Image de couverture de livre

MARS: Enabling Autoregressive Models Multi-Token Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jin, Ziqi, Wang, Lei, Luo, Ziwei, Sun, Aixin
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search
par: Wang, Ziqi, et autres
Publié: (2025)

On the Role of Discreteness in Diffusion LLMs
par: Jin, Ziqi, et autres
Publié: (2025)

Enabling Autoregressive Models to Fill In Masked Tokens
par: Israel, Daniel, et autres
Publié: (2025)

GCRE-GPT: A Generative Model for Comparative Relation Extraction
par: Wang, Yequan, et autres
Publié: (2023)

PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking
par: Pooja, KM, et autres
Publié: (2025)

Cultural Value Differences of LLMs: Prompt, Language, and Model Size
par: Zhong, Qishuai, et autres
Publié: (2024)

MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset
par: Wang, Weiqi, et autres
Publié: (2024)

Benchmarking and Rethinking Knowledge Editing for Large Language Models
par: He, Guoxiu, et autres
Publié: (2025)

Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution
par: Li, Xinze, et autres
Publié: (2023)

Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning
par: He, Guoxiu, et autres
Publié: (2025)

Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data
par: Wang, Jiapeng, et autres
Publié: (2025)

MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
par: Li, Pengfei, et autres
Publié: (2026)

On Context Utilization in Summarization with Large Language Models
par: Ravaut, Mathieu, et autres
Publié: (2023)

Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
par: Li, Xinze, et autres
Publié: (2026)

FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation
par: He, Siyang, et autres
Publié: (2026)

MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization
par: Zhang, Jian, et autres
Publié: (2025)

MARS: Multilingual Aspect-centric Review Summarisation
par: Mukku, Sandeep Sricharan, et autres
Publié: (2024)

Problematic Tokens: Tokenizer Bias in Large Language Models
par: Yang, Jin, et autres
Publié: (2024)

SOUP: Token-level Single-sample Mix-policy Reinforcement Learning for Large Language Models
par: Yang, Lei, et autres
Publié: (2026)

Direct Multi-Token Decoding
par: Luo, Xuan, et autres
Publié: (2025)

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
par: Yang, Chenghao, et autres
Publié: (2025)

MARS: Memory-Enhanced Agents with Reflective Self-improvement
par: Liang, Xuechen, et autres
Publié: (2025)

Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models
par: Xu, Zihao, et autres
Publié: (2026)

Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models
par: Zhang, Fan, et autres
Publié: (2024)

The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models
par: Fan, Siqi, et autres
Publié: (2025)

MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
par: Bakman, Yavuz Faruk, et autres
Publié: (2024)

Long Context vs. RAG for LLMs: An Evaluation and Revisits
par: Li, Xinze, et autres
Publié: (2024)

Differences in Text Generated by Diffusion and Autoregressive Language Models
par: Zhang, Zeyang, et autres
Publié: (2026)

Lossless Token Sequence Compression via Meta-Tokens
par: Harvill, John, et autres
Publié: (2025)

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
par: Dragunov, Nikita, et autres
Publié: (2025)

Open-domain Implicit Format Control for Large Language Model Generation
par: Yao, Yiqun, et autres
Publié: (2024)

Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!
par: Ma, Yubo, et autres
Publié: (2023)

MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning
par: Chen, Guoxin, et autres
Publié: (2025)

FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
par: Wang, Hui, et autres
Publié: (2025)

MARS: toward more efficient multi-agent collaboration for LLM reasoning
par: Wang, Xiao, et autres
Publié: (2025)

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
par: Song, Yakun, et autres
Publié: (2025)

Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness
par: Yang, Zhipeng, et autres
Publié: (2026)

Autoregressive Models Rival Diffusion Models at ANY-ORDER Generation
par: Du, Tianqi, et autres
Publié: (2026)

Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs
par: Pramanik, Vishal, et autres
Publié: (2026)

Multi-Token Attention
par: Golovneva, Olga, et autres
Publié: (2025)