generative Diffusion Models ICCV 2025 Beyond Constant Parameters: Hyper Prediction Models and HyperMPC CoRL 2025 Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning ICML 2025 Beyond Discretization: Learning the Optimal Solution Path AISTATS 2025 Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation ICML 2025 Beyond Excess and Deficiency: Adaptive Length Bias Mitigation in Reward Models for RLHF NAACL 2025 Beyond Fixed Length: Bucket Pre-training is All You Need IJCAI 2025 Beyond Fixed-Length Calibration for Post-Training Compression of LLMs EMNLP 2025 Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution AAAI 2025 Beyond IID: Optimizing Instruction Finetuning from the Perspective of Instruction Interaction and Dependency AAAI 2025 Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning CVPR 2025 Beyond Low-rankness: Guaranteed Matrix Recovery via Modified Nuclear Norm IJCAI 2025 Beyond Mandatory Federations: Balancing Egoism, Utilitarianism and Egalitarianism in Mixed-Motive Games AAAI 2025 Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity ICML 2025 Beyond Next Token Prediction: Patch-Level Training for Large Language Models ICLR 2025 Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs EMNLP 2025 Beyond propagation of chaos: A stochastic algorithm for mean field optimization COLT 2025 Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs ICML 2025 Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities AAAI 2025 Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks ICLR 2025 Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents EMNLP 2025 Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs ICCV 2025