Image de couverture de livre

T$^\star$: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xia, Hanchen, Chen, Baoyou, Ge, Yutang, Zhao, Guojiang, Zhu, Siyu
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

Latent Poincaré Shaping for Agentic Reinforcement Learning
par: Xia, Hanchen, et autres
Publié: (2026)

BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation
par: Chen, Baoyou, et autres
Publié: (2026)

TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
par: Chen, Lingjie, et autres
Publié: (2026)

Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step
par: Yang, Jingyi, et autres
Publié: (2025)

Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router
par: Shao, Chenyang, et autres
Publié: (2025)

MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
par: Zhao, Guojiang, et autres
Publié: (2025)

$R^3$: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks
par: Xia, Hanchen, et autres
Publié: (2024)

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

Scaling Beyond Masked Diffusion Language Models
par: Sahoo, Subham Sekhar, et autres
Publié: (2026)

TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Models
par: Saini, Shreshth, et autres
Publié: (2026)

Advancing Block Diffusion Language Models for Test-Time Scaling
par: Lu, Yi, et autres
Publié: (2026)

d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
par: Zhao, Siyan, et autres
Publié: (2025)

LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models
par: Su, Yupeng, et autres
Publié: (2024)

Scaling up Masked Diffusion Models on Text
par: Nie, Shen, et autres
Publié: (2024)

Block Circulant Adapter for Large Language Models
par: Ding, Xinyu, et autres
Publié: (2025)

Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules
par: Mohamed, Amr, et autres
Publié: (2025)

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
par: Chen, Kecheng, et autres
Publié: (2026)

Activation Steering for Masked Diffusion Language Models
par: Shnaidman, Adi, et autres
Publié: (2025)

Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models
par: Zou, Shun, et autres
Publié: (2026)

Masked Diffusion Language Models with Frequency-Informed Training
par: Kosmopoulou, Despoina, et autres
Publié: (2025)

LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models
par: Xi, Haocheng, et autres
Publié: (2026)

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
par: Zhang, Jiebin, et autres
Publié: (2026)

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
par: Wang, Chenyu, et autres
Publié: (2025)

Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data
par: Xia, Han, et autres
Publié: (2024)

Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents
par: Shao, Chenyang, et autres
Publié: (2025)

Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
par: Huang, Zemin, et autres
Publié: (2025)

Embedding Inversion via Conditional Masked Diffusion Language Models
par: Xiao, Han
Publié: (2026)

Edit-Based Refinement for Parallel Masked Diffusion Language Models
par: Ren, Houxing, et autres
Publié: (2026)

Diffusion-State Policy Optimization for Masked Diffusion Language Models
par: Oba, Daisuke, et autres
Publié: (2026)

Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling
par: Padole, Tejomay Kishor, et autres
Publié: (2025)

LLaMA Pro: Progressive LLaMA with Block Expansion
par: Wu, Chengyue, et autres
Publié: (2024)

Soft-Masked Diffusion Language Models
par: Hersche, Michael, et autres
Publié: (2025)

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
par: Wang, Yinjie, et autres
Publié: (2025)

Where-to-Unmask: Ground-Truth-Guided Unmasking Order Learning for Masked Diffusion Language Models
par: Asano, Hikaru, et autres
Publié: (2026)

PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning
par: Lu, Keer, et autres
Publié: (2025)

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
par: He, Xiang, et autres
Publié: (2026)

Variational Masked Diffusion Models
par: Zhang, Yichi, et autres
Publié: (2025)

Diffutron: A Masked Diffusion Language Model for Turkish Language
par: Kocabay, Şuayp Talha, et autres
Publié: (2026)

Timestep-Aware Block Masking for Efficient Diffusion Model Inference
par: He, Haodong, et autres
Publié: (2026)

DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
par: Monsefi, Amin Karimi, et autres
Publié: (2026)