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. Fewer Truncations Improve Language Modeling taaft In large language model training, input documents are typically concatenated together and then spli… 2024-04-16 published
  2. Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction taaft One model passed our fidelity check without ever opening the datasheet. We found it while qualifyin… 2026-08-28 published
  3. FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback taaft Captions are crucial for understanding scientific visualizations and documents. Existing captioning… 2023-07-20 published
  4. Figures as Programs: Recursive Generation of Editable Scientific Figures taaft Scientific methodology figures are essential for communicating complex methods clearly, yet creatin… 2026-09-01 published
  5. Fill My Mirror: Geometry-Constrained Mirror Inpainting taaft Mirrors are common in real-world images, yet producing geometrically consistent reflections with ge… 2026-09-03 published
  6. FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality taaft A merchant's payment processor, ledger, ERP and bank feed are updated by messages that get delayed,… 2026-09-04 published
  7. Finding Distributed Object-Centric Properties in Self-Supervised Transformers taaft Self-supervised Vision Transformers (ViTs) like DINO show an emergent ability to discover objects,… 2026-03-27 published
  8. Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration taaft Multi-agent systems (MAS) powered by large language models have shown promise for complex tasks but… 2026-08-28 published
  9. Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework taaft Image enhancement and restoration have become standard back-end operations on short-video and socia… 2026-09-02 published
  10. Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space taaft Fine-tuning Low-bit models aims to adapt a quantized model while keeping the final deployed checkpo… 2026-08-31 published
  11. FinExam-10K: When Retrieval Helps Financial Reasoning? taaft Professional financial examinations require models to combine domain knowledge, calculation, and ju… 2026-08-28 published
  12. FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue taaft Repeated banking interactions require assistants to maintain complete, current, and traceable custo… 2026-09-01 published
  13. FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review taaft Deploying large language models for professional financial review requires more than measuring gene… 2026-08-26 published
  14. FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading taaft We present FinRL-X, a modular and deployment-consistent trading architecture that unifies data proc… 2026-03-22 published
  15. First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents taaft We present Qwen-GuidePlay-2B, a 2B-parameter language model for dialogue-game interaction. We fine-… 2026-08-27 published
  16. First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle taaft The Abstraction and Reasoning Corpus (ARC) was recently introduced by François Chollet as a tool to… 2021-12-01 published
  17. First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves taaft Recent progress in multimodal large language models (MLLMs) has fueled significant enthusiasm in th… 2026-09-04 published
  18. FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation taaft Unsupervised action segmentation is a challenging task. It involves finding action categories and b… 2026-08-30 published
  19. FISGuard: Defending Against Membership Inference via Fixed Input Subspaces taaft As large language models are increasingly adopted in federated learning, protecting user privacy wh… 2026-08-28 published
  20. FixationFormer: Direct Utilization of Expert Gaze Trajectories for Chest X-Ray Classification taaft Expert eye movements provide a rich, passive source of domain knowledge in radiology, offering a po… 2026-03-24 published
  21. FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation taaft Token aggregation converts token-level representations into fixed-dimensional sample representation… 2026-09-01 published
  22. FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings Owkin Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to coll… 2022-10-10 published
  23. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness KRAFTON Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of… 2022-05-27 published
  24. FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow taaft We present FlashRender, a few-step generative rendering framework that retakes a source video along… 2026-09-03 published
  25. FlexiViT: One Model for All Patch Sizes taaft Vision Transformers convert images to sequences by slicing them into patches. The size of these pat… 2022-12-15 published
  26. FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering taaft Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number… 2023-08-23 published
  27. flexvec: SQL Vector Retrieval with Programmatic Embedding Modulation taaft As AI agents become the primary consumers of retrieval APIs, there is an opportunity to expose more… 2026-03-23 published
  28. Flint: A Semantics-Driven Data Visualization Intermediate Language taaft We present Flint, an intermediate language that enables authors to create high-quality visualizatio… 2026-07-22 published
  29. Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference taaft We introduce Stateless Bernoulli Watermarking (SBW), a new statistical watermark for Large Language… 2026-09-03 published
  30. Flow Matching for Generative Modeling Meta Platforms We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), a… 2022-10-06 published
  31. FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience taaft A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: te… 2026-09-03 published
  32. FlowMoDL: Model-Based Deep Learning with Conjugate-Gradient Data Consistency for Highly Accelerated 4D Flow MRI Reconstruction taaft We present FlowMoDL, an unrolled neural network for highly accelerated 4D flow MRI reconstruction t… 2026-08-26 published
  33. FluxDisco: Symbolic Regression for Stoichiometric Dynamical Systems via Monte Carlo Graph Search taaft Dynamical symbolic regression methods identify governing differential equations from noisy data, ba… 2026-09-04 published
  34. FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models taaft Evaluating large language models (LLMs) in safety-critical, physics-governed environments requires… 2026-09-03 published
  35. Focus Anywhere for Fine-grained Multi-page Document Understanding taaft Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation… 2024-05-23 published
  36. FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos taaft We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs di… 2026-08-31 published