researchPapers · 488k papers, semantic search, PageRank

Semantic search

Natural-language search across 488k abstracts. Powered by all-MiniLM-L6-v2 embeddings + cosine similarity over ClickHouse. Try: "papers about emergent capabilities" or "diffusion model training instability".

Research answer API

A demo of the monetizable data-app layer: users ask a high-value question, the backend calls a live Knowledgebase RAG domain, and the response returns cited evidence from high-citation OpenAlex Computer Science papers.

Hot right now

Recent papers combining citation velocity, peer-review signal where available, and graph centrality.

#
1	4.662	The Llama 3 Herd of Models	arxiv	8,241	16,065	—	2024
2	4.642	GPT-4 Technical Report	arxiv	7,657	25,157	—	2023
3	4.527	LLaMA: Open and Efficient Foundation Language Models	arxiv	6,043	20,316	—	2023
4	4.500	Llama 2: Open Foundation and Fine-Tuned Chat Models	arxiv	5,841	17,238	—	2023
5	4.346	Segment Anything	arxiv	4,344	13,904	—	2023
6	4.263	DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning	arxiv	3,713	5,368	—	2025
7	4.169	Visual Instruction Tuning	arxiv	3,062	9,800	—	2023
8	4.157	Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena	arxiv	3,006	9,120	—	2023
9	4.148	Mamba: Linear-Time Sequence Modeling with Selective State Spaces	arxiv	2,954	7,482	—	2023
10	4.145	Direct Preference Optimization: Your Language Model is Secretly a Reward Model	arxiv	2,928	9,132	—	2023
11	4.106	DINOv2: Learning Robust Visual Features without Supervision	arxiv	2,696	8,629	—	2023
12	4.045	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models	arxiv	2,391	8,241	—	2023
13	3.911	SAM 2: Segment Anything in Images and Videos	arxiv	1,836	3,424	—	2024
14	3.857	SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis	arxiv	1,645	4,855	—	2023
15	3.848	YOLOv11: An Overview of the Key Architectural Enhancements	arxiv	1,622	2,753	—	2024
16	3.846	Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context	arxiv	1,614	3,686	—	2024
17	3.773	A Survey of Large Language Models	arxiv	1,384	4,548	—	2026
18	3.766	Generative Agents: Interactive Simulacra of Human Behavior	arxiv	1,374	4,398	—	2023
19	3.764	Retrieval-Augmented Generation for Large Language Models: A Survey	arxiv	1,365	3,457	—	2023
20	3.760	Tree of Thoughts: Deliberate Problem Solving with Large Language Models	arxiv	1,353	4,219	—	2023

100 rows

Page 1 of 5

Reviewer-loved early work

High OpenReview scores on recent submissions. Citation counts for OpenReview-only records are hidden until a verified citation crosswalk is added.

#
1	Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport	ICLR-2025	10.00	4	Accepted oral
2	Safety Alignment Should be Made More Than Just a Few Tokens Deep	ICLR-2025	9.50	4	Accepted oral
3	Simplifying, Stabilizing and Scaling Continuous-time Consistency Models	ICLR-2025	9.20	5	Accepted oral
4	SAM 2: Segment Anything in Images and Videos	ICLR-2025	9.00	4	Accepted oral
5	Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models	ICLR-2025	9.00	4	Accepted oral
6	Artificial Kuramoto Oscillatory Neurons	ICLR-2025	9.00	4	Accepted oral
7	Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think	ICLR-2025	9.00	6	Accepted oral
8	Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning	ICLR-2025	9.00	4	Accepted oral
9	BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions	ICLR-2025	9.00	4	Accepted oral
10	Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering	NeurIPS-2024	8.75	4	Accepted oral
11	Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport	ICLR-2025	8.67	3	Accepted oral
12	Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models	ICLR-2025	8.67	3	Accepted oral
13	Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment	ICLR-2025	8.67	3	Accepted oral
14	OLMoE: Open Mixture-of-Experts Language Models	ICLR-2025	8.67	3	Accepted oral
15	Transformers Provably Solve Parity Efficiently with Chain of Thought	ICLR-2025	8.67	3	Accepted oral
16	LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization	ICLR-2025	8.67	3	Accepted oral
17	Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs	ICLR-2025	8.50	4	Accepted oral
18	Cut Your Losses in Large-Vocabulary Language Models	ICLR-2025	8.50	4	Accepted oral
19	SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers	ICLR-2025	8.50	4	Accepted oral
20	TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation	ICLR-2025	8.50	4	Accepted oral

100 rows

Page 1 of 5

Topics reviewers are most excited about

Mean reviewer rating by extracted topic. This is the compact view of what top venues are rewarding.

#
1	6.74	7.40	10
2	6.45	7.50	13
3	6.30	7.00	12
4	6.29	6.96	13
5	6.28	7.22	12
6	6.27	7.40	13
7	6.26	7.27	13
8	6.24	7.22	12
9	6.24	7.60	10
10	6.23	7.93	12
11	6.23	6.74	12
12	6.22	7.00	11
13	6.22	7.64	10
14	6.21	6.95	13
15	6.20	7.30	15
16	6.20	7.50	10
17	6.20	7.35	13
18	6.18	6.90	13
19	6.18	8.00	19
20	6.18	7.55	10

100 rows

Page 1 of 5

Research map

Semantic clusters from MiniLM embeddings. Use this as the one map of the corpus, not a separate diagnostics area.

Top papers

The strongest papers in the corpus by citations and graph centrality.

#
1	1003.0358	Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition Handwritten Text Recognition Techniques Computer Vision and Pattern Recognition Computer Science	1,015	95	0.007159	0.0141
2	1207.0580	Improving neural networks by preventing co-adaptation of feature detectors Neural Networks and Applications Artificial Intelligence Computer Science	8,008	890	0.007054	0.1107
3	1409.1556	Very Deep Convolutional Networks for Large-Scale Image Recognition Advanced Vision and Imaging Computer Vision and Pattern Recognition Computer Science	111,966	7,817	0.005091	0.3442
4	1412.6980	Adam: A Method for Stochastic Optimization Stochastic Gradient Optimization Techniques Artificial Intelligence Computer Science	167,125	10,161	0.004405	0.4239
5	1212.5701	ADADELTA: An Adaptive Learning Rate Method Neural Networks and Applications Artificial Intelligence Computer Science	6,859	1,074	0.003272	0.0880
6	1308.0850	Generating Sequences With Recurrent Neural Networks Handwritten Text Recognition Techniques Computer Vision and Pattern Recognition Computer Science	4,301	711	0.003113	0.0978
7	1312.4659	DeepPose: Human Pose Estimation via Deep Neural Networks Human Pose and Action Recognition Computer Vision and Pattern Recognition Computer Science	3,066	415	0.002682	0.0305
8	1409.4842	Going Deeper with Convolutions Advanced Neural Network Applications Computer Vision and Pattern Recognition Computer Science	47,388	556	0.002291	0.0915
9	1408.5093	Caffe: Convolutional Architecture for Fast Feature Embedding Advanced Image and Video Retrieval Techniques Computer Vision and Pattern Recognition Computer Science	14,860	1,347	0.001966	0.0976
10	1311.2901	Visualizing and Understanding Convolutional Networks Explainable Artificial Intelligence (XAI) Artificial Intelligence Computer Science	17,093	147	0.001851	0.0409
11	1211.3711	Sequence Transduction with Recurrent Neural Networks Natural Language Processing Techniques Artificial Intelligence Computer Science	2,095	414	0.001819	0.0259
12	1311.5591	PANDA: Pose Aligned Networks for Deep Attribute Modeling Human Pose and Action Recognition Computer Vision and Pattern Recognition Computer Science	23	18	0.001785	0.0076
13	1409.3215	Sequence to Sequence Learning with Neural Networks Natural Language Processing Techniques Artificial Intelligence Computer Science	22,087	2,142	0.001762	0.1101
14	1102.1523	The NumPy array: a structure for efficient numerical computation Parallel Computing and Optimization Techniques Hardware and Architecture Computer Science	7,398	270	0.001686	0.0152
15	1201.0490	Scikit-learn: Machine Learning in Python Computational Physics and Python Applications Artificial Intelligence Computer Science	90,087	2,420	0.001647	0.0812
16	1103.0398	Natural Language Processing (almost) from Scratch Topic Modeling Artificial Intelligence Computer Science	7,913	772	0.001454	0.0453
17	1108.3298	A Machine Learning Perspective on Predictive Coding with PAQ Algorithms and Data Compression Artificial Intelligence Computer Science	1	1	0.001324	0.0054
18	1211.5590	Theano: new features and speed improvements Parallel Computing and Optimization Techniques Hardware and Architecture Computer Science	1,412	222	0.001263	0.0308
19	1406.4729	Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition Advanced Neural Network Applications Computer Vision and Pattern Recognition Computer Science	12,567	406	0.001218	0.0518
20	1502.03167	Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Neural Networks and Applications Artificial Intelligence Computer Science	46,926	2,519	0.001202	0.1169

200 rows

Page 1 of 10

What the field cites

Works most cited by the corpus, useful as a compact reading list of durable foundations.

#
1	Deep Residual Learning for Image Recognition	2016	19,503	220,705	Advanced Neural Network Applications
2	Adam: A Method for Stochastic Optimization	2014	10,161	84,666	Stochastic Gradient Optimization Techniques
3	Very Deep Convolutional Networks for Large-Scale Image Recognition	2014	7,817	75,505	Advanced Vision and Imaging
4	Long Short-Term Memory	1997	7,733	97,142	Neural Networks and Applications
5	ImageNet: A large-scale hierarchical image database	2009	7,406	61,533	Advanced Image and Video Retrieval Techniques
6	GAN（Generative Adversarial Nets）	2017	6,347	21,795	Generative Adversarial Networks and Image Synthesis
7	ImageNet classification with deep convolutional neural networks	2017	6,136	75,677	Advanced Neural Network Applications
8	Learning Multiple Layers of Features from Tiny Images	2024	5,729	25,472	Generative Adversarial Networks and Image Synthesis
9	Gradient-based learning applied to document recognition	1998	5,707	57,866	Handwritten Text Recognition Techniques
10	ImageNet Large Scale Visual Recognition Challenge	2015	5,379	40,076	Advanced Image and Video Retrieval Techniques
11	Glove: Global Vectors for Word Representation	2014	5,192	33,633	Topic Modeling
12	<i>Quantum Computation and Quantum Information</i>	2002	4,528	22,727	Quantum Mechanics and Applications
13	Microsoft COCO: Common Objects in Context	2014	4,506	41,960	Advanced Neural Network Applications
14	U-Net: Convolutional Networks for Biomedical Image Segmentation	2015	4,237	88,304	Cell Image Analysis Techniques
15	Dropout: a simple way to prevent neural networks from overfitting	2014	3,866	34,247	Machine Learning and Data Classification
16	Going deeper with convolutions	2015	3,843	46,713	Advanced Neural Network Applications
17	Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift	2024	3,658	15,691	Domain Adaptation and Few-Shot Learning
18	Fully convolutional networks for semantic segmentation	2015	3,388	36,774	Advanced Neural Network Applications
19	Visualizing Data using t-SNE	2008	3,261	35,713	Data Visualization and Analytics
20	Quantum computation and quantum information	2001	3,238	19,241	Quantum Mechanics and Applications

200 rows

Page 1 of 10