rleak.com

Research Leak • Alpha Signals

Spot the Future of AI Research

Track citation trends and discover emerging breakthroughs before they go mainstream

Papers from 2024 onwardsBeta - Some data may be inaccurateSuggestions & Feedback

Cut Through the Noise

Find papers actually getting cited, not just published

Alpha Signal

Spot Emerging Trends

Track citation velocity to find rising research early

Topic Lifecycle Analysis

See research areas rising, peaking, or declining

Browse by Conference

CVPR, NeurIPS, ICLR, ICML, ECCV, ICCV, COLM

ICLRICMLNEURIPSCVPR

Browse by Topic

Diffusion, Transformers, 3D Vision, LLMs

diffusion modelsvision-language models3d gaussian splattingmultimodal large language models

Browse by Author

Top researchers ranked by citations

View top 100 by citation count

📋 Rankings (Countries, Institutions)📚 Browse All Papers

🏅

2025 Conference Highlights

Latest

CVPR 2025

Top 30

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

917 citations

VGGT: Visual Geometry Grounded Transformer

612 citations

Structured 3D Latents for Scalable and Versatile 3D Generation

434 citations

Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces

371 citations

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

293 citations

OmniGen: Unified Image Generation

271 citations

MambaVision: A Hybrid Mamba-Transformer Vision Backbone

264 citations

Continuous 3D Perception Model with Persistent State

250 citations

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

245 citations

Infinity∞: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

201 citations

MambaOut: Do We Really Need Mamba for Vision?

193 citations

Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

184 citations

Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

180 citations

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

164 citations

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

164 citations

MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

162 citations

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

158 citations

NVILA: Efficient Frontier Visual Language Models

157 citations

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

156 citations

Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding

155 citations

Navigation World Models

151 citations

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

149 citations

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

144 citations

MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos

136 citations

AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea

135 citations

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

131 citations

DepthSplat: Connecting Gaussian Splatting and Depth

131 citations

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

128 citations

WonderWorld: Interactive 3D Scene Generation from a Single Image

128 citations

MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds

124 citations

ICCV 2025

Top 30

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

360 citations

Visual-RFT: Visual Reinforcement Fine-Tuning

357 citations

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

265 citations

NEURIPS 2025

Top 30

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

1,277 citations

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

1,213 citations

YOLOv12: Attention-Centric Real-Time Object Detectors

938 citations

ICML 2025

Top 30

WorldSimBench: Towards Video Generation Models as World Simulators

842 citations

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

442 citations

From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline

357 citations

ICLR 2025

Top 30

SAM 2: Segment Anything in Images and Videos

2,393 citations

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

2,226 citations

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

1,409 citations

〰️

Topic Trends

Research topic lifecycle

View all topics →

Large Language Models

5148 papers · Language Models

Mar '24 — Feb '264243 papers

Representation Learning

4782 papers · Representation Learning

Mar '24 — Feb '263765 papers

Vision Transformers

4105 papers · Architectures

Mar '24 — Feb '263338 papers

Language Modeling

3637 papers · Language Models

Mar '24 — Feb '262909 papers

Diffusion Models

3332 papers · Generative Models

Mar '24 — Feb '262631 papers

Vision-Language Models

3239 papers · Multimodal

Mar '24 — Feb '262641 papers

Compare Topic Trends

Compare research momentum across topics side-by-side

Compare

📜

Most Cited

Improved Baselines with Visual Instruction Tuning

Haotian Liu, Chunyuan Li, Yuheng Li et al.

CVPR 2024

4,359

citations

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Dustin Podell, Zion English, Kyle Lacey et al.

ICLR 2024

3,991

citations

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Shilong Liu, Zhaoyang Zeng, Tianhe Ren et al.

ECCV 2024

3,442

citations

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao

ECCV 2024

3,033

citations

Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

Patrick Esser, Sumith Kulal, Andreas Blattmann et al.

ICML 2024

2,966

citations

MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Deyao Zhu, jun chen, Xiaoqian Shen et al.

ICLR 2024

2,806

citations

DETRs Beat YOLOs on Real-time Object Detection

Yian Zhao, Wenyu Lv, Shangliang Xu et al.

CVPR 2024

2,565

citations

Let's Verify Step by Step

Hunter Lightman, Vineet Kosaraju, Yuri Burda et al.

ICLR 2024

2,488

citations

SAM 2: Segment Anything in Images and Videos

Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu et al.

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Zhe Chen, Jiannan Wu, Wenhai Wang et al.

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Clemencia Siro, Guy Gur-Ari, Gaurav Mishra et al.

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Tri Dao

MMBENCH: Is Your Multi-Modal Model an All-around Player?

Yuan Liu, Haodong Duan, Yuanhan Zhang et al.

MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI

Xiang Yue, Yuansheng Ni, Kai Zhang et al.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Carlos E Jimenez, John Yang, Alexander Wettig et al.

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Lihe Yang, Bingyi Kang, Zilong Huang et al.

T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion

Chong Mou, Xintao Wang, Liangbin Xie et al.

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Lianghui Zhu, Bencheng Liao, Qian Zhang et al.

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Akari Asai, Zeqiu Wu, Yizhong Wang et al.

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Zhuoyi Yang, Jiayan Teng, Wendi Zheng et al.

Top Authors