SOTAVerified

Large Language Model

Papers

Showing 226250 of 6097 papers

TitleStatusHype
Multimodal Table UnderstandingCode3
Multi-agent Architecture Search via Agentic SupernetCode3
GuardT2I: Defending Text-to-Image Models from Adversarial PromptsCode3
AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API CallsCode3
MoMA: Multimodal LLM Adapter for Fast Personalized Image GenerationCode3
APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model PromptsCode3
DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video GenerationCode3
MeshXL: Neural Coordinate Field for Generative 3D Foundation ModelsCode3
OceanGPT: A Large Language Model for Ocean Science TasksCode3
Hierarchical Prompting Assists Large Language Model on Web NavigationCode3
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language ModelCode3
Detecting hallucinations in large language models using semantic entropyCode3
AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive ReasoningCode3
Deep Learning and LLM-based Methods Applied to Stellar Lightcurve ClassificationCode3
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive MemoryCode3
M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language ModelsCode3
TaskGen: A Task-Based, Memory-Infused Agentic Framework using StrictJSONCode3
An Actionable Framework for Assessing Bias and Fairness in Large Language Model Use CasesCode3
Llemma: An Open Language Model For MathematicsCode3
HuatuoGPT, towards Taming Language Model to Be a DoctorCode3
LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at ScaleCode3
GroundingGPT:Language Enhanced Multi-modal Grounding ModelCode3
LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache ManagementCode3
Lifelong Learning of Large Language Model based Agents: A RoadmapCode3
Large Language Model based Long-tail Query Rewriting in Taobao SearchCode3
Show:102550
← PrevPage 10 of 244Next →

No leaderboard results yet.