Copertina

CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Weng, Yepeng, Mei, Dianwen, Qiu, Huishi, Chen, Xujie, Liu, Li, Tian, Jiang, Shi, Zhongchao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Traversal Verification for Speculative Tree Decoding
di: Weng, Yepeng, et al.
Pubblicazione: (2025)

UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
di: Weng, Yepeng, et al.
Pubblicazione: (2026)

Multi-Drafter Speculative Decoding with Alignment Feedback
di: Kim, Taehyeon, et al.
Pubblicazione: (2026)

Mamba Drafters for Speculative Decoding
di: Choi, Daewon, et al.
Pubblicazione: (2025)

ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
di: Xiao, Zilin, et al.
Pubblicazione: (2024)

Coupling without Communication and Drafter-Invariant Speculative Decoding
di: Daliri, Majid, et al.
Pubblicazione: (2024)

Recurrent Drafter for Fast Speculative Decoding in Large Language Models
di: Cheng, Yunfei, et al.
Pubblicazione: (2024)

Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters
di: Yi, Euiin, et al.
Pubblicazione: (2024)

SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding
di: Sandler, Jameson, et al.
Pubblicazione: (2025)

OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding
di: Ramakrishnan, Ramchalam Kinattinkara, et al.
Pubblicazione: (2025)

READER: Retrieval-Assisted Drafter for Efficient LLM Inference
di: Divilkovskiy, Maxim, et al.
Pubblicazione: (2025)

Steering Pretrained Drafters during Speculative Decoding
di: Berdoz, Frédéric, et al.
Pubblicazione: (2025)

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
di: An, Li, et al.
Pubblicazione: (2025)

Transition-Oriented Programming: Developing Provably Correct Systems
di: Ding, Yepeng
Pubblicazione: (2020)

SD$^2$: Self-Distilled Sparse Drafters
di: Lasby, Mike, et al.
Pubblicazione: (2025)

Sparser, Faster, Lighter Transformer Language Models
di: Cetin, Edoardo, et al.
Pubblicazione: (2026)

Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation
di: Liu, Zheng, et al.
Pubblicazione: (2024)

Learning Harmonized Representations for Speculative Sampling
di: Zhang, Lefan, et al.
Pubblicazione: (2024)

Adaptive Text Watermark for Large Language Models
di: Liu, Yepeng, et al.
Pubblicazione: (2024)

Speculating LLMs' Chinese Training Data Pollution from Their Tokens
di: Zhang, Qingjie, et al.
Pubblicazione: (2025)

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
di: Cheng, Yiruo, et al.
Pubblicazione: (2024)

LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented Generation
di: Chouhan, Ashish, et al.
Pubblicazione: (2024)

Multi-Candidate Speculative Decoding
di: Yang, Sen, et al.
Pubblicazione: (2024)

VideoStudio: Generating Consistent-Content and Multi-Scene Videos
di: Long, Fuchen, et al.
Pubblicazione: (2024)

Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
di: Liu, Hongyi, et al.
Pubblicazione: (2025)

HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models
di: Xie, Zhinan, et al.
Pubblicazione: (2025)

Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
di: Jin, Tao, et al.
Pubblicazione: (2026)

Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
di: Beutel, Alex, et al.
Pubblicazione: (2024)

Agentic Society: Merging skeleton from real world and texture from Large Language Model
di: Bai, Yuqi, et al.
Pubblicazione: (2024)

Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
di: Wang, Pei-Shuo, et al.
Pubblicazione: (2025)

Towards Lighter and Robust Evaluation for Retrieval Augmented Generation
di: Ispas, Alex-Razvan, et al.
Pubblicazione: (2025)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
di: Liu, Jingyu, et al.
Pubblicazione: (2025)

Two-step Automated Cybercrime Coded Word Detection using Multi-level Representation Learning
di: Kim, Yongyeon, et al.
Pubblicazione: (2024)

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference
di: Zhang, Libo, et al.
Pubblicazione: (2024)

DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting
di: Lv, Kai, et al.
Pubblicazione: (2025)

Flatter Tokens are More Valuable for Speculative Draft Model Training
di: Fan, Jiaming, et al.
Pubblicazione: (2026)

Speculative Decoding for Multi-Sample Inference
di: Li, Yiwei, et al.
Pubblicazione: (2025)

Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward
di: Chavan, Arnav, et al.
Pubblicazione: (2024)

Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
di: Ranaldi, Leonardo, et al.
Pubblicazione: (2023)

Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition
di: Liang, Siyu, et al.
Pubblicazione: (2025)