ScholarGate
Msaidizi

Linganisha mbinu

Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.

Uboreshaji wa Mapendeleo ya Moja kwa Moja×Mamba (Muundo wa Nafasi ya Hali)×
NyanjaUjifunzaji wa KinaUjifunzaji wa Kina
FamiliaMachine learningMachine learning
Mwaka wa asili20232023
MwanzilishiRafael RafailovAlbert Gu
AinaTraining methodologyNeural network architecture
Chanzo asiliaRafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2023). Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290. link ↗Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956. link ↗
Majina mbadalaDPO, Direct preferenceMamba, State space models, Selective state space
Zinazohusiana44
MuhtasariDirect Preference Optimization (DPO) is a training method introduced by Rafailov et al. in 2023 that aligns language models with human preferences without requiring an explicit reward model. By directly optimizing for preference pairs (better response vs worse response), DPO simplifies the training pipeline compared to reinforcement learning from human feedback (RLHF).Mamba is a sequence model architecture introduced by Gu and Dao in 2023 that achieves linear-time complexity while maintaining strong performance on language modeling tasks. By combining state space models with input-dependent selectivity, Mamba addresses the quadratic complexity of transformers while preserving modeling power.
ScholarGateSeti ya data
  1. v1
  2. 1 Vyanzo
  3. PUBLISHED
  1. v1
  2. 1 Vyanzo
  3. PUBLISHED

Nenda kwenye utafutaji Pakua slaidi

ScholarGateLinganisha mbinu: Direct Preference Optimization · Mamba (State Space Model). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/compare