Blog Promote Sign in Sign up

Catalogs

Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose papers

Use the summary to find relevant work, then read the original paper. Compare the method, evaluation setting, baselines and limitations with your own problem. Check whether code and datasets are available; a reported benchmark result may not transfer to your use case.

Understand our sources and data limits

  1. On two proofs of $d^2$ mixing of weighted Dikin walks taaft We study the mixing time of weighted Dikin walks for sampling from exponential distributions on pol… 2026-08-28 published
  2. On-device Panoptic Segmentation for Camera Using Transformers Apple Describes HyperDETR for panoptic segmentation in the Camera pipeline, emphasizing large-resolution… Apple
  3. On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rerankers taaft Compact instruction-following rerankers are attractive for deployment, but conventional distillatio… 2026-09-01 published
  4. On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios taaft While feed-forward 3D reconstruction (3R) offers efficient end-to-end modeling, its application in… 2026-09-01 published
  5. One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning taaft Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new cla… 2026-08-31 published
  6. One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation taaft Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint… 2026-09-04 published
  7. One Policy Is Enough: Single-Agent Reinforcement Learning Outperforms Tree Search for Chemistry Tool Learning taaft Chemistry questions often demand exact computation and database lookups that a language model canno… 2026-08-31 published
  8. One Prompt Is Enough: Watermark Laundering Through Foundation Image Models taaft Invisible watermarks are typically evaluated against predefined perturbations such as compression,… 2026-09-01 published
  9. One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context taaft We extend recent work establishing an equivalence between one-layer transformers and nearest-neighb… 2026-09-01 published
  10. Online Change-point Detection for Cooperative Multi-Agent Reinforcement Learning taaft Cooperative multi-agent reinforcement learning (MARL) systems rely on past experience for learning… 2026-09-04 published
  11. Online Estimation of Dynamic Origin-Destination Matrices Using Reinforcement Learning with Link-Flow Propagation Guidance taaft Online dynamic origin-destination (OD) matrix estimation (DODE) calibrates time-dependent OD demand… 2026-08-31 published
  12. Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling taaft Machine-learnt corrections can complement numerical weather prediction provided that they operate s… 2026-09-02 published
  13. Online Self-Weighted Fine-Tuning taaft Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonst… 2026-09-01 published
  14. Online Statistical Inference of Constant Sample-averaged Q-Learning taaft Reinforcement learning algorithms have been widely used for decision-making tasks in various domain… 2026-03-27 published
  15. Ontology-Guided Multi-Agent Extraction of Evaluation Objects from Academic Review Texts: Evidence from Chinese Library and Information Science taaft Academic reviews, scholarly commentaries, and book reviews serve as sources of evaluative statement… 2026-08-30 published
  16. OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification taaft Prototypical part-based models provide explainable predictions by comparing input regions to learne… 2026-08-30 published
  17. Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning taaft This paper studies the performance of open-source Large Language Models (LLMs) in text classificati… 2023-07-05 published
  18. OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization taaft Fine-grained Cross-View Localization (CVL) estimates the precise position and orientation of a grou… 2026-08-26 published
  19. openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents taaft Long-horizon coding agents operate over evolving repository states while increasingly relying on he… 2026-08-28 published
  20. OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis taaft Training deep research agents requires long-horizon trajectories that interleave search, evidence a… 2026-03-17 published
  21. OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories taaft Deep search capabilities have become an indispensable competency for frontier Large Language Model… 2026-05-05 published
  22. Operational Regimes in Non-Convex Optimization: A Multiplier-Based Taxonomy taaft This paper introduces a structural taxonomy for constrained non-convex optimization based on the si… 2026-08-31 published
  23. Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments taaft We present three large-scale studies of spoken parliamentary speech across four Slavic languages (C… 2026-08-31 published
  24. OPT: Open Pre-trained Transformer Language Models Meta Platforms Large language models, which are often trained for hundreds of thousands of compute days, have show… 2022-05-02 published
  25. OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes taaft Monocular depth estimation has achieved strong open-domain generalization, yet reliable robotic dep… 2026-08-30 published
  26. Optimal Rates for Agentic Networked Information Aggregation taaft Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregati… 2026-09-04 published
  27. Optimizer Memory Schedules for Outscaling the Overtraining Axis taaft We investigate how optimizers scale across the overtraining axis and show that relative optimizer p… 2026-09-04 published
  28. Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences taaft Machine learning models are widely integrated into modern mobile apps to analyze user behaviors and… 2026-03-23 published
  29. Optimizing On-Device Inference for Apple Silicon Perplexity Perplexity built Lily, a custom inference engine for Apple Silicon, to run Qwen3.6-35B-A3B more eff… Perplexity
  30. Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning taaft Translating Natural Language to SQL (NL2SQL) remains a critical bottleneck for democratization of d… 2026-03-24 published
  31. OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection taaft Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queri… 2026-08-31 published
  32. OR-Transformer: Scaling Real-Time Decision-Making to 1,000 Items taaft Modern supply chain operations can require coordinating replenishment across thousands of heterogen… 2026-09-01 published
  33. Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models taaft Knowledge graphs have become an important source of structured knowledge for Web applications, incl… 2026-09-02 published
  34. ORB-SVM : An Innovative Hybrid Framework for Efficient Brain Tumor Detection from MRI Scans taaft Brain cancer remains one of the most significant challenges in modern medicine, where the accuracy… 2026-09-02 published
  35. OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers taaft Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-… 2026-07-02 published
  36. Orca: Progressive Learning from Complex Explanation Traces of GPT-4 Microsoft Recent research has focused on enhancing the capability of smaller models through imitation learnin… 2023-06-05 published