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. VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding taaft Long video understanding remains challenging for multimodal large language models (MLLMs) due to li… 2026-03-23 published
  2. VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models taaft Long-video understanding depends not only on the capability of a vision-language model (VLM), but a… 2026-08-25 published
  3. VideoMatGen: PBR Materials through Joint Generative Modeling NVIDIA We present a method for generating physically-based materials for 3D shapes based on a video diffus… 2026-03-17 published
  4. VideoPoet: A Large Language Model for Zero-Shot Video Generation Google We present VideoPoet, a language model capable of synthesizing high-quality video, with matching au… 2023-12-21 published
  5. VIDS-Seg: Towards Reliable Uncertainty Quantification in Pediatric Cardiac Ultrasound Segmentation taaft Reliable clinical deployment of machine learning requires models that know when they are likely to… 2026-08-11 published
  6. VietAIDetector: An Open-Source Zero-Shot Detector for Vietnamese AI-Generated Text taaft In recent years, distinguishing between AI-generated text and human-written text has remained a cha… 2026-08-26 published
  7. ViHOI: Human-Object Interaction Synthesis with Visual Priors taaft Generating realistic and physically plausible 3D Human-Object Interactions (HOI) remains a key chal… 2026-03-25 published
  8. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision taaft Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-languag… 2021-02-05 published
  9. VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeutics taaft Drug synergy prediction estimates whether two drugs produce a stronger joint effect than expected f… 2026-08-26 published
  10. VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation taaft End-to-end autonomous driving in urban environments requires robust decision-making under partial o… 2026-09-02 published
  11. Virgil: Navigating Explainability for Transformer-based Language Models taaft Explainability for transformer-based language models is becoming crucial as these systems are deplo… 2026-08-26 published
  12. VirTooS: A ROS 2 - Unity Virtualization Toolkit for Fleet Management of Autonomous Mobile Robots taaft In this paper, we present VirTooS, a Python/C# toolkit designed to implement fleet-management tasks… 2026-08-26 published
  13. ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering taaft Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), w… 2026-09-02 published
  14. VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence taaft AI-assisted computer-aided design (CAD) for industrial products involves two challenging phases. Pa… 2026-09-03 published
  15. VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs taaft Object hallucination remains a persistent reliability issue in large vision-language models, where… 2026-08-31 published
  16. Vision Language Model Fusion for Explainable Face Recognition taaft Responsible deployment of face verification systems requires more than accurate decisions: systems… 2026-08-25 published
  17. VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions taaft Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largel… 2026-03-24 published
  18. Vision-Language Models vs Human: Perceptual Image Quality Assessment taaft Psychophysical experiments remain the most reliable approach for perceptual image quality assessmen… 2026-03-25 published
  19. VISReg: Variance-Invariance-Sketching Regularization for JEPA training taaft Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit reg… 2026-06-01 published
  20. VISTA: Dense Multi-Label Classroom Coding with Vision-Language Models taaft Video-language benchmarks are usually constructed by the dataset authors without published reliabil… 2026-09-03 published
  21. ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits taaft Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal bl… 2026-09-01 published
  22. ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives taaft We introduce ViTAMINS, a method that integrates synthetic hard negatives into unsupervised vision t… 2026-09-01 published
  23. VizAnchor: Decoding Manipulation Intent from Tampering Visualizations via Dual-Anchor Reasoning taaft Data visualizations are widely used for communicating information, but they are also vulnerable to… 2026-08-25 published
  24. VOID: Video Object and Interaction Deletion taaft Existing video object removal methods excel at inpainting content "behind" the object and correctin… 2026-04-02 published
  25. VoRTeC: Taming Foundation Flow for One-step Real time Video Compression taaft Ultra-low bitrate video compression still faces critical challenges: traditional neural video compr… 2026-09-02 published
  26. VoxelFix: Post-Hoc Semantic Correction of Completed 3D Voxel Maps taaft Semantic 3D maps are increasingly constructed automatically for aerial robotics by integrating lear… 2026-09-04 published
  27. VoxReason: Listener-Free Evaluation of Source-Grounded Speech Planning Before Synthesis taaft Speech systems increasingly infer how an utterance should be delivered from context, but a plausibl… 2026-09-02 published
  28. Voyager: An Open-Ended Embodied Agent with Large Language Models NVIDIA We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that cont… 2023-05-25 published
  29. VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought taaft Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static… 2026-03-24 published
  30. VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance taaft Restoring degraded music signals is essential to enhance audio quality for downstream music manipul… 2023-09-13 published
  31. VSD-MOT: End-to-End Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Distillation taaft Existing multi-object tracking algorithms typically fail to adequately address the issues in low-qu… 2026-03-21 published
  32. WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes taaft Locating a specific object instance in a cluttered scene using a single reference image and a short… 2026-08-28 published
  33. Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning taaft Text-only training is a popular paradigm in zero-shot video captioning, where the video distributio… 2026-08-11 published
  34. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations Meta Platforms We show for the first time that learning powerful representations from speech audio alone followed… 2020-06-20 published
  35. Wave Function Backpropagation with Explicit Temporal-Interval Dynamics taaft Conventional neural networks learn predominantly through affine transformations followed by nonline… 2026-09-01 published
  36. WaveSFNet: A Wavelet-Based Codec and Spatial--Frequency Dual-Domain Gating Network for Spatiotemporal Prediction taaft Spatiotemporal predictive learning aims to forecast future frames from historical observations in a… 2026-03-24 published