Showing 541–560 of 1,726 results
/ Date/ Name
May 13, 2025Behind Maya: Building a Multilingual Vision Language ModelMay 7, 2025HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific InsightsMay 7, 2025Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUsMay 6, 2025Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and ExtrapolationMay 5, 2025Developing A Framework to Support Human Evaluation of Bias in Generated Free Response TextMay 1, 2025On the generalization of language models from in-context learning and finetuning: a controlled studyApr 30, 2025Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMsApr 26, 2025Theory of Mind in Large Language Models: Assessment and EnhancementApr 25, 2025EvidenceBench: A Benchmark for Extracting Evidence from Biomedical PapersApr 25, 2025SMARTFinRAG: Interactive Modularized Financial RAG BenchmarkApr 24, 2025HalluLens: LLM Hallucination BenchmarkApr 24, 2025A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and AdaptationApr 23, 2025Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" ControlApr 23, 2025WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World ModelApr 22, 2025Vision-Language Models Are Not Pragmatically Competent in Referring Expression GenerationApr 20, 2025A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMsApr 17, 2025ChatEXAONEPath: An Expert-level Multimodal Large Language Model for Histopathology Using Whole Slide ImagesApr 16, 2025WebRollback: Enhancing Web Agents with Explicit Rollback MechanismsApr 15, 2025Exploring Persona-dependent LLM Alignment for the Moral Machine ExperimentApr 14, 2025RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability