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. User Representation via Cross Multi-source Behavior Pre-training for Mobile Games taaft User representation pre-training has become a fundamental paradigm for alleviating data sparsity in… 2026-09-01 published
  2. Using AI-based virtual triage to improve acuity-level alignment of patient care seeking in an ambulatory care setting Infermedica Analyses 8,088 outpatient online encounters in an ambulatory network to see how virtual triage shif… Infermedica
  3. Using Grounded Theory for Agent Behavior Analysis at Scale taaft Understanding agent behavior requires methods that scale to thousands of trajectories and surface n… 2026-08-31 published
  4. Using profiles of cognitive capability to assess AI suitability for workplace tasks taaft Organisations deploying AI face a scoping problem: which tasks can be automated, which should remai… 2026-08-26 published
  5. Using Prosody to Predict Syntactic Structure taaft While it is well-established that prosody carries crucial cues for syntactic structure, the degree… 2026-08-31 published
  6. UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory taaft Long-term memory is increasingly important for conversational agents, yet existing benchmarks prima… 2026-08-31 published
  7. UTP-Bench: Uncertainty-aware Travel Planning Benchmark taaft Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel iti… 2026-09-02 published
  8. UW-VOS: A Large-Scale Dataset for Underwater Video Object Segmentation taaft Underwater Video Object Segmentation (VOS) is essential for marine exploration, yet open-air method… 2026-03-25 published
  9. V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models taaft Vision-language-action (VLA) models provide a scalable path toward generalist robotic manipulation… 2026-08-26 published
  10. VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages taaft Real-world communication often requires pragmatic reasoning: interpreting meanings implied through… 2026-09-01 published
  11. Validation of HRV Studio: A Transparent and Quality-Control-Aware Platform for Heart Rate Variability Analysis taaft Reproducibility of heart rate variability (HRV) analysis is limited by differences in preprocessing… 2026-08-25 published
  12. Validity-Aware Jailbreak Evaluation for Large Language Models taaft Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevai… 2026-08-31 published
  13. Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture -- Bridging Predictive and Generative Self-Supervised Learning taaft The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to… 2026-03-20 published
  14. Variational Continuation for Double Pendulum Periodic Orbits taaft We present a Hessian-based approach to numerically continue periodic orbits in dynamical systems. A… 2026-09-04 published
  15. VATO: A Vortex-Force-Aware Transformer Operator for Unsteady Separated Aerofoil Flows taaft Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend… 2026-09-01 published
  16. VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning Alibaba Recent studies have demonstrated the potential of cross-lingual transferability by training a unifi… 2023-04-17 published
  17. Vectorizing Classical Tamil: Representation Learning for Verse-Commentary Pairs taaft We construct a corpus of 1,262 verse--commentary (urai) pairs from five Classical Tamil source sect… 2026-09-04 published
  18. Verbalizable Representations Form a Global Workspace in Language Models Anthropic This paper introduces the Jacobian lens (J-lens), a new interpretability technique that identifies… Anthropic
  19. VERIA: Verification-Centric Multimodal Instance Augmentation for Long-Tailed 3D Object Detection taaft Long-tail distributions in driving datasets pose a fundamental challenge for 3D perception, as rare… 2026-03-25 published
  20. Verifiable Error Bounds for Physics-Informed Neural Network Solutions of Lyapunov and Hamilton-Jacobi-Bellman Equations taaft Many core problems in nonlinear systems analysis and control can be recast as solving partial diffe… 2026-03-20 published
  21. Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation taaft On-policy distillation (OPD) accelerates post-training by providing dense token-level supervision f… 2026-09-02 published
  22. Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification taaft Agent harnesses shape how language-model agents use instructions, tools, and runtime components, bu… 2026-08-27 published
  23. VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement taaft Visual fluency in generated video does not imply physical reliability, and a scalar quality score a… 2026-09-02 published
  24. VerNav: Verifier-First Low-Latency Vision-and-Language Navigation taaft Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments a… 2026-09-01 published
  25. VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch taaft A long-lived KV cache must be compressed before the queries that will read it exist. Selection by o… 2026-09-03 published
  26. VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation Quality taaft We introduce VGA-BenchV2, an extended human-aligned benchmark and optimization framework for jointl… 2026-08-26 published
  27. VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues taaft 3D foundation models (3DFMs) excel at predicting camera poses and dense depth from multiple views o… 2026-09-03 published
  28. VIBE: Video Instruction-aligned Background music gEneration taaft Current video-to-music (V2M) models lack semantic control and fail to penalize instruction violatio… 2026-08-31 published
  29. VibeJam: A User Study Platform for Web Development with Agents taaft Programming with AI is increasingly agentic, users prompt LLMs to directly edit their code and revi… 2026-08-30 published
  30. VibeVoice-ASR-Streaming Technical Report taaft Traditional speaker-attributed ASR systems treated ASR and speaker diarization as two separate task… 2026-09-02 published
  31. VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition taaft Multi-expert models have become the dominant paradigm for long-tailed learning, largely attributed… 2026-09-04 published
  32. VICT: Verifier-Instrumented Credit Tracing for Long-Horizon LLM Agent Reinforcement Learning taaft Fine-grained credit assignment is a central challenge in reinforcement learning for long horizon LL… 2026-08-28 published
  33. Video Recognition in Portrait Mode taaft The creation of new datasets often presents new challenges for video recognition and can inspire no… 2023-12-21 published
  34. Video-Based Palm-Vein Authentication under Challenging Conditions taaft Palm-vein biometrics are increasingly used for secure, contactless authentication. Yet real-world d… 2026-09-02 published
  35. Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining taaft Recent advances in multimodal large language models have driven growing interest in graphical user… 2026-05-14 published
  36. Video2Reaction: Training Foundation Video Models to Predict Audience Reaction taaft We introduce Video2Reaction, a multimodal dataset that maps short movie segments to the induced emo… 2026-09-01 published