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. Harness-agnostic detection and immunization of reward hacking in self-evolving language models taaft Self-evolving language models improve by proposing candidate updates and keeping whatever raises a… 2026-09-04 published
  2. Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement taaft This paper studies autonomous software development, in which LLM-based coding agents transform high… 2026-09-01 published
  3. Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories taaft Agents built around large language models continually accumulate interaction trajectories during de… 2026-08-03 published
  4. HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses taaft Harness design plays a critical role in agent performance by shaping how large language models (LLM… 2026-08-03 published
  5. HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? taaft As agents move from research prototypes to deployed tools, their capability increasingly depends on… 2026-09-01 published
  6. HarnessOpt-Bench: Evaluating LLMs at Harness Optimization taaft As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the… 2026-08-06 published
  7. HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models taaft Long-context inference retains a growing key--value (KV) cache during decoding, which consumes subs… 2026-09-02 published
  8. Hearing Anything Anywhere taaft Recent years have seen immense progress in 3D computer vision and computer graphics, with emerging… 2024-06-11 published
  9. Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models taaft Text-to-Speech (TTS) foundation models are increasingly fine-tuned on private datasets to synthesiz… 2026-09-01 published
  10. HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation taaft Fully homomorphic encryption (FHE) allows a server to run a language model directly on encrypted us… 2026-09-01 published
  11. HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation taaft In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter t… 2020-12-07 published
  12. HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit taaft Audio representation learning typically evaluates design choices such as input frontend, sequence b… 2026-03-22 published
  13. HellaSwag: Can a Machine Really Finish Your Sentence? taaft Recent work by Zellers et al. (2018) introduced a new task of commonsense natural language inferenc… 2019-05-19 published
  14. Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials taaft While machine-learning interatomic potentials (MLIPs) have successfully learned potential energy su… 2026-09-04 published
  15. Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detection taaft Most referring object detection (ROD) models, especially the modern grounding detectors, are design… 2026-03-25 published
  16. Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering taaft A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a questi… 2026-08-31 published
  17. Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR taaft Intelligent extended reality (XR) systems increasingly use eye and head tracking to infer user inte… 2026-09-04 published
  18. Hierarchical Diffusion Models for Singing Voice Neural Vocoder taaft Recent progress in deep generative models has improved the quality of neural vocoders in speech dom… 2022-10-14 published
  19. Hierarchical Possession-Aware Graph Pointer Network for Pass Receiver Selection taaft Pass receiver selection is a fundamental task in football analytics, aiming to predict the intended… 2026-09-04 published
  20. Hierarchical Text-Conditional Image Generation with CLIP Latents OpenAI Contrastive models like CLIP have been shown to learn robust representations of images that capture… 2022-04-13 published
  21. High Speed All-optical extended DV-Curve-based DNA sequence alignment utilizing wavelength and polarization modulation Apple This paper presents a novel optical processing approach for exploring genome sequences built upon o… 2017-12-27 published
  22. High-Quality and Efficient Turbulence Mitigation with Events taaft Turbulence mitigation (TM) is highly ill-posed due to the stochastic nature of atmospheric turbulen… 2026-03-21 published
  23. High-Resolution Image Synthesis with Latent Diffusion Models taaft By decomposing the image formation process into a sequential application of denoising autoencoders,… 2021-12-20 published
  24. Higher Structures in Deep Learning taaft We provide an expository introduction on the importance of higher-arity tensor operations to deep l… 2026-08-31 published
  25. Highly accurate protein structure prediction with AlphaFold Google DeepMind Solved the protein structure prediction problem to near-experimental accuracy (median GDT >90 at CA… Google DeepMind
  26. Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation taaft When a hint turns a failing generated program into a passing one, does it provide missing informati… 2026-09-01 published
  27. HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design taaft Polymeric materials are central to modern technologies, with applications ranging from energy to he… 2026-09-02 published
  28. HiSfM: Disambiguating Structure-from-Motion via Scaffold-Anchored Hierarchical Reconstruction taaft Structure-from-Motion (SfM) is a fundamental tool for sparse 3D reconstruction with broad impact in… 2026-09-04 published
  29. HiVe: Beyond Static Prompts for Multitask Learning via Hierarchy-based Vertical Mixture-of-Experts taaft As large language models (LLMs) continue to scale, parameter-efficient fine-tuning (PEFT) has becom… 2026-08-30 published
  30. Holistic Evaluation of Language Models taaft Language models (LMs) are becoming the foundation for almost all major language technologies, but t… 2022-11-16 published
  31. Holographic dynamics simulations with a trapped ion quantum computer Honeywell International Quantum computers have the potential to efficiently simulate the dynamics of many interacting quant… 2021-05-19 published
  32. HOMEY: Heuristic Object Masking with Enhanced YOLO for Property Insurance Risk Detection taaft Automated property risk detection is a high-impact yet underexplored frontier in computer vision wi… 2026-03-19 published
  33. HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement taaft Human-object centric video personalization (HOCVP) is a core task within subject-driven video gener… 2026-07-20 published
  34. HorizonNet for visual terrain navigation taaft This paper investigates the problem of position estimation of unmanned surface vessels (USVs) opera… 2026-08-31 published
  35. HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising taaft The paper presents a novel approach for vector-floorplan generation via a diffusion model, which de… 2022-11-23 published
  36. How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI taaft Chatbots built on large language models (LLMs) are increasingly used as confidants. Tuned to satisf… 2026-09-04 published