Papers

• NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval (2026)
  Zhuchenyang Liu et al.
  1.94
• Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation (2026)
  M. Ali Bayram et al.
  1.89
• Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (2025)
  Xiaojun Jia et al.
  1.28
• Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMS (2025)
  Anand et al.
  1.28
• Cottention: Linear Transformers With Cosine Attention (2024)
  Gabriel Mongaras et al.
  —