Optimization

Chip Placement with Diffusion Models ICML 2025 CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers ICCV 2025 CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems ICLR 2025 Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off ICML 2025 Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies ICML 2025 Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed ICML 2025 CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling EMNLP 2025 CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control ICLR 2025 Closed-form Solutions: A New Perspective on Solving Differential Equations ICML 2025 Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models CVPR 2025 ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation EMNLP 2025 ClusterAttn: KV Cache Compression under Intrinsic Attention Clustering ACL 2025 Clustering Items through Bandit Feedback: Finding the Right Feature out of Many ICML 2025 ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs EMNLP 2025 COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection CVPR 2025 COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training ICLR 2025 CoA: Towards Real Image Dehazing via Compression-and-Adaptation CVPR 2025 CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization ICML 2025 CODA: Repurposing Continuous VAEs for Discrete Tokenization ICCV 2025 CodeArena: A Collective Evaluation Platform for LLM Code Generation ACL 2025 CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning ICCV 2025 CODEOFCONDUCT at Multilingual Counterspeech Generation: A Context-Aware Model for Robust Counterspeech Generation in Low-Resource Languages COLING 2025 CodePRM: Execution Feedback-enhanced Process Reward Model for Code Generation ACL 2025 CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation ACL 2025 Co-Design of Soft Gripper with Neural Physics CoRL 2025