You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations

Documenti analoghi

• Silent Tokens, Loud Effects: Padding in LLMs
  di: Himelstein, Rom, et al.
  Pubblicazione: (2025)
• Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
  di: Rahimi, Eliron, et al.
  Pubblicazione: (2026)
• Silenced Biases: The Dark Side LLMs Learned to Refuse
  di: Himelstein, Rom, et al.
  Pubblicazione: (2025)
• Jailbreak Attack Initializations as Extractors of Compliance Directions
  di: Levi, Amit, et al.
  Pubblicazione: (2025)
• Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software
  di: Kordonsky, Tomer, et al.
  Pubblicazione: (2026)