Optimization

Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-Norm ICLR 2025 Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization ICML 2025 Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models COLING 2025 Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF ICLR 2025 Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning ICML 2025 Exploring Equity of Climate Policies Using Multi-Agent Multi-Objective Reinforcement Learning IJCAI 2025 Exploring Learning Complexity for Efficient Downstream Dataset Pruning ICLR 2025 Exploring Model Kinship for Merging Large Language Models EMNLP 2025 Exploring One Million Machine Learning Pipelines: A Benchmarking Study AutoML 2025 Exploring the Design Space of Visual Context Representation in Video MLLMs ICLR 2025 Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness ICLR 2025 Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization EMNLP 2025 Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality ICLR 2025 Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant IJCAI 2025 Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs ICML 2025 Extending Temperature Scaling with Homogenizing Maps JMLR 2025 Extreme Value Policy Optimization for Safe Reinforcement Learning ICML 2025 Factorized Learning for Temporally Grounded Video-Language Models ICCV 2025 Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree AAAI 2025 Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization ICML 2025 Fast Algorithm for Constrained Linear Inverse Problems JMLR 2025 FAST: A Lightweight Mechanism Unleashing Arbitrary Client Participation in Federated Learning IJCAI 2025 Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play COLT 2025 Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity ICML 2025 Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage ICLR 2025