Copertina

CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dumitru, Razvan-Gabriel, Yang, Minglai, Yadav, Vikas, Surdeanu, Mihai
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning I.2.7; I.2.0
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy
di: Dumitru, Razvan-Gabriel, et al.
Pubblicazione: (2024)

Enhancing Transformer RNNs with Multiple Temporal Perspectives
di: Dumitru, Razvan-Gabriel, et al.
Pubblicazione: (2024)

Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels
di: Dumitru, Razvan-Gabriel, et al.
Pubblicazione: (2024)

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
di: Dumitru, Razvan-Gabriel, et al.
Pubblicazione: (2025)

LLMs and the Human Condition
di: Wallis, Peter
Pubblicazione: (2024)

Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors
di: Williamson, Dane, et al.
Pubblicazione: (2025)

ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
di: Deng, Minghang, et al.
Pubblicazione: (2025)

TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
di: Du, Bangde, et al.
Pubblicazione: (2025)

ChemPro: A Progressive Chemistry Benchmark for Large Language Models
di: Baranwal, Aaditya, et al.
Pubblicazione: (2026)

Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval
di: Bayarri-Planas, Jordi, et al.
Pubblicazione: (2024)

A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development
di: Adjovi, Mahounan Pericles, et al.
Pubblicazione: (2026)

Quo Vadis ChatGPT? From Large Language Models to Large Knowledge Models
di: Venkatasubramanian, Venkat, et al.
Pubblicazione: (2024)

QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization
di: Khanna, Danush, et al.
Pubblicazione: (2025)

OpenAI Cribbed Our Tax Example, But Can GPT-4 Really Do Tax?
di: Blair-Stanek, Andrew, et al.
Pubblicazione: (2023)

MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese
di: Teixeira, Tiago, et al.
Pubblicazione: (2026)

Automated Circuit Interpretation via Probe Prompting
di: Birardi, Giuseppe
Pubblicazione: (2025)

SeLeRoSa: Sentence-Level Romanian Satire Detection Dataset
di: Smădu, Răzvan-Alexandru, et al.
Pubblicazione: (2025)

Aspect-Based Sentiment Analysis for Future Tourism Experiences: A BERT-MoE Framework for Persian User Reviews
di: Taskooh, Hamidreza Kazemi, et al.
Pubblicazione: (2026)

The Invisible Coalition Partner: How LLMs Vote When Democracy Gets Concrete
di: Barmettler, Joel
Pubblicazione: (2026)

Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games
di: Wu, Dekun, et al.
Pubblicazione: (2023)

Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA
di: Badshah, Sher, et al.
Pubblicazione: (2024)

Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
di: Goldstein, Daniel, et al.
Pubblicazione: (2026)

Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard
di: Plevris, Vagelis, et al.
Pubblicazione: (2023)

Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
di: Edin, Joakim, et al.
Pubblicazione: (2025)

Prompt Tuned Embedding Classification for Multi-Label Industry Sector Allocation
di: Buchner, Valentin Leonhard, et al.
Pubblicazione: (2023)

NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation
di: Saito, Kei
Pubblicazione: (2025)

Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam
di: Santos, Matheus L. O., et al.
Pubblicazione: (2023)

ALISON: Fast and Effective Stylometric Authorship Obfuscation
di: Xing, Eric, et al.
Pubblicazione: (2024)

NRR-Phi: Text-to-State Mapping for Ambiguity Preservation in LLM Inference
di: Saito, Kei
Pubblicazione: (2026)

Next Token Prediction Is a Dead End for Creativity
di: Olatunji, Ibukun, et al.
Pubblicazione: (2025)

RWKV-7 "Goose" with Expressive Dynamic State Evolution
di: Peng, Bo, et al.
Pubblicazione: (2025)

BabyReasoningBench: Generating Developmentally-Inspired Reasoning Tasks for Evaluating Baby Language Models
di: Dhole, Kaustubh D.
Pubblicazione: (2026)

ACCORD: Closing the Commonsense Measurability Gap
di: Roewer-Després, François, et al.
Pubblicazione: (2024)

Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question
di: Rosales, Rafael, et al.
Pubblicazione: (2025)

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
di: Kaplanski, Pawel
Pubblicazione: (2026)

Incentives or Ontology? A Structural Rebuttal to OpenAI's Hallucination Thesis
di: Ackermann, Richard, et al.
Pubblicazione: (2025)

Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
di: Vegner, Ivan, et al.
Pubblicazione: (2025)

The Drill-Down and Fabricate Test (DDFT): A Protocol for Measuring Epistemic Robustness in Language Models
di: Baxi, Rahul
Pubblicazione: (2025)

Graph Language Models
di: Plenz, Moritz, et al.
Pubblicazione: (2024)

AI-generated stories favour stability over change: homogeneity and cultural stereotyping in narratives generated by gpt-4o-mini
di: Rettberg, Jill Walker, et al.
Pubblicazione: (2025)