Copertina

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jin, Xiangqi, Wang, Yuxuan, Gao, Yifeng, Wen, Zichen, Qi, Biqing, Liu, Dongrui, Zhang, Linfeng
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 Speculative Decoding for Diffusion Large Language Models
di: Gao, Yifeng, et al.
Pubblicazione: (2025)

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
di: Huang, Jianuo, et al.
Pubblicazione: (2025)

Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles
di: Wei, Qingyan, et al.
Pubblicazione: (2025)

Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way
di: Yang, Yicun, et al.
Pubblicazione: (2025)

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
di: Wen, Zichen, et al.
Pubblicazione: (2025)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
di: Wen, Zichen, et al.
Pubblicazione: (2025)

GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction
di: Li, Xuelin, et al.
Pubblicazione: (2025)

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
di: Wen, Zichen, et al.
Pubblicazione: (2025)

Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning
di: Wang, Shaobo, et al.
Pubblicazione: (2025)

AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
di: He, Peize, et al.
Pubblicazione: (2025)

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
di: Wang, Yue, et al.
Pubblicazione: (2025)

Towards Building Specialized Generalist AI with System 1 and System 2 Fusion
di: Zhang, Kaiyan, et al.
Pubblicazione: (2024)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
di: Qian, Chen, et al.
Pubblicazione: (2025)

SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation
di: Li, Gengyang, et al.
Pubblicazione: (2026)

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
di: Ma, Qianli, et al.
Pubblicazione: (2025)

Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
di: Zhou, Yufa, et al.
Pubblicazione: (2025)

FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
di: Zhang, Yaojie, et al.
Pubblicazione: (2026)

Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages
di: Li, Haolin, et al.
Pubblicazione: (2025)

On the Universal Truthfulness Hyperplane Inside LLMs
di: Liu, Junteng, et al.
Pubblicazione: (2024)

Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
di: Yang, Junyao, et al.
Pubblicazione: (2026)

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
di: Chen, Xingyu, et al.
Pubblicazione: (2024)

ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy
di: Li, Gengyang, et al.
Pubblicazione: (2025)

DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
di: Yang, Jingyi, et al.
Pubblicazione: (2026)

DiffuMask: Diffusion Language Model for Token-level Prompt Pruning
di: Zheng, Caleb, et al.
Pubblicazione: (2026)

SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
di: Huang, Yue, et al.
Pubblicazione: (2025)

Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles
di: Chen, Qi, et al.
Pubblicazione: (2024)

Structured Prompt Language: Declarative Context Management for LLMs
di: Gong, Wen G.
Pubblicazione: (2026)

TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts
di: Xie, Yuxuan, et al.
Pubblicazione: (2024)

Estranged Predictions: Measuring Semantic Category Disruption with Masked Language Modelling
di: Liu, Yuxuan, et al.
Pubblicazione: (2025)

ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs
di: Wen, Pengcheng, et al.
Pubblicazione: (2025)

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
di: Jia, Xinda, et al.
Pubblicazione: (2025)

Inside-Out: Hidden Factual Knowledge in LLMs
di: Gekhman, Zorik, et al.
Pubblicazione: (2025)

Shifting AI Efficiency From Model-Centric to Data-Centric Compression
di: Liu, Xuyang, et al.
Pubblicazione: (2025)

REEF: Representation Encoding Fingerprints for Large Language Models
di: Zhang, Jie, et al.
Pubblicazione: (2024)

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
di: Liu, Runze, et al.
Pubblicazione: (2025)

CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
di: Zhang, Kaiyan, et al.
Pubblicazione: (2024)

AIDBench: A benchmark for evaluating the authorship identification capability of large language models
di: Wen, Zichen, et al.
Pubblicazione: (2024)

How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning
di: Yuan, Jiahao, et al.
Pubblicazione: (2026)

On the Role of Discreteness in Diffusion LLMs
di: Jin, Ziqi, et al.
Pubblicazione: (2025)

Constrained Code Generation with Discrete Diffusion
di: Shao, Lize, et al.
Pubblicazione: (2026)