conftrace_

speculative sampling

15 papers

Explore in graph

Also known as

SS

Co-occurring keywords · papers mentioning both

large language model (7) inference acceleration (6) model compression (3) language model inference (2) draft model (2) inference optimization (2) language model (2) text generation (2) knowledge distillation (2) watermark injection (1)

Papers

Re-SpS: A Reinforcement Learning Approach to Speculative Sampling AAAI 2026 Accelerated Diffusion Models via Speculative Sampling ICML 2025 FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling ACL 2025 Learning Harmonized Representations for Speculative Sampling ICLR 2025 Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits ICLR 2025 Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation Interspeech 2025 Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner EMNLP 2025 Speculative Safety-Aware Decoding EMNLP 2025 Accelerated Speculative Sampling Based on Tree Monte Carlo ICML 2024 Controlled Text Generation via Language Model Arithmetic ICLR 2024 EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees EMNLP 2024 EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty ICML 2024 Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models NeurIPS 2024 Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024 Speculative Sampling in Variational Autoencoders for Dialogue Response Generation EMNLP 2021