awesome-llm4tr
Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap
https://github.com/tongnie/awesome-llm4tr
Last synced: 4 days ago
JSON representation
-
🌟 Awesome Lists and Resource Hubs
- jbhuang0604/awesome-computer-vision
- RUCAIBox/LLMSurvey - training, fine-tuning, and reasoning. |
- thunlp/GNNPapers - read list of papers on Graph Neural Networks, highly relevant for transportation network modeling. |
- manfreddiaz/awesome-autonomous-driving
- huggingface/datasets
- BradyFU/Awesome-Multimodal-Large-Language-Models
- diff-usion/Awesome-Diffusion-Models
- kaushikb11/awesome-llm-agents - based agents. |
- microsoft/DeepSpeed
- ge25nab/Awesome-VLM-AD-ITS - Language Models for Autonomous Driving and ITS. |
-
💡 Foundational LLM Techniques
- Attention Is All You Need
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Language Models are Few-Shot Learners
- Training language models to follow instructions with human feedback
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- The Power of Scale for Parameter-Efficient Prompt Tuning
- Prefix-Tuning: Optimizing Continuous Prompts for Generation
- LoRA: Low-Rank Adaptation of Large Language Models
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- Language Models are Unsupervised Multitask Learners
- QLoRA: Efficient Finetuning of Quantized LLMs
- Improving Language Understanding by Generative Pre-Training
- ReAct: Synergizing Reasoning and Acting in Language Models
- Measuring Massive Multitask Language Understanding
- Finetuned Language Models Are Zero-Shot Learners
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
- Constitutional AI: Harmlessness from AI Feedback
- Scaling Laws for Neural Language Models
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Fast Decoding from Language Models with Speculative Sampling
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Parameter-Efficient Transfer Learning for NLP
-
🛠️ Popular Open-Source Libraries for LLM Development
- Sentence Transformers
- LangChain - step workflows | RAG, agentic reasoning, data preprocessing |
- DeepSpeed - scale models | Distributed training, memory optimization, pipeline parallelism |
- FastMoE - of-Experts (MoE) models based on PyTorch | Transfer Transformer models to MoE models, data parallelism, model parallelism |
- Ollama - sensitive apps, local development |
- OpenLLM - prem hosting |
- DeepEval
- RAGAS
-
📋 Summary of Language-Enhanced Datasets
- KITTI
- Talk2Car - vehicle interaction. |
- SUTD-TrafficQA
- MAPLM - tuning LLMs and VLMs and vision QA tasks. |
- Driving QA - making. |
- BDD-X - to-end driving through visual question answering. |
- NuScenes-QA - to-end autonomous driving systems. |
- DriveBench - modal understanding for autonomous driving. |
- VLAAD
- Argoverse 2
- TrafficSafety-2K - tuning for safety situational awareness. |
- NuPrompt - centric language prompt set for 3D driving scenes | Prompt-based driving task to predict the described object trajectory. |
- LaMPilot
- CoVLA - Language-Action alignment (80+ hrs driving videos) | Trajectory planning with natural language maneuver descriptions. |
- CrashLLM - if causal analysis for traffic safety using 19k crash reports. |
- TransportBench - level transportation engineering problem | Benchmarking LLMs on planning, design, management, and control questions. |
- DrivingDojo - agent interplay, and driving knowledge | Training and action instruction following benchmark for driving world models. |
- TransportationGames - related tasks. |
- TUMTraffic-VideoQA - choice video question answering. |
- V2V-QA - related questions. |
-
📄 Representative Surveys on LLMs
- A survey of Large Language Models - training, evaluation, and benchmarks. |
- Instruction Tuning for Large Language Models: A Survey
- Towards Reasoning in Large Language Models: A Survey
- A Survey on In-context Learning
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Large Language Models: A Survey
- A Survey of LLM Surveys
-
📚 Papers by Category
- MagicDrive: Street view generation with diverse 3D geometry control - uiuc.github.io/magicdrive.github.io/)
- GAIA-1: A generative world model for autonomous driving - gaia1/)
- DriveGPT4: Interpretable end-to-end autonomous driving via large language model
- GPT-Driver: Learning to drive with gpt - Driver)
- LanguageMPC: Large language models as decision makers for autonomous driving - mpc)
- Eureka: Human-level reward design via coding large language models - rl.github.io/)
- Large language models are zero-shot time series forecasters
- On the road with GPT-4V(ision): Early explorations of visual-language model on autonomous driving - ADG/GPT4V-AD-Exploration)
- Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving
- DriveLM: Driving with graph visual question answering
- Language conditioned traffic generation - Gen)
- RAG-Driver: Generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model - Yuan/RAG-Driver)
- AccidentGPT: Accident analysis and prevention from V2X environmental perception with multi-modal large model
- DriveDreamer-2: LLM-enhanced world models for diverse driving video generation - g/DriveDreamer-2)
- DriveMM: All-in-one large multimodal model for autonomous driving
- TP-GPT: Real-time data informed intelligent chatbot for transportation surveillance and management
- ChatSUMO: Large language model for automating traffic scenario generation in simulation of urban mobility - IV 2024]**.
- ChatScene: Knowledge-enabled safety-critical scenario generation for autonomous vehicles
- Video-to-text pedestrian monitoring (VTPM): Leveraging computer vision and large language models for privacy-preserve pedestrian activity monitoring at intersections
- CrashLLM: Learning traffic crashes as language: Datasets, benchmarks, and what-if causal analyses
- TrafficGPT: Viewing, processing and interacting with traffic foundation models
- Large language models in analyzing crash narratives—a comparative study of chatGPT, BARD and GPT-4
- A large language model framework to uncover underreporting in traffic crashes
- When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis - unsafe/SeeUnsafe)
- Using multimodal large language models (MLLMs) for automated detection of traffic safety-critical events
- Enhancing vision-language models with scene graphs for traffic accident understanding
- TransGPT: Multi-modal generative pre-trained transformer for transportation
- TrafficSafetyGPT: Tuning a pre-trained large language model to a domain-specific expert in transportation safety
- TARGET: Automated scenario generation from traffic rules for testing autonomous vehicles
- IncidentResponseGPT: Generating traffic incident response plans with generative artificial intelligence
- Harnessing multimodal large language models for traffic knowledge graph generation and decision-making
- Geolocation representation from large language models are generic enhancers for spatio-temporal learning
- Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approach
- ALT-Pilot: Autonomous navigation with language augmented topometric maps
- Large language models powered context-aware motion prediction - DISCOVER/LLM-Augmented-MTR)
- Classifying pedestrian maneuver types using the advanced language model
- AutoReward: Closed-loop reward design with large language models for autonomous driving - IV 2024]**.
- Large language model-enhanced reinforcement learning for generic bus holding control strategies
- Can chatgpt enable its? The case of mixed traffic control via reinforcement learning
- CRITICAL: Enhancing autonomous vehicle training with language model integration and critical scenario generation
- iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement - Alpha/iLLM-TSC)
- DrPlanner: Diagnosis and repair of motion planners for automated vehicles using large language models
- Large language models as traffic signal control agents: Capacity and opportunity
- COMAL: Collaborative multi-agent large language models for mixed-autonomy traffic - Yao/CoMAL)
- TPLLM: A traffic prediction framework based on pretrained large language models
- Spatial-temporal large language model for traffic prediction - HNU/ST-LLM)
- MobilityGPT: Enhanced human mobility modeling with a GPT model
- A universal model for human mobility prediction
- TrafficGPT: Viewing, processing and interacting with traffic foundation models
- A large language model framework to uncover underreporting in traffic crashes
- Harnessing multimodal large language models for traffic knowledge graph generation and decision-making
- Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approach
- Large language model-enhanced reinforcement learning for generic bus holding control strategies
- ChatGPT as your vehicle Co-pilot: An initial attempt - IV 2023]**.
-
⭐ Overview of Mainstream LLMs
Programming Languages
Categories
Sub Categories
Keywords
llm
5
machine-learning
3
deep-learning
3
large-language-models
3
natural-language-processing
3
pytorch
2
computer-vision
2
llmops
2
chain-of-thought
2
instruction-tuning
2
in-context-learning
2
open-source-llm
1
openllm
1
vicuna
1
autonomous-cars
1
autonomous-vehicles
1
car-driving
1
datasets
1
chatgpt
1
nlp
1
numpy
1
pandas
1
speech
1
tensorflow
1
instruction-following
1
large-vision-language-model
1
pre-trained-language-models
1
pre-training
1
rlhf
1
gnn
1
paper-list
1
bentoml
1
fine-tuning
1
llama
1
llama2
1
llama3-1
1
llama3-2
1
llama3-2-vision
1
llm-inference
1
llm-ops
1
llm-serving
1
llms
1
mistral
1
mlops
1
model-inference
1
large-vision-language-models
1
video-reasoning
1
vqa
1
vqa-dataset
1
autonomous-driving
1