Deep Learning
Recurrent neural network dynamical systems for biological vision
To address this, we introduce a hybrid architecture that integrates the continuous-time recurrent dynamics of RNNs with the spatial processing capabilities of CNNs.
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
The current paradigm of evaluating Large Language Models (LLMs) through static benchmarks comes with significant limitations, such as vulnerability to data contamination and a lack of adaptability to the evolving capabilities of LLMs.
UniIF: Unified Molecule Inverse Folding Zhangyang Gao
Molecule inverse folding has been a long-standing challenge in chemistry and biology, with the potential to revolutionize drug discovery and material science.
A Concept-Based Explainability Framework for Large Multimodal Models
Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks.
AirSketch: Generative Motion to Sketch Hui Xian Grace Lim
Illustration is a fundamental mode of human expression and communication.
CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
However, the complexity and duration of procedural activities inherently increase the likelihood of making errors.
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
Transformers have demonstrated great power in the recent development of large foundational models.
