CVPR 2024 accepted papers on Large language models
25 of the 2,716 papers accepted at CVPR 2024 (0.9%) are on Large language models, compared with 0.3% at CVPR 2023. They fall into 6 topics.
See CVPR 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Language, safety and interpretability · 8 papers
- LLMs are Good Sign Language Translators (70 citations)
- LLaFS: When Large Language Models Meet Few-Shot Segmentation (50 citations)
- LLMs are Good Action Recognizers (44 citations)
- Language Models as Black-Box Optimizers for Vision-Language Models (22 citations)
- LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model (19 citations)
- Link-Context Learning for Multimodal LLMs (7 citations)
- DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model (4 citations)
- Generating Illustrated Instructions (3 citations)
Agents, code and math · 7 papers
- LMDrive: Closed-Loop End-to-End Driving with Large Language Models (167 citations)
- ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles (79 citations)
- LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs (48 citations)
- Driving Everywhere with Large Language Model Policy Adaptation (35 citations)
- AvatarGPT: All-in-One Framework for Motion Understanding Planning Generation and Beyond (24 citations)
- CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update (12 citations)
- E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator (10 citations)
Retrieval and knowledge · 4 papers
- OpenEQA: Embodied Question Answering in the Era of Foundation Models (72 citations)
- CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering (7 citations)
- SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge (7 citations)
- Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA (7 citations)
Instruction and fine-tuning · 3 papers
Reasoning and chain of thought · 2 papers
Alignment and preferences · 1 paper
- Diffusion Model Alignment Using Direct Preference Optimization (154 citations)