Loading the SOTA2 catalog…
SOTA2 Research · papers
Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.
| arxiv 2510.06820 |
| Weak-to-Strong Knowledge Distillation Accelerates Visual Learning | Baiang Li, Wenhao Chai, Felix Heide | 2026 | arxiv 2604.15451 |
|---|
| Good Scores, Bad Data: A Metric for Multimodal Coherence | Vasundra Srinivasan | 2026 | arxiv 2603.25924 |
|---|
| Learnable Instance Attention Filtering for Adaptive Detector Distillation | Chen Liu, Qizhen Lan, Zhicheng Ding | 2026 | arxiv 2603.26088 |
|---|
| Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration | Mingtao Xian, Yifeng Yang, Qinying Gu | 2026 | arxiv 2605.11591 |
|---|
| Scaling Pre-training to One Hundred Billion Data for Vision Language Models | Xiao Wang, Ibrahim Alabdulmohsin, Daniel Salz | 2025 | arxiv 2502.07617 |
|---|
| MicroViTv2: Beyond the FLOPS for Edge Energy-Friendly Vision Transformers | Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu | 2026 | arxiv 2605.10148 |
|---|
| Repurposing CLIP to Localize at Pixel Level | Jiaxiang Fang, Shiqiang Ma, Jing Wang | 2026 | arxiv 2607.05253 |
|---|
| SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learning | Nikos Giakoumoglou, Tania Stathaki | 2024 | arxiv 2410.02401 |
|---|
| Boosting Few-shot Semantic Segmentation with Transformers | Guolei Sun, Yun Liu, Jingyun Liang | 2021 | arxiv 2108.02266 |
|---|
| ViT Cane: Visual Assistant for the Visually Impaired | Bhavesh Kumar | 2021 | arxiv 2109.13857 |
|---|