A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper revisits neural scaling laws for language and vision models, finding that scaling trends hold across modalities but with different exponents and saturation points.
D. Du, Gu Gong, Xiaowen Chu
A comprehensive survey of model quantization and hardware acceleration techniques for vision transformers.
Unknown
This paper integrates knowledge distillation with self-supervised contrastive learning to improve student model performance without requiring labeled data.
Unknown
MtLoRA introduces task-agnostic and task-specific low-rank adaptation modules for efficient multi-task learning in vision.
Baohao Liao, Hanze Dong, Christof Monz, et al.
ReOPD enables efficient multi-turn on-policy distillation for LLM agents by reusing teacher trajectories as replayed prefixes, avoiding costly environment interactions.
Haoru Tan, Wang Wang, Sitong Wu, et al.
Dataset Distillation by Influence Matching aligns the final outcome of training by learning a compact synthetic set whose effect on converged parameters matches that of the full dataset.
Korota Arsène Coulibaly, Mohamed Hamlich, Khalid Hmali, et al.
A synthetic data generation framework for rotogravure printing defects enables training object detectors to achieve 80.9% mAP on real samples, eliminating manual data collection.
Wenhao Li, Xueying Jiang, Quanhao Qian, et al.
VLM-IE3D enhances 3D spatial awareness of vision-language models by fusing implicit and explicit 3D geometries learned from RGB videos.
Hao Liang, Qihan Lin, Zhaoyang Han, et al.
Introduces K12-KGraph, a curriculum-aligned knowledge graph from Chinese textbooks, with benchmark and training data to improve LLMs' curriculum cognition.
Unknown
A survey and benchmark of parameter-efficient fine-tuning methods for pre-trained vision models.
Unknown
This paper empirically studies the design of vision Mixture-of-Experts (MoE) models, providing insights into routing strategies and expert architectures for improved scalability.
Unknown
This book provides a broad overview of synthetic data for deep learning, focusing on computer vision and future improvements.