Papers

• Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts (2026)
  Yingfa Chen et al.
  1.94
• NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval (2026)
  Zhuchenyang Liu et al.
  1.94
• Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning (2026)
  Jiayi Lei et al.
  1.94
• APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding (2025)
  Xinyu Yang et al.
  1.28
• VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary (2025)
  Kevin Qinghong Lin et al.
  1.28
• un^2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP (2025)
  Yinqi Li et al.
  1.28
• CoMemo: LVLMs Need Image Context with Image Memory (2025)
  Shi Liu et al.
  1.28
• Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation (2025)
  Peiyu Wang et al.
  1.28
• FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models (2025)
  Zheng Chong et al.
  1.28
• Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer (2025)
  Ziyuan Huang et al.
  1.28
• Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs (2025)
  Bao Tang et al.
  1.28
• Time is Encoded in the Weights of Finetuned Language Models (2023)
  Kai Nylund et al.
  —
• Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support (2024)
  Xiaojun Wu et al.
  —
• BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data (2024)
  Mateusz Łajszczak et al.
  —
• Improving Long-Text Alignment for Text-to-Image Diffusion Models (2024)
  Luping Liu et al.
  —
• ROICtrl: Boosting Instance Control for Visual Generation (2024)
  Yuchao Gu et al.
  —