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. How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space taaft Aesthetics are an important part of the symbolism of artistic works. Although subjective, humans ca… 2026-08-27 published
  2. How Do Language Models Choose Between Context and Memory? taaft When contextual information conflicts with knowledge stored in model parameters, activation directi… 2026-09-01 published
  3. How Do Language Models Represent and Use Phonological Information for Allomorph Selection? taaft Language models are trained on tokenized text that obscures the sound structure of words, yet they… 2026-09-04 published
  4. How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions taaft As LLMs take on roles requiring moral advice, understanding how they attribute moral agency becomes… 2026-09-04 published
  5. How Do Prompt Variations Affect Energy Consumption in On-Device LLMs? taaft Large language models (LLMs) are increasingly deployed on mobile devices, making energy efficiency… 2026-09-01 published
  6. How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account taaft How do LLM agents come to both understand environments they act in and master tasks set within them… 2026-08-30 published
  7. How Edge of Stability Hinders SCAFFOLD in Federated Optimization taaft In federated learning, it is well known that heterogeneous data can (in theory) slow down optimizat… 2026-08-26 published
  8. How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study taaft Deep models for sales forecasting, such as WaveNet-style dilated convolutional networks, are accura… 2026-09-04 published
  9. How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models taaft Video generation for autonomous driving cannot follow the web-scale route: driving data is expensiv… 2026-08-28 published
  10. How Far Can Synthetic Data Take Thai OCR? taaft We investigate what makes synthetic OCR supervision transfer to real Thai documents and use the res… 2026-09-03 published
  11. How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making taaft Production deployments of large language model (LLM) agents remain unreliable on long, multi-step w… 2026-08-31 published
  12. How good was my shot? Quantifying Player Skill Level in Table Tennis taaft Gauging an individual's skill level is crucial, as it inherently shapes their behavior. Quantifying… 2026-03-26 published
  13. How Language Models Organize and Structure Moral Knowledge taaft How do large language models (LLMs) organize moral knowledge? Models detect moral content broadly,… 2026-08-27 published
  14. How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling taaft In this paper, we analyze how Large Language Models (LLMs) employ worldbuilding strategies, focusin… 2026-09-02 published
  15. How Much Can AI Understand? Toward AI-Assisted Sensemaking of Collaborative Discussion in Groups with Shared History taaft AI tools that support collaborative discussion typically treat the discussion as a standalone task,… 2026-08-28 published
  16. How Output Format Confounds Data Quality and Capability in Instruction Tuning taaft Instruction-tuning data are judged by quality metrics, and tuned models are judged by benchmarks, b… 2026-09-02 published
  17. How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models taaft Language models encounter typos, corrupted text, altered words, and disrupted token order, yet robu… 2026-09-03 published
  18. How Prolific Sellers Self-Present: Dissecting the Communication Patterns of 1.6 Million Reverb Listings taaft The current paper draws on self-presentation theory and warranting theory to evaluate how the langu… 2026-08-30 published
  19. How Temporal Correlations Shape Memory in Linear Recurrent Neural Networks taaft The linear recurrent neural network (LRNN) is a simple model for studying how much memory a network… 2026-08-31 published
  20. How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method taaft LLM agents deployed for software engineering fail expensively: they act confidently wrong, and bad… 2026-09-04 published
  21. HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes taaft Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook… 2023-12-31 published
  22. HSRM: Hidden-State Reward Models for Test-Time Verification taaft Large language models can often generate plausible mathematical reasoning traces, but reliably iden… 2026-08-31 published
  23. Human-Anchored Factuality Evaluation with Strategic Annotation taaft LLM-based factuality judges provide scalable evaluation signals, but their metrics are often system… 2026-08-31 published
  24. Humanoid Safe Stop via Learned Stoppability Value taaft Humanoid robots responding to emergency stop commands typically execute a fixed maneuver, without r… 2026-09-02 published
  25. Hybrid topic modelling for computational close reading: Mapping narrative themes in Pushkin's Evgenij Onegin taaft This study presents a hybrid topic modelling framework for computational literary analysis that int… 2026-03-20 published
  26. HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs taaft Scientific knowledge graphs organize entities and relations extracted from scientific literature, b… 2026-09-02 published
  27. HyperMC: Multi-Fidelity Hyperparameter Tuning for Stochastic Gradient MCMC taaft Stochastic gradient Markov chain Monte Carlo (SGMCMC) methods enable scalable Bayesian inference, b… 2026-09-02 published
  28. Hyperspectral Trajectory Image for Multi-Month Trajectory Anomaly Detection taaft Trajectory anomaly detection underpins applications from fraud detection to urban mobility analysis… 2026-03-26 published
  29. HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks taaft Low-resource authorship style transfer (LAST) aims to rewrite text into the style of an arbitrary t… 2026-09-02 published
  30. HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning taaft Large language models (LLMs) have enabled AI scientist systems to automate scientific discovery, ye… 2026-08-26 published
  31. HyQuant: Hybrid-Precision Quantization for LLM Attention taaft Quantization has been widely adopted in LLM training and inference to reduce cost and improve effic… 2026-08-28 published
  32. I M Avatar: Implicit Morphable Head Avatars from Videos taaft Traditional 3D morphable face models (3DMMs) provide fine-grained control over expression but canno… 2021-12-14 published
  33. I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization taaft Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, bu… 2026-08-13 published
  34. I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation taaft Despite remarkable progress in video generation, maintaining long-term scene consistency upon revis… 2026-03-24 published
  35. ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing taaft Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Bef… 2026-08-26 published
  36. ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects taaft Accurately modeling how real-world materials reflect light remains a core challenge in inverse rend… 2026-03-26 published