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. TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models taaft Visual grounding maps language referents to spatial targets and is central to open-vocabulary perce… 2026-09-02 published
  2. Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting taaft This paper presents a novel study on harnessing Large Language Models' (LLMs) outstanding knowledge… 2023-06-19 published
  3. TempTabQA: Temporal Question Answering for Semi-Structured Tables taaft Semi-structured data, such as Infobox tables, often include temporal information about entities, ei… 2023-11-14 published
  4. Ten Architectures, One Error: Shared Failure Modes in Hyperspectral Classification under Spatially Disjoint Evaluation taaft Hyperspectral image classification still relies heavily on random pixel splits within a single scen… 2026-09-01 published
  5. Tensor-based Brain Surface Modeling and Analysis taaft We present a unified computational approach to tensor-based morphometry in detecting the brain surf… 2026-09-03 published
  6. Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments taaft As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while… 2026-09-03 published
  7. Test-time adaptation for speech enhancement with an autoregressive speech prior taaft Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models und… 2026-09-03 published
  8. Test-Time Logit Prompting for Source-Free Missing Modality Adaptation taaft Vision-language models (VLMs) have achieved remarkable performance by leveraging complementary info… 2026-09-02 published
  9. Testing Interchangeability in LLM Agent Teams taaft Production multi-agent systems replace agents constantly, on the assumption that an agent filling a… 2026-09-04 published
  10. Text Restoration of Ancient Documents with Language Models taaft Purpose - This study investigates the feasibility of restoring missing text caused by physical lacu… 2026-08-28 published
  11. text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation taaft Natural language interfaces to databases have traditionally suffered from three structural limitati… 2026-09-02 published
  12. Textbooks Are All You Need Microsoft We introduce phi-1, a new large language model for code, with significantly smaller size than compe… 2023-06-20 published
  13. Texture Image Classification Using DWT AlexNet Feature Fusion and Deep Neural Networks taaft Texture image classification plays a significant role in computer vision applications, including in… 2026-08-28 published
  14. The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion taaft LLM-generated search queries are widely used to augment IR evaluation, yet they may contain concept… 2026-08-26 published
  15. The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100 taaft The ambition of the 2025 PNPL competition (Landau et al., 2025) was to launch a multi-year curricul… 2026-09-03 published
  16. The Answer Is Not the Argument taaft Chain-of-thought monitoring is proposed for AI oversight, yet evaluations often provide monitors wi… 2026-08-31 published
  17. The Approximation Rank of Softmax Attention: Sharp Geometric Laws and Robust Interaction Dimension taaft How much matrix rank is required to preserve every bounded value output of normalized softmax atten… 2026-08-28 published
  18. The asymptotic version of the Erdős-Sós conjecture and beyond taaft Klimošová, Piguet, and Rozhoň conjectured that any graph with minimum degree $k/2$ and sufficiently… 2026-03-18 published
  19. The Attention Triangle in Audio-Video Models taaft Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual co… 2026-09-03 published
  20. The Average Relative Entropy and Transpilation Depth determines the noise robustness in Variational Quantum Classifiers taaft Variational Quantum Algorithms (VQAs) have been extensively researched for applications in Quantum… 2026-03-22 published
  21. The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations taaft Noisy annotations pose a significant challenge for supervised deep learning, as neural networks rel… 2026-09-03 published
  22. The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinical Prediction taaft Clinical prediction can saturate for two different reasons: a fitted learner may fail to extract av… 2026-09-01 published
  23. The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent Systems taaft Humans are the transport layer between AI systems, losing context at every hop. We present the Civi… 2026-09-03 published
  24. The Claude 3 Model Family: Opus, Sonnet, and Haiku Anthropic This report introduces Claude 3, a family of large language models (Opus, Sonnet, Haiku) designed f… Anthropic
  25. The Constitutional Coverage Trilemma in AI Governance taaft Frontier AI systems function as \emph{constitutional institutions}: each deployed model encodes an… 2026-09-01 published
  26. The Dawn of Natural Language to SQL: Are We Fully Ready? taaft Translating users' natural language questions into SQL queries (i.e., NL2SQL) significantly lowers… 2024-06-03 published
  27. The Depth Flow of Token Representations Is Nonlinear and Does Not Descend Its Own Density taaft A token's representation is carried through the network layer by layer. The whole vocabulary carrie… 2026-08-30 published
  28. The Diagnosis a Reporter Leaves Unspoken: Surfacing Frozen Tumor Features for Brain-Tumor MRI Reporting taaft A capable brain-MRI report generator can still be, in effect, diagnostically silent. When a multi-c… 2026-09-02 published
  29. The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations taaft Background: Researchers increasingly use repeated identical prompts to audit stochastic variation i… 2026-09-03 published
  30. The Differential Reasoning Router: Operationalizing Cost-Aware LLM Annotation in E-commerce taaft Large Language Models (LLMs) are increasingly used to annotate structured product data in e-commerc… 2026-08-31 published
  31. The Dually Flat Geometry of Planning as Inference taaft We present an alternative characterization of the occupancy measure of reinforcement learning, obta… 2026-09-03 published
  32. The Dynamics of Continuous Mixture Collapse in Language Models taaft LLMs latent-state reasoning methods replace discrete intermediate tokens with continuous states, su… 2026-09-02 published
  33. The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits taaft Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LL… 2024-02-27 published
  34. The Faiss library taaft Vector databases typically manage large collections of embedding vectors. Currently, AI application… 2024-01-16 published
  35. The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors taaft What does a language model predict when it has few clues? The answer lurks in its unembedding geome… 2026-09-02 published
  36. The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA taaft Continuous chain-of-thought models compress reasoning into latent tokens. Matrix-valued variants, w… 2026-09-02 published