The Research Desk.

The most upvoted and starred AI research crossing the community today.

Last Updated: Mar 19, 2026, 8:07 AM PT

AlphaXiv Trending

Mixture-of-Depths Attention
AlphaXiv
76

Mixture-of-Depths Attention

Lianghui Zhu, Yuxin Fang, Bencheng Liao

#alphaxiv
Mamba-3: Improved Sequence Modeling using State Space Principles
AlphaXiv
70

Mamba-3: Improved Sequence Modeling using State Space Principles

Aakash Lahoti, Kevin Y. Li, Berlin Chen

#alphaxiv
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
AlphaXiv
64

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Universidad de Zaragoza, Matthew Muckley, Amir Bar

#computer-vision#alphaxiv
Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
AlphaXiv
36

Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science

Emmanuel Dupoux, Yann LeCun, Jitendra Malik

#robotics#alphaxiv

HuggingFace Daily Papers

Video-CoE: Reinforcing Video Event Prediction via Chain of Events
HuggingFace
80

Video-CoE: Reinforcing Video Event Prediction via Chain of Events

Qile Su, Jing Tang, Rui Chen +2 more

#computer-vision
Alignment Makes Language Models Normative, Not Descriptive
HuggingFace
31

Alignment Makes Language Models Normative, Not Descriptive

Eilam Shapira, Moshe Tennenholtz, Roi Reichart

#nlp#safety-alignment
GigaWorld-Policy: An Efficient Action-Centered World--Action Model
HuggingFace
18

GigaWorld-Policy: An Efficient Action-Centered World--Action Model

Angen Ye, Boyuan Wang, Chaojun Ni +2 more

#reinforcement-learning#efficiency#open-gigaai
ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models
HuggingFace
2

ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language Models

M. Arda Aydın, Melih B. Yilmaz, Aykut Koç +1 more

#nlp#computer-vision#efficiency#icon-lab
FINER: MLLMs Hallucinate under Fine-grained Negative Queries
HuggingFace
2

FINER: MLLMs Hallucinate under Fine-grained Negative Queries

Rui Xiao, Sanghwan Kim, Yongqin Xian +2 more

#nlp#ExplainableML
HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models
HuggingFace
1

HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language Models

Md Jahidul Islam

#nlp#computer-vision#multimodal#Jahid12012021