Copertina

Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Kecheng, Liu, Ziru, Tao, Xijia, Liu, Hui, Fu, Xinyu, Zhang, Suiyun, Tu, Dandan, Kong, Lingpeng, Liu, Rui, Li, Haoliang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
di: Chen, Kecheng, et al.
Pubblicazione: (2026)

Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
di: Liu, Hui, et al.
Pubblicazione: (2025)

GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
di: Liu, Ziru, et al.
Pubblicazione: (2025)

MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents
di: Tao, Xijia, et al.
Pubblicazione: (2025)

Proxy Compression for Language Modeling
di: Zheng, Lin, et al.
Pubblicazione: (2026)

ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
di: Tao, Xijia, et al.
Pubblicazione: (2024)

Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
di: Liu, Hui, et al.
Pubblicazione: (2026)

Beyond Confidence: The Rhythms of Reasoning in Generative Models
di: Liu, Deyuan, et al.
Pubblicazione: (2026)

TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees
di: Liu, Tianyu, et al.
Pubblicazione: (2026)

DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
di: Wu, Zirui, et al.
Pubblicazione: (2026)

Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling
di: Prange, Jakob, et al.
Pubblicazione: (2021)

Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding
di: Liu, Xin, et al.
Pubblicazione: (2024)

A Reparameterized Discrete Diffusion Model for Text Generation
di: Zheng, Lin, et al.
Pubblicazione: (2023)

Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules
di: Mohamed, Amr, et al.
Pubblicazione: (2025)

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
di: Zhao, Xueliang, et al.
Pubblicazione: (2024)

CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification
di: Chen, Jinpeng, et al.
Pubblicazione: (2026)

Locally Coherent Parallel Decoding in Diffusion Language Models
di: Hersche, Michael, et al.
Pubblicazione: (2026)

Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding
di: Luo, Xiangzhong, et al.
Pubblicazione: (2026)

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
di: Ye, Jiacheng, et al.
Pubblicazione: (2024)

Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models
di: Fang, Liancheng, et al.
Pubblicazione: (2026)

Dream 7B: Diffusion Large Language Models
di: Ye, Jiacheng, et al.
Pubblicazione: (2025)

Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks
di: Li, Qintong, et al.
Pubblicazione: (2023)

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
di: Zhu, Wenhao, et al.
Pubblicazione: (2023)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
di: Wang, Xu, et al.
Pubblicazione: (2026)

Efficient Reasoning via Reward Model
di: Wang, Yuhao, et al.
Pubblicazione: (2025)

Adaptive Draft-Verification for Efficient Large Language Model Decoding
di: Liu, Xukun, et al.
Pubblicazione: (2024)

Relay Decoding: Concatenating Large Language Models for Machine Translation
di: Fu, Chengpeng, et al.
Pubblicazione: (2024)

Interpretable Multimodal Misinformation Detection with Logic Reasoning
di: Liu, Hui, et al.
Pubblicazione: (2023)

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism
di: Wei, Zhepei, et al.
Pubblicazione: (2025)

PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models
di: Zhao, Xueliang, et al.
Pubblicazione: (2025)

Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
di: Liu, Hui, et al.
Pubblicazione: (2026)

CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models
di: Khandelwal, Anant, et al.
Pubblicazione: (2025)

Non-myopic Generation of Language Models for Reasoning and Planning
di: Ma, Chang, et al.
Pubblicazione: (2024)

AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference
di: Lu, Kuan-Wei, et al.
Pubblicazione: (2025)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
di: Ye, Jiacheng, et al.
Pubblicazione: (2024)

Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions
di: Wu, Zirui, et al.
Pubblicazione: (2025)

CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models
di: Liang, Yihao, et al.
Pubblicazione: (2026)

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?
di: Li, Pengxiang, et al.
Pubblicazione: (2026)

Teaching Language Models to Critique via Reinforcement Learning
di: Xie, Zhihui, et al.
Pubblicazione: (2025)

Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
di: Cao, Mingyu, et al.
Pubblicazione: (2026)