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. World Models taaft We explore building generative neural network models of popular reinforcement learning environments… 2018-03-27 published
  2. World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models taaft World Action Models (WAMs) aim to control robots by stochastically generating visual futures and th… 2026-09-02 published
  3. World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain taaft Foothold-constrained terrain is characterized by sparse, discontinuous, or geometrically restricted… 2026-09-02 published
  4. WorldBench: Culturally Grounded Benchmark for Multilingual Agents taaft Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, ex… 2026-09-01 published
  5. WorldReward: Reward Modeling for Camera-Conditioned World Models taaft Camera-conditioned world models generate interactive videos in which commanded actions should induc… 2026-09-03 published
  6. WorldSculpt: Generating Compositional Worlds from Grounded Videos taaft We study the problem of generating a compositional 3D representation of a cluttered scene containin… 2026-09-04 published
  7. Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores taaft When a large language model fails a reasoning task, it is often assumed to lack the underlying capa… 2026-08-31 published
  8. X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis taaft Imaging factor disentanglement in text-to-image generation aims to independently control image acqu… 2026-08-25 published
  9. X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention taaft We propose X-Portrait, an innovative conditional diffusion model tailored for generating expressive… 2024-03-23 published
  10. XDG: Accelerated Visual Disambiguation taaft Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from… 2026-08-30 published
  11. Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories taaft We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) foll… 2026-07-16 published
  12. XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression taaft Removing complete transformer layers preserves a standard serving architecture, but existing depth-… 2026-09-02 published
  13. XP-JEPA: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics taaft Latent world models plan by predicting how candidate actions advance learned latent dynamics. In se… 2026-08-25 published
  14. XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals taaft Evaluating data-text alignment remains challenging: existing metrics often provide limited explanat… 2026-08-30 published
  15. xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token taaft This paper introduces xRAG, an innovative context compression method tailored for retrieval-augment… 2024-05-22 published
  16. YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification taaft Referring multi-object tracking (RMOT) aims to track every instance in a video that matches a given… 2026-09-02 published
  17. YOLO Object Detectors for Robotics -- a Comparative Study taaft YOLO object detectors recently became a key component of vision systems in many domains. The family… 2026-03-27 published
  18. YOLOv10 with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection and trustworthy multimodal AI in computer vision perception taaft The trustworthy object detection capabilities of a novel Kolmogorov-Arnold network framework are ex… 2026-03-24 published
  19. You Can't Escape Your Own Activations : Evaluation Awareness and Multi-Agent Monitoring taaft LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping t… 2026-09-02 published
  20. You Know What I Mean: A Benchmark for Agentic Conversational Reference Grounding taaft Collaborative conversations frequently contain references whose targets are indirect rather than na… 2026-08-30 published
  21. Your Voice Cloning System is Secretly a Voice Anonymizer taaft Speaker anonymization suppresses speaker-identifying attributes from speech while preserving lingui… 2026-08-27 published
  22. Zero- and Few-shot Sound Event Localization and Detection taaft Sound event localization and detection (SELD) systems estimate direction-of-arrival (DOA) and tempo… 2023-09-17 published
  23. Zero-Mem: Zero-Token Memory Operations for LLM Agents taaft LLM agents need memory to act consistently over long interactions, yet many systems use additional… 2026-07-31 published
  24. Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations taaft 3D Foundation Models (3DFMs) such as VGGT have recently pushed the boundaries of 3D vision by predi… 2026-09-03 published
  25. Zero-Shot Personalization of Objects via Textual Inversion taaft Recent advances in text-to-image diffusion models have substantially improved the quality of image… 2026-03-24 published
  26. Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models taaft If generalist robots are to operate in truly unstructured environments, they need to be able to rec… 2023-10-16 published
  27. Zero-Shot Video Restoration and Enhancement with Text-to-Image Latent Diffusion Models and Multi-Modal References taaft Zero-shot image restoration methods with text-to-image latent diffusion models have achieved great… 2026-08-27 published
  28. Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization taaft Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen duri… 2026-08-26 published
  29. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models Microsoft Large deep learning models offer significant accuracy gains, but training billions to trillions of… 2019-10-04 published
  30. Zeta-Lite: A Concurrent, Branchable In-Browser SQL Database for Agentic Memory taaft The browser has become a first-class database host: applications increasingly want to store, query,… 2026-09-01 published
  31. ZETA: A Controlled Study of Zero-Shot Cross-Embodiment VLA Transfer for Tabletop Manipulation taaft Zero-shot generalization to unseen embodiments is important for generalizable vision-language-actio… 2026-09-02 published
  32. Zetta $ζ$: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence taaft Embodied agents are increasingly used to close the gap left by end-to-end policy models. Yet the ag… 2026-08-17 published
  33. ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training taaft Robotic manipulation faces a fundamental scaling challenge: robust generalization demands broad phy… 2026-08-31 published
  34. ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device taaft Monocular depth estimation has seen remarkable progress through foundation models achieving robust… 2026-07-09 published
  35. ZipMVS: Multi-View Stereo with Compressed Cost Volumes taaft Multi-view stereo (MVS) methods typically deliver highly accurate 3D reconstructions from multiple… 2026-08-28 published
  36. ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes taaft Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers… 2026-09-01 published