Awesome Papers
Curated collections of academic research across 17 domains — continuously updated, ranked by community signal, and explained.
Research Collections
Large Language ModelsLLM
Scholarly research on large language models: GPT, transformers, prompting, fine-tuning, multimodal AI, and NLP.
Quantum ComputingQC
Quantum algorithms, quantum ML, error correction, quantum supremacy, VQE, and foundational quantum theory.
Similarity SearchSimSearch
Learning-based hashing methods, approximate nearest neighbour search, LSH, deep hashing, and binary embeddings.
AI for CodeAI4Code
AI-assisted software engineering: code generation, program synthesis, code completion, code search, and LLM tools.
AI AgentsAgents
Autonomous agents, tool use, multi-agent systems, planning, orchestration, and agent safety.
Computer VisionCV
Object detection, segmentation, image generation, 3D vision, video understanding, and visual models.
RoboticsRobotics
Robot learning, manipulation, navigation, sim-to-real, embodied AI, humanoids, and drones.
CybersecurityCyber
AI for threat detection, adversarial ML, LLM security, privacy, vulnerability analysis, and red teaming.
AI for ScienceSci
Drug discovery, protein folding, materials science, climate modeling, physics ML, and genomics.
Speech & AudioAudio
Speech recognition, TTS, voice cloning, music generation, audio AI, and spoken language understanding.
Reinforcement LearningRL
Deep RL, RLHF, game AI, multi-agent RL, reward modeling, safe RL, and decision making.
MultimodalMM
Vision-language models, audio-text, cross-modal retrieval, multimodal foundation models, and unified architectures.
Generative ModelsGenAI
Diffusion models, GANs, VAEs, flow-based models, image/video/3D synthesis, and generative foundations.
Graph LearningGraph
Graph neural networks, graph transformers, knowledge graphs, message passing, and structured-data learning.
Time SeriesTS
Forecasting, anomaly detection, time-series foundation models, sequence modeling, and temporal reasoning.
Recommender SystemsRecSys
Collaborative filtering, sequential recommendation, ranking, LLM-based recommenders, and personalization.
Federated LearningFL
Federated learning, privacy-preserving ML, differential privacy, secure aggregation, and distributed training.