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. JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents taaft Creative AI is moving from single-step asset generation toward long-horizon multimodal production.… 2026-07-26 published
  2. JAXBench: Benchmarking Autonomous TPU Kernel Optimization taaft Rigorous benchmarks have driven progress in autonomous GPU kernel performance optimization by estab… 2026-05-19 published
  3. Jellyfish: A Large Language Model for Data Preprocessing taaft This paper explores the utilization of LLMs for data preprocessing (DP), a crucial step in the data… 2023-12-04 published
  4. JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees taaft In the maintenance of complex systems, fault trees are used to locate problems and provide targeted… 2026-03-24 published
  5. Jigsaw Regularization in Whole-Slide Image Classification Google Computational pathology involves the digitization of stained tissues into whole-slide images (WSIs)… 2026-03-20 published
  6. jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers taaft In this work, we introduce GELATO (Geometry-preserving Embeddings via Locked Aligned TOwers), a nov… 2026-05-08 published
  7. Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards taaft We present Jina-OCR-v1, an end-to-end document parsing model built to serve on low-budget GPUs. It… 2026-09-02 published
  8. JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution taaft Agent capability is not determined by the model alone. The agent harness, encompassing memory manag… 2026-08-26 published
  9. JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models taaft Mathematical reasoning is an important capability of large language models~(LLMs) for real-world ap… 2024-05-23 published
  10. JLIR: A Julia-Native MLIR-Inspired Intermediate Representation with Automatic JACC Kernel Extraction taaft The Multi-Level Intermediate Representation (MLIR) has made reusable compiler infrastructure practi… 2026-09-04 published
  11. Joint Distribution Alignment for Universal Domain Adaptation taaft Unsupervised domain adaptation (UDA) has been widely concerned in the fields of machine learning, p… 2026-08-25 published
  12. Joint Initialization of Flux Networks and Effective Multiplication Factor for Physics-Informed Neural Networks Solving Neutron Diffusion Problems taaft Efficient determination of the effective multiplication factor (keff) is an important computational… 2026-08-26 published
  13. Joint Spatiotemporal Spectral Neural Operators for Learning PDEs on Irregular Domains taaft Learning solution operators for partial differential equations (PDEs) on irregular and geometry-dep… 2026-08-30 published
  14. Joint Surrogate Learning of Objectives, Constraints, and Sensitivities for Efficient Multi-objective Optimization of Neural Dynamical Systems taaft Gaussian process surrogates dominate constrained multi-objective optimization because they are effe… 2026-03-22 published
  15. JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion taaft Real-time video editing requires low-latency causal generation with bounded computational resources… 2026-08-04 published
  16. JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence taaft Many moments in the real world do not wait for a user to ask. A fire starts on a security monitor,… 2026-06-10 published
  17. JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction taaft Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing o… 2026-08-30 published
  18. JRM: Joint Reconstruction Model for Multiple Objects without Alignment taaft Object-centric reconstruction seeks to recover the 3D structure of a scene through composition of i… 2026-03-27 published
  19. JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs AISphere Social biases reflected in language are inherently shaped by cultural norms, which vary significant… 2026-03-21 published
  20. JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols taaft Large language model (LLM) judges are increasingly used across various evaluation scenarios, making… 2026-08-27 published
  21. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena taaft Evaluating large language model (LLM) based chat assistants is challenging due to their broad capab… 2023-06-09 published
  22. Judging single-image 3D generation without humans (and why cheap proxies fall short) Transformer Lab Proposes a human-free protocol for ranking single-image-to-3D-mesh generations using two independen… Transformer Lab
  23. Judging to improve: a 3D judge you can train against, and the limit of cheap 3D specialization Transformer Lab Develops a human-free VLM-judge protocol (cross-model independence, position-bias correction, calib… Transformer Lab
  24. Just Zoom In: Cross-View Geo-Localization via Autoregressive Zooming taaft Cross-view geo-localization (CVGL) estimates a camera's location by matching a street-view image to… 2026-03-26 published
  25. KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training taaft Independently trained domain specialists can be fused post-hoc into a single model that outperforms… 2026-03-24 published
  26. Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention taaft Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perfor… 2026-08-31 published
  27. KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents taaft As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge… 2026-09-03 published
  28. KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits taaft Digital circuits representation learning has made remarkable progress in the electronic design auto… 2026-03-25 published
  29. Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields taaft Neural fields (NFs) map continuous coordinates to signals such as color or density, but fast high-q… 2026-09-02 published
  30. Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones taaft Linear attention promises constant-time recurrent inference but degrades sharply on associative rec… 2026-07-19 published
  31. Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning taaft Large language models (LLMs) have shown great potential in complex reasoning tasks, yet their perfo… 2024-03-04 published
  32. KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation taaft Knowledge Graph Question Answering (KGQA) over RDF graphs remains challenging in domain-specific se… 2026-09-01 published
  33. KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records taaft Land ownership in Bangladesh is recorded in Ana-Ganda-Kora-Kranti-Til, a base-16 positional fractio… 2026-09-03 published
  34. KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction taaft Stochastic human motion prediction aims to generate diverse, plausible futures from observed sequen… 2026-03-22 published
  35. KidsNanny: A Two-Stage Multimodal Content Moderation Pipeline Integrating Visual Classification, Object Detection, OCR, and Contextual Reasoning for Child Safety Vartit We present KidsNanny, a two-stage multimodal content moderation architecture for child safety. Stag… 2026-03-17 published
  36. Kirin: Animal Motion Generation from In-the-Wild Video taaft Understanding animal motion is fundamental to modeling animal behavior and biomechanics, yet progre… 2026-09-01 published