https://github.com/ruc-nlpir/webthinker
공식 코드WebThinker: Empowering Large Reasoning Models with Deep Research Capability
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
QAGCN: Answering Multi-Relation Questions via Single-Step Implicit Reasoning over Knowledge Graphs
Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
AidUI: Toward Automated Recognition of Dark Patterns in User Interfaces
When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine
Investigating and Mitigating Failure Modes in Physics-informed Neural Networks (PINNs)
Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks
SafeRoute: Learning to Navigate Streets Safely in an Urban Environment
LAMP: Leveraging Language Prompts for Multi-person Pose Estimation
SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces
Towards real-world navigation with deep differentiable planners
Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments
Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic
Image-based Guidance of Autonomous Aircraft for Wildfire Surveillance and Prediction
LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent
DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences
Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation
Learning to automate cryo-electron microscopy data collection with Ptolemy
Like trainer, like bot? Inheritance of bias in algorithmic content moderation
PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning
MAGE: A Multi-Agent Engine for Automated RTL Code Generation
Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.