Latest Research
Auto-Encoding Morph-Tokens for Multimodal LLM
For multimodal LLMs, the synergy of visual comprehension (textual output) and generation (visual output) presents an ongoing challenge.
Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models
We introduce Vibe-Eval: a new open benchmark and framework for evaluating multimodal chat models.
Neural Context Flows for Learning Generalizable Dynamical Systems
Neural Ordinary Differential Equations typically struggle to generalize to new dynamical behaviors created by parameter changes in the underlying system, even when the dynamics are close to previously seen behaviors.
An Attention Based Pipeline for Identifying Pre-Cancer Lesions in Head and Neck Clinical Images
Early detection of cancer can help improve patient prognosis by early intervention.
On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?
Additionally, our method does not rely on ad hoc rules (e. g., confidence threshold) used in some previous test-time augmentation techniques to filter the augmented views.
Multi-level projection with exponential parallel speedup; Application to sparse auto-encoders neural networks
In this paper, we propose a new bi-level projection method for which we show that the time complexity for the $\ell_{1,\infty}$ norm is only $\mathcal{O}\big(n m \big)$ for a matrix in $\mathbb{R}^{n\times m}$, and $\mathcal{O}\big(n + m \big)$ with full parallel power.
TOPICAL: TOPIC Pages AutomagicaLly
Topic pages aggregate useful information about an entity or concept into a single succinct and accessible article.
Probablistic Restoration with Adaptive Noise Sampling for 3D Human Pose Estimation
The accuracy and robustness of 3D human pose estimation (HPE) are limited by 2D pose detection errors and 2D to 3D ill-posed challenges, which have drawn great attention to Multi-Hypothesis HPE research.
Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection
The success of knowledge distillation mainly relies on how to keep the feature discrepancy between the teacher and student model, in which it assumes that: (1) the teacher model can jointly represent two different distributions for the normal and abnormal patterns, while (2) the student model can only reconstruct the normal distribution.
Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations
In addition, we further take multiple zoomed observations to explore self-supervised RefSR, and present a progressive fusion scheme for the effective utilization of reference images.
