Large Language Models

ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework EMNLP 2025 MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning ICML 2025 Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMs EMNLP 2025 MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty NAACL 2025 Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support EMNLP 2025 Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language ACL 2025 Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models ACL 2025 MARGE: Improving Math Reasoning with Guided Exploration ICML 2025 MARK: Multi-agent Collaboration with Ranking Guidance for Text-attributed Graph Clustering ACL 2025 MARS: Unleashing the Power of Variance Reduction for Training Large Models ICML 2025 MASA: LLM-Driven Multi-Agent Systems for Autoformalization EMNLP 2025 Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models ACL 2025 MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems ICML 2025 Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More ICML 2025 MasRouter: Learning to Route LLMs for Multi-Agent Systems ACL 2025 Massively Multilingual Instruction-Following Information Extraction ACL 2025 Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality EMNLP 2025 Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding ICML 2025 MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models ICML 2025 Mastering Board Games by External and Internal Planning with Language Models ICML 2025 Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness ICCV 2025 MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks ACL 2025 MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection ACL 2025 MathBuddy: A Multimodal System for Affective Math Tutoring EMNLP 2025 MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning ACL 2025