Optimization

Why Do Some Inputs Break Low-Bit LLM Quantization? EMNLP 2025 Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg ICML 2025 WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild ICLR 2025 Witty: An Efficient Solver for Computing Minimum-Size Decision Trees AAAI 2025 X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale ICLR 2025 XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML EMNLP 2025 xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation ICLR 2025 XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression EMNLP 2025 YinYang-Align: A new Benchmark for Competing Objectives and Introducing Multi-Objective Preference based Text-to-Image Alignment ACL 2025 Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding ACL 2025 YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model ACL 2025 Z1: Efficient Test-time Scaling with Code EMNLP 2025 ZEN: Empowering Distributed Training with Sparsity-driven Data Synchronization OSDI 2025 ZERA: Zero-init Instruction Evolving Refinement Agent – From Zero Instructions to Structured Prompts via Principle-based Optimization EMNLP 2025 ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think ICML 2025 Zero-Shot Offline Imitation Learning via Optimal Transport ICML 2025 Zeroth-Order Fine-Tuning of LLMs in Random Subspaces ICCV 2025 Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity ICLR 2025 Zeroth-Order Methods for Nonconvex Stochastic Problems with Decision-Dependent Distributions AAAI 2025 Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference ICLR 2025 ZETA: Leveraging Z-order Curves for Efficient Top-k Attention ICLR 2025 ZipMPC: Compressed Context-Dependent MPC Cost via Imitation Learning CoRL 2025 𝜙-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation ACL 2025 β-DPO: Direct Preference Optimization with Dynamic β NeurIPS 2024 $C^2M^3$: Cycle-Consistent Multi-Model Merging NeurIPS 2024