Copertina

Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ou, Jingyang, Han, Jiaqi, Xu, Minkai, Xu, Shaoxuan, Xie, Jianwen, Ermon, Stefano, Wu, Yi, Li, Chongxuan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents
di: Zhao, Jiahao, et al.
Pubblicazione: (2026)

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
di: Yang, Ling, et al.
Pubblicazione: (2024)

TFG: Unified Training-Free Guidance for Diffusion Models
di: Ye, Haotian, et al.
Pubblicazione: (2024)

$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization
di: Han, Jiaqi, et al.
Pubblicazione: (2024)

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
di: Manvi, Rohin, et al.
Pubblicazione: (2024)

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance
di: Chen, Tianlang, et al.
Pubblicazione: (2025)

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
di: Wu, Yuheng, et al.
Pubblicazione: (2025)

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
di: Tian, Yuchuan, et al.
Pubblicazione: (2025)

Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL
di: Mao, Hanyi, et al.
Pubblicazione: (2025)

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
di: Cundy, Chris, et al.
Pubblicazione: (2023)

MADiff: Offline Multi-agent Learning with Diffusion Models
di: Zhu, Zhengbang, et al.
Pubblicazione: (2023)

Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation
di: Wan, Yixin, et al.
Pubblicazione: (2023)

Contextualized Diffusion Models for Text-Guided Image and Video Generation
di: Yang, Ling, et al.
Pubblicazione: (2024)

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
di: Li, Jia-Nan, et al.
Pubblicazione: (2025)

The Principles of Diffusion Models
di: Lai, Chieh-Hsin, et al.
Pubblicazione: (2025)

Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs
di: Pan, Xu, et al.
Pubblicazione: (2025)

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
di: Gao, Jiaxuan, et al.
Pubblicazione: (2025)

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
di: Yang, Zhihe, et al.
Pubblicazione: (2025)

Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models
di: Zhao, Juntu, et al.
Pubblicazione: (2024)

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
di: Cen, Zhepeng, et al.
Pubblicazione: (2025)

Geometric Trajectory Diffusion Models
di: Han, Jiaqi, et al.
Pubblicazione: (2024)

Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective
di: Yang, Zhuoyi, et al.
Pubblicazione: (2025)

Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs
di: Ma, Huanhuan, et al.
Pubblicazione: (2025)

Divergence Minimization Preference Optimization for Diffusion Model Alignment
di: Li, Binxu, et al.
Pubblicazione: (2025)

Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
di: Han, Chao, et al.
Pubblicazione: (2025)

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
di: Lin, Haokun, et al.
Pubblicazione: (2025)

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

IPED: An Implicit Perspective for Relational Triple Extraction based on Diffusion Model
di: Zhao, Jianli, et al.
Pubblicazione: (2024)

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
di: Gao, Jiaxuan, et al.
Pubblicazione: (2026)

Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
di: Xu, Yuzhuang, et al.
Pubblicazione: (2026)

GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
di: Bai, Yuyang, et al.
Pubblicazione: (2026)

Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives
di: Sun, Qiushi, et al.
Pubblicazione: (2023)

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
di: Wei, Zhepei, et al.
Pubblicazione: (2025)

GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters
di: Zhao, Wanjia, et al.
Pubblicazione: (2025)

Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games
di: Zhao, Juntu, et al.
Pubblicazione: (2025)

AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
di: Qing, Liu, et al.
Pubblicazione: (2026)

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
di: Guo, Yiran, et al.
Pubblicazione: (2025)

MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation
di: Li, Guoyi, et al.
Pubblicazione: (2026)

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation
di: Zhou, Yuhang, et al.
Pubblicazione: (2024)