Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations

Documenti analoghi

• Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate
  di: Bochkov, A.
  Pubblicazione: (2025)
• Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes
  di: Bochkov, A.
  Pubblicazione: (2026)
• Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
  di: Chen, Daiwei, et al.
  Pubblicazione: (2026)
• Script Sensitivity: Benchmarking Language Models on Unicode, Romanized and Mixed-Script Sinhala
  di: Rajapakse, Minuri, et al.
  Pubblicazione: (2026)
• Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
  di: Damani, Mehul, et al.
  Pubblicazione: (2025)