Loading leaderboard...

Weekly rankings

Good research deserves attention. Every week, we evaluate thousands of new preprints and surface the ones with the most signal. Read this week's recap or see statistics.

Jun 1 – Jun 7, 2026

Scores are calibrated so that around 70 marks a strong venue's acceptance bar. How scores work

#	Paper	Score
1	RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents Ameya Joshi et al.Computer Vision	82.2
2	GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines Jafar Isbarov et al.AI	80.2
3	vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models Khanh D. Nguyen et al.Robotics	79.8
4	ScaleDisturb: Exploiting Temporal Asymmetry to Amplify Read Disturbance in Modern DRAM Chips Jikun Wang et al.Computer Architecture	78.9
5	The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence Kelly McConvey et al.AI	78.3
6	The Windows IOCTL Census: A Corpus-Scale, Multi-Architecture Database of the Driver Control-Code Surface Michael J. Bommarito IIOperating Systems	77.4
7	Optimal Online Equitable Allocation with Indivisible Resources Ramiro N. Deo-Campo VuongOptimization	77.1
8	STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control Priyansh Bhatnagar et al.Machine Learning	76.8
9	Verifiable and Confidential DNN Inference on Low-End Edge Devices Mohamed Khalil Kiri et al.Machine Learning	76.5
10	Gated Bidirectional Linear Attention for Generative Retrieval Artem Matveev et al.Information Retrieval	76.1