SOTAVerified

Large Language Model

Papers

Showing 151175 of 6097 papers

TitleStatusHype
Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement LearningCode4
Fast Transformer Decoding: One Write-Head is All You NeedCode4
AgentGym: Evolving Large Language Model-based Agents across Diverse EnvironmentsCode4
G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language ModelCode4
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world EnvironmentsCode4
Multimodal Table UnderstandingCode3
Multi-agent Architecture Search via Agentic SupernetCode3
Evaluation Report on MCP ServersCode3
Evalverse: Unified and Accessible Library for Large Language Model EvaluationCode3
Enhancing Decision Analysis with a Large Language Model: pyDecision a Comprehensive Library of MCDA Methods in PythonCode3
OceanGPT: A Large Language Model for Ocean Science TasksCode3
Editable Scene Simulation for Autonomous Driving via Collaborative LLM-AgentsCode3
MoMA: Multimodal LLM Adapter for Fast Personalized Image GenerationCode3
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM ModelCode3
Odyssey: Empowering Minecraft Agents with Open-World SkillsCode3
MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare CopilotCode3
Baichuan-Omni Technical ReportCode3
MeshXL: Neural Coordinate Field for Generative 3D Foundation ModelsCode3
AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive ReasoningCode3
Baichuan-Audio: A Unified Framework for End-to-End Speech InteractionCode3
M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language ModelsCode3
LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at ScaleCode3
Detecting hallucinations in large language models using semantic entropyCode3
Llemma: An Open Language Model For MathematicsCode3
BayLing 2: A Multilingual Large Language Model with Efficient Language AlignmentCode3
Show:102550
← PrevPage 7 of 244Next →

No leaderboard results yet.