Cover Image

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Goel, Raghavv, Gagrani, Mukul, Lee, Mingu, Lott, Chris
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction
by: Goel, Raghavv, et al.
Published: (2025)

On Speculative Decoding for Multimodal Large Language Models
by: Gagrani, Mukul, et al.
Published: (2024)

Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
by: Goel, Raghavv, et al.
Published: (2024)

ConFu: Contemplate the Future for Better Speculative Sampling
by: Qin, Zongyue, et al.
Published: (2026)

Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement
by: Jeon, Wonseok, et al.
Published: (2024)

VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs
by: Goel, Raghavv, et al.
Published: (2025)

A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs
by: Goel, Raghavv, et al.
Published: (2026)

Spiffy: Multiplying Diffusion LLM Acceleration via Lossless Speculative Decoding
by: Agrawal, Sudhanshu, et al.
Published: (2025)

Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity
by: Gautam, Aayush, et al.
Published: (2026)

KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
by: Park, Junyoung, et al.
Published: (2025)

AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability
by: Agrawal, Sudhanshu, et al.
Published: (2024)

Harmonic Token Projection (HTP): A Vocabulary-Free, Training-Free, Deterministic, and Reversible Embedding Methodology
by: Schmitz, Tcharlies
Published: (2025)

Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction
by: Qian, Junlang, et al.
Published: (2025)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
by: Deiseroth, Björn, et al.
Published: (2024)

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
by: Fu, Yuchen, et al.
Published: (2024)

Weight Tying Biases Token Embeddings Towards the Output Space
by: Lopardo, Antonio, et al.
Published: (2026)

DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval
by: Lee, Taegyeong, et al.
Published: (2026)

Efficient Pre-Training with Token Superposition
by: Peng, Bowen, et al.
Published: (2026)

Pre-Training Curriculum for Multi-Token Prediction in Language Models
by: Aynetdinov, Ansar, et al.
Published: (2025)

Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference
by: Wu, Zimeng, et al.
Published: (2026)

Attention with Trained Embeddings Provably Selects Important Tokens
by: Wu, Diyuan, et al.
Published: (2025)

Multi-Token Prediction via Self-Distillation
by: Kirchenbauer, John, et al.
Published: (2026)

Efficient Document Parsing via Parallel Token Prediction
by: Li, Lei, et al.
Published: (2026)

Do BERT Embeddings Encode Narrative Dimensions? A Token-Level Probing Analysis of Time, Space, Causality, and Character in Fiction
by: Bei, Beicheng, et al.
Published: (2026)

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
by: Goddard, Charles, et al.
Published: (2025)

SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism
by: Bhatnagar, Priyansh, et al.
Published: (2024)

Quantifying Positional Biases in Text Embedding Models
by: Lee, Reagan J., et al.
Published: (2024)

Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs
by: Tan, Wenhui, et al.
Published: (2026)

Reasoning Bias of Next Token Prediction Training
by: Lin, Pengxiao, et al.
Published: (2025)

ETT-CKGE: Efficient Task-driven Tokens for Continual Knowledge Graph Embedding
by: Zhu, Lijing, et al.
Published: (2025)

Locality Matters for Training-Free Audio Token Compression in Audio-Language Models
by: Luo, Jiale, et al.
Published: (2026)

Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing
by: Bedratyuk, Leonid
Published: (2026)

How Much is Enough? The Diminishing Returns of Tokenization Training Data
by: Reddy, Varshini, et al.
Published: (2025)

Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking
by: Zhang, Xiaokang, et al.
Published: (2024)

A General and Efficient Training for Transformer via Token Expansion
by: Huang, Wenxuan, et al.
Published: (2024)

BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training
by: Chizhov, Pavel, et al.
Published: (2024)

Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
by: Si, Jianfeng, et al.
Published: (2025)

LLM-Augmented Semantic Steering of Text Embedding Projection Spaces
by: Liu, Wei, et al.
Published: (2026)

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
by: Yang, Wang, et al.
Published: (2026)

ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations
by: Wang, Zijian, et al.
Published: (2025)