Pith. sign in

INDEX 8,488,275 cited works 298,575 reviewed citing papers 501,433 with resolved metadata

Every reference in a reviewed paper becomes a page; the most cited works rank here.

top-cited works

Ranked by how many Pith-reviewed papers cite each work. Reviewed entries open to their full review; the rest open to their citation dossier.

  1. 429 citing papers
    Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

    unverdicted 2022 arXiv:2209.03003

    Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.

  2. 386 citing papers
    UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

    unverdicted 2026 arXiv:1802.03426

    UMAP is a novel, scalable manifold learning algorithm for dimension reduction that competes with t-SNE while preserving more global structure and having no embedding dimension restrictions.

  3. 343 citing papers
    SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

    unverdicted 2025 arXiv:2502.14786

    SigLIP 2 models trained with a unified recipe of captioning, self-supervised losses, and curated diverse data outperform prior SigLIP versions on classification, retrieval, localization, dense prediction, and multilingual understanding at scales from 86M to 1B parameters.

  4. 363 citing papers
    AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

    unverdicted 2023 arXiv:2308.08155

    AutoGen provides an open-source framework for multi-agent LLM conversations that support customizable interactions across diverse applications.

  5. 364 citing papers
    DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

    unverdicted 2018 arXiv:2512.02556

    DeepSeek-V3.2 adds sparse attention, scaled RL post-training, and large-scale agentic data synthesis to reach GPT-5-level performance and gold medals in 2025 IMO and IOI with its high-compute variant.

  6. 396 citing papers
    A Survey of Large Language Models

    accept 2016 arXiv:2303.18223

    This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.

  7. 487 citing papers
    Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

    conditional 2024 arXiv:2403.05530

    Gemini 1.5 models achieve near-perfect recall over up to 10M tokens of multimodal context, improve long-document and long-video QA, and match or exceed prior Gemini 1.0 Ultra performance on standard benchmarks.

  8. 415 citing papers
    HunyuanVideo: A Systematic Framework For Large Video Generative Models

    unverdicted 2024 arXiv:2412.03603

    HunyuanVideo presents a 13B-parameter open-source video generative model with integrated data, architecture, training, and inference systems whose professional evaluations show it outperforming prior SOTA models including Runway Gen-3 and Luma 1.6.

  9. 593 citing papers
    Attention Is All You Need

    unverdicted 2021 arXiv:1706.03762

    Pith review generated a malformed one-line summary.

  10. 417 citing papers
    Hierarchical Text-Conditional Image Generation with CLIP Latents

    accept 2022 arXiv:2204.06125

    A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.

browse citation demand ›