Image de couverture de livre

Improving Diffusion Language Model Decoding through Joint Search in Generation Order and Token Space

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Yangyi, Feng, Tianjian, Han, Jiaqi, Wang, Wen, Chen, Tianlang, Shen, Chunhua, Leskovec, Jure, Ermon, Stefano
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance
par: Chen, Tianlang, et autres
Publié: (2025)

Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
par: Chen, Tianlang, et autres
Publié: (2026)

Energy-Based Diffusion Language Models for Text Generation
par: Xu, Minkai, et autres
Publié: (2024)

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
par: Zhong, Linhao, et autres
Publié: (2026)

RelGNN: Composite Message Passing for Relational Deep Learning
par: Chen, Tianlang, et autres
Publié: (2025)

Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models
par: Wang, Wen, et autres
Publié: (2025)

TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
par: Shi, Juntong, et autres
Publié: (2024)

Large Language Models are Good Relational Learners
par: Wu, Fang, et autres
Publié: (2025)

Reverse Image Retrieval Cues Parametric Memory in Multimodal LLMs
par: Xu, Jialiang, et autres
Publié: (2024)

Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding
par: Guo, Gabe, et autres
Publié: (2025)

RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models
par: Hudovernik, Valter, et autres
Publié: (2025)

$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization
par: Han, Jiaqi, et autres
Publié: (2024)

Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution
par: Wu, Tailin, et autres
Publié: (2024)

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
par: Wu, Jialiang, et autres
Publié: (2025)

MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
par: Li, Liyang, et autres
Publié: (2026)

Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
par: Lou, Aaron, et autres
Publié: (2023)

Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
par: Christopher, Jacob K, et autres
Publié: (2024)

Jointly Reinforcing Diversity and Quality in Language Model Generations
par: Li, Tianjian, et autres
Publié: (2025)

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models
par: Yao, Jui-Ming, et autres
Publié: (2025)

Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective
par: Ou, Jingyang, et autres
Publié: (2025)

Equivariant Graph Neural Operator for Modeling 3D Dynamics
par: Xu, Minkai, et autres
Publié: (2024)

Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
par: Zhong, Linhao, et autres
Publié: (2026)

TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees
par: Liu, Tianyu, et autres
Publié: (2026)

Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training
par: Chen, Yangyi, et autres
Publié: (2025)

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
par: Manvi, Rohin, et autres
Publié: (2024)

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
par: Dang, Meihua, et autres
Publié: (2026)

Neural Search Space in Gboard Decoder
par: Zhang, Yanxiang, et autres
Publié: (2024)

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
par: Li, Tianjian, et autres
Publié: (2025)

Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering
par: Li, Yangyi, et autres
Publié: (2025)

EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
par: Cheong, Minsoo, et autres
Publié: (2026)

One Token Is Enough: Improving Diffusion Language Models with a Sink Token
par: Zhang, Zihou, et autres
Publié: (2026)

Diffusion Language Models Know the Answer Before Decoding
par: Li, Pengxiang, et autres
Publié: (2025)

Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes
par: Bereket, Michael, et autres
Publié: (2025)

Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
par: Gu, Siyi, et autres
Publié: (2024)

Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoders
par: Shi, Hao, et autres
Publié: (2023)

Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models
par: Kukić, Matija Luka, et autres
Publié: (2026)

Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference
par: Qin, Zongyue, et autres
Publié: (2024)

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
par: Xu, Shicheng, et autres
Publié: (2024)

BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
par: Zhuang, Shaobin, et autres
Publié: (2026)

Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training
par: Feng, Xidong, et autres
Publié: (2023)