← Core AI
Artificial Intelligence › Core AI ›

Foundation Models

4845 directly classified papers

Papers per year

Papers

CODA: Repurposing Continuous VAEs for Discrete Tokenization ICCV 2025
All in One: Visual-Description-Guided Unified Point Cloud Segmentation ICCV 2025
Leveraging Debiased Cross-modal Attention Maps and Code-based Reasoning for Zero-shot Referring Expression Comprehension ICCV 2025
UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence ICCV 2025
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams ICCV 2025
INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance ICCV 2025
ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models ICCV 2025
Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning ICCV 2025
Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling ICCV 2025
Rethinking DPO-style Diffusion Aligning Frameworks ICCV 2025
HPSv3: Towards Wide-Spectrum Human Preference Score ICCV 2025
CAT: A Unified Click-and-Track Framework for Realistic Tracking ICCV 2025
Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection ICCV 2025
LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes ICCV 2025
Knowledge Transfer from Interaction Learning ICCV 2025
Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection ICCV 2025
Hierarchical Divide-and-Conquer Grouping for Classification Adaptation of Pre-Trained Models ICCV 2025
LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation AAAI 2025
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data AAAI 2025
Towards S²-Challenges Underlying LLM-Based Augmentation for Personalized News Recommendation AAAI 2025
Integrating Large Language Models and Möbius Group Transformations for Temporal Knowledge Graph Embedding on the Riemann Sphere AAAI 2025
Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation AAAI 2025
STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis AAAI 2025
QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language Models AAAI 2025
Design Principle Transfer in Neural Architecture Search via Large Language Models AAAI 2025