CVPR 2025 accepted papers on Large language models
37 of the 2,871 papers accepted at CVPR 2025 (1.3%) are on Large language models, compared with 0.9% at CVPR 2024. They fall into 6 topics.
See CVPR 2025 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
Agents, code and math · 16 papers
- Distilling Multi-modal Large Language Models for Autonomous Driving (19 citations)
- 3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination (11 citations)
- EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark (11 citations)
- SketchAgent: Language-Driven Sequential Sketch Generation (10 citations)
- BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing (6 citations)
- Scene Map-based Prompt Tuning for Navigation Instruction Generation (6 citations)
- Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation (4 citations)
- GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill (4 citations)
- PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation (4 citations)
- ChatHuman: Chatting about 3D Humans with Tools (3 citations)
- CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation (3 citations)
- GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation (2 citations)
and 4 more in the interactive map.
Language, safety and interpretability · 15 papers
- CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation (29 citations)
- Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues (13 citations)
- Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy (10 citations)
- FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Models (8 citations)
- Bridging Gait Recognition and Large Language Models Sequence Modeling (7 citations)
- The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation (7 citations)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (6 citations)
- A Simple yet Effective Layout Token in Large Language Models for Document Understanding (5 citations)
- FSboard: Over 3 Million Characters of ASL Fingerspelling Collected via Smartphones (5 citations)
- EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions (4 citations)
- CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model (3 citations)
- Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction (3 citations)
and 3 more in the interactive map.
Instruction and fine-tuning · 3 papers
- CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset (20 citations)
- Empowering LLMs to Understand and Generate Complex Vector Graphics (10 citations)
- LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs (2 citations)