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. Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance taaft Long-horizon predictive maintenance requires models to distinguish slowly evolving degradation from… 2026-09-04 published
  2. Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration taaft AI agents are increasingly used in mathematics research, but it is often unclear how to use them ef… 2026-08-11 published
  3. Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading taaft AI agents have become capable of autonomously completing short, well-specified tasks. However, exis… 2026-07-09 published
  4. Long-Time Trajectory Approximation via SA-NODEs: Model Predictive and Floquet Strategies taaft We study the approximation of dynamical systems by semi-autonomous neural ordinary differential equ… 2026-08-11 published
  5. LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails taaft Safety guardrails serve as the last line of defense against harmful inputs and outputs of large lan… 2026-08-27 published
  6. LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks taaft Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained… 2026-08-03 published
  7. LongPIBench: A Long-Context Benchmark for Prompt Injection taaft Prompt injection attacks pose a serious security risk to large language models in real-world applic… 2026-08-28 published
  8. LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory taaft Vision-Language Navigation (VLN) requires an embodied agent to follow natural-language instructions… 2026-09-02 published
  9. LookThere! Sparse Vision by Reinforced Selection taaft Vision transformers typically treat every image token as equally important, yet for most tasks in c… 2026-09-04 published
  10. Loom: Weaving Diagnostic Strands into Free-Text Consensus via Embedding-Space Reweighting taaft Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challe… 2026-09-02 published
  11. Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence? taaft Recent work identifies a mid-depth band of verbalisable, causally potent representations in a stand… 2026-09-01 published
  12. LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates taaft Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors… 2026-09-02 published
  13. LoRA: Low-Rank Adaptation of Large Language Models Microsoft An important paradigm of natural language processing consists of large-scale pre-training on genera… 2021-06-17 published
  14. Loss-Based Active Learning for Neural Abstractive Summarization taaft Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaini… 2026-08-26 published
  15. Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Edge-Deployable Virtual Sensing taaft Virtual sensing enables digital twins and safety-critical systems to reconstruct and forecast spati… 2026-08-25 published
  16. Low-Overhead Fault-Tolerant Quantum Error Correction with the Surface-GKP Code Honeywell International Addresses the high qubit cost of simulating quantum systems. It uses tensor network techniques to s… Honeywell International
  17. Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints taaft Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded… 2026-09-01 published
  18. LRM: Large Reconstruction Model for Single Image to 3D Adobe We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from… 2023-11-08 published
  19. Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling taaft Composable scene modeling aims to recover a real indoor scene as complete, editable object assets a… 2026-08-31 published
  20. LUMIN: Lightweight Universal Manufacturing Inspection Network for Anomaly Detection taaft Industrial anomaly detection faces two engineering bottlenecks: memory bank construction latency an… 2026-09-04 published
  21. LumiXAI: A Modular Full-Stack Framework for Feature Attribution taaft Feature attribution is a central tool of model interpretability, yet the software through which it… 2026-08-25 published
  22. LUTSeg: A Longitudinal Multi-Expert Dataset for Ulcer Tissue Segmentation taaft Quantifying wound tissue composition is essential for monitoring chronic ulcer progression and guid… 2026-08-26 published
  23. M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems Alibaba Industrial recommender systems have been growing increasingly complex, may involve \emph{diverse do… 2022-05-17 published
  24. M6: A Chinese Multimodal Pretrainer Alibaba In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consist… 2021-03-01 published
  25. MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization taaft Multi-arm collaboration is becoming a core capability in embodied manipulation. Recent vision-langu… 2026-08-26 published
  26. MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate taaft Media bias in news articles operates through subtle linguistic cues---loaded language, selective fr… 2026-09-04 published
  27. Magic-Me: Identity-Specific Video Customized Diffusion ByteDance Creating content with specified identities (ID) has attracted significant interest in the field of… 2024-02-14 published
  28. Mahalanobis-Based Multi-Head Attention for Complex State Propagation taaft In this paper, we propose \textbf{Mahalanobis-Based Multi-Head Attention} (MHA-CSP), a novel attent… 2026-08-25 published
  29. Make-A-Video: Text-to-Video Generation without Text-Video Data taaft We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in T… 2022-09-29 published
  30. Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models taaft Modern vision-language models (VLMs) can directly answer many image-grounded questions, yet they of… 2026-09-03 published
  31. Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents taaft Prospective memory means carrying out a deferred intention at the right future cue while other work… 2026-09-01 published
  32. Making Video Models Adhere to User Intent with Minor Adjustments taaft With the recent drastic advancements in text-to-video diffusion models, controlling their generatio… 2026-03-20 published
  33. MAMA-FLUX.2: Image-to-Image Synthesis of Post-Contrast Breast DCE-MRI for the MAMA-SYNTH Challenge taaft Dynamic contrast-enhanced breast MRI is central to cancer diagnosis and monitoring, but requires ga… 2026-08-26 published
  34. Mamba-VMR: Multimodal Query Augmentation via Generated Videos for Precise Temporal Grounding taaft Video Corpus Moment Retrieval (VCMR) aims to retrieve both the correct video and its temporal segme… 2026-03-23 published
  35. Man and machine: artificial intelligence and judicial decision making taaft The integration of artificial intelligence (AI) technologies into judicial decision-making, particu… 2026-03-19 published
  36. Manacá-1B: An Open, Reproducible Brazilian-Portuguese Language Model and a Tokenizer-Aware, Paired Evaluation taaft Brazilian Portuguese remains under-served by open language models, and the few that exist are diffi… 2026-08-31 published