Large Language Models

Optimization before Evaluation: Evaluation with Unoptimized Prompts Can be Misleading ACL 2025 Optimizing Adaptive Attacks against Watermarks for Language Models ICML 2025 Optimizing Cost-Efficiency with LLM-Generated Training Data for Conversational Semantic Frame Analysis NAACL 2025 Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models EMNLP 2025 Optimizing Large Language Model Training Using FP4 Quantization ICML 2025 Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation NAACL 2025 Optimizing Temperature for Language Models with Multi-Sample Inference ICML 2025 Optimizing Test-Time Compute via Meta Reinforcement Finetuning ICML 2025 Option Symbol Matters: Investigating and Mitigating Multiple-Choice Option Symbol Bias of Large Language Models NAACL 2025 OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling ICML 2025 OpusLM: A Family of Open Unified Speech Language Models Interspeech 2025 Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference ICML 2025 OrcaLoca: An LLM Agent Framework for Software Issue Localization ICML 2025 Orchestrating Emergent Storytelling with Embodied Multi-Agent Systems NeurIPS 2025 OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM ICCV 2025 Order Doesn’t Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation EMNLP 2025 Organize the Web: Constructing Domains Enhances Pre-Training Data Curation ICML 2025 ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research ACL 2025 ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities EMNLP 2025 OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference ICML 2025 OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use ACL 2025 OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction ICML 2025 Otter: Generating Tests from Issues to Validate SWE Patches ICML 2025 OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding ICCV 2025 Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models ACL 2025