Copertina

Few-Step Diffusion Language Models via Trajectory Self-Distillation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Tunyu, Zhang, Xinxi, Han, Ligong, Shi, Haizhou, He, Xiaoxiao, Li, Zhuowei, Wang, Hao, Xu, Kai, Srivastava, Akash, Mao, Chengzhi, Pavlovic, Vladimir, Metaxas, Dimitris N.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Overcoming the Curvature Bottleneck in MeanFlow
di: Zhang, Xinxi, et al.
Pubblicazione: (2025)

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
di: Zhang, Tunyu, et al.
Pubblicazione: (2025)

BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
di: Wang, Yibin, et al.
Pubblicazione: (2024)

Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
di: Zhang, Xinxi, et al.
Pubblicazione: (2024)

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
di: Dao, Quan, et al.
Pubblicazione: (2024)

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
di: Han, Ligong, et al.
Pubblicazione: (2026)

Score-Guided Diffusion for 3D Human Recovery
di: Stathopoulos, Anastasis, et al.
Pubblicazione: (2024)

SNLP: Layer-Parallel Inference via Structured Newton Corrections
di: Han, Ligong, et al.
Pubblicazione: (2026)

SQuat: Subspace-orthogonal KV Cache Quantization
di: Wang, Hao, et al.
Pubblicazione: (2025)

Implicit In-context Learning
di: Li, Zhuowei, et al.
Pubblicazione: (2024)

SINE: SINgle Image Editing with Text-to-Image Diffusion Models
di: Zhang, Zhixing, et al.
Pubblicazione: (2022)

Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models
di: Zhao, Yicong, et al.
Pubblicazione: (2025)

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
di: Shi, Haizhou, et al.
Pubblicazione: (2024)

Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
di: Chatzoudis, Gerasimos, et al.
Pubblicazione: (2025)

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
di: Li, Zhuowei, et al.
Pubblicazione: (2025)

Rate-My-LoRA: Efficient and Adaptive Federated Model Tuning for Cardiac MRI Segmentation
di: He, Xiaoxiao, et al.
Pubblicazione: (2025)

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
di: Liu, Tao, et al.
Pubblicazione: (2026)

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models
di: Wang, Hengyi, et al.
Pubblicazione: (2024)

Hopscotch: Discovering and Skipping Redundancies in Language Models
di: Eyceoz, Mustafa, et al.
Pubblicazione: (2025)

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
di: Chen, Hansheng, et al.
Pubblicazione: (2025)

Few-Step Diffusion via Score identity Distillation
di: Zhou, Mingyuan, et al.
Pubblicazione: (2025)

PAC Privacy Preserving Diffusion Models
di: Xu, Qipan, et al.
Pubblicazione: (2023)

MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
di: Dao, Quan, et al.
Pubblicazione: (2026)

Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
di: Gao, Yunhe, et al.
Pubblicazione: (2023)

Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
di: Chatzoudis, Gerasimos, et al.
Pubblicazione: (2026)

Evidence Over Plans: Online Trajectory Verification for Skill Distillation
di: Zhou, Yang, et al.
Pubblicazione: (2026)

ReDiF: Reinforced Distillation for Few Step Diffusion
di: Tighkhorshid, Amirhossein, et al.
Pubblicazione: (2025)

Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation
di: Wang, Chuhan, et al.
Pubblicazione: (2026)

One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow
di: Jutras-Dube, Pascal, et al.
Pubblicazione: (2025)

Infinite Mask Diffusion for Few-Step Distillation
di: Yoo, Jaehoon, et al.
Pubblicazione: (2026)

PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation
di: Mo, Wenyi, et al.
Pubblicazione: (2025)

LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
di: Jin, Can, et al.
Pubblicazione: (2025)

Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
di: Monsefi, Amin Karimi, et al.
Pubblicazione: (2026)

DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
di: He, Xiaoxiao, et al.
Pubblicazione: (2024)

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
di: Li, Ran, et al.
Pubblicazione: (2025)

Distilling ODE Solvers of Diffusion Models into Smaller Steps
di: Kim, Sanghwan, et al.
Pubblicazione: (2023)

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
di: Wu, Zhuguanyu, et al.
Pubblicazione: (2026)

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
di: Jin, Can, et al.
Pubblicazione: (2026)

Learning Few-Step Diffusion Models by Trajectory Distribution Matching
di: Luo, Yihong, et al.
Pubblicazione: (2025)

Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
di: Dang, Meihua, et al.
Pubblicazione: (2025)