Latest Research in Artificial Intelligence
129 research papers · 2026 median publication year
Top Research Topics in Artificial Intelligence
- Computer Vision and Pattern Recognition — 96 papers
- Artificial Intelligence — 8 papers
- Machine Learning — 6 papers
- Generative Adversarial Networks and Image Synthesis — 3 papers
- Graphics — 3 papers
- Constraint Satisfaction and Optimization — 3 papers
- Advanced Neural Network Applications — 2 papers
- Computation and Language — 2 papers
- Multimodal Machine Learning Applications — 2 papers
- Software System Performance and Reliability — 1 papers
Highest-Cited Papers
- Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
- CoMa: Contextual Massing Generation with Vision-Language Models
- UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
- Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis
- MSR: Multiple Subject Reference for Video Generation
- Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM
- DR.WILSS: Diffusion-Based Replay for Weakly Supervised Continual Semantic Segmentation
- Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation
- SlotDiT: Object-Centric Representations for Diffusion Transformers
- EdiTikZ: Scientific Figure Editing from Revision Trajectories
- PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection
- Prompt Engineering in the Segment Anything Model: Methodologies, Applications, and Emerging Challenges
- Bridging Text and Motion: Generative AI Models for Video Synthesis
- Does Attention-Guided Masking Really Help Object Discovery in Object-Centric Learning?
- WithEveryone: Unified Planning and Identity Grounding for Group Image Generation
- ViCo-SAM3: Vision-Conditioned Alignment for Open-Vocabulary Camouflaged Object Segmentation
- A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models
- DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Counting
- Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
- Adapting Open-Weight MLLMs to Generate Point Prompts for Electron Microscopy Segmentation