Image de couverture de livre

CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liang, Yihao, Wang, Ze, Chen, Hao, Sun, Ximeng, Wu, Jialian, Yu, Xiaodong, Liu, Jiang, Barsoum, Emad, Liu, Zicheng, Jha, Niraj K.
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

XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
par: Wang, Xingrui, et autres
Publié: (2025)

KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation
par: Wang, Xingrui, et autres
Publié: (2025)

VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
par: Lin, Jingyang, et autres
Publié: (2026)

Learning from Online Videos at Inference Time for Computer-Use Agents
par: Liu, Yujian, et autres
Publié: (2025)

Latent Visual Reasoning
par: Li, Bangzheng, et autres
Publié: (2025)

Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation
par: Wang, Ze, et autres
Publié: (2025)

ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
par: Guo, Yuxiang, et autres
Publié: (2025)

Unleashing Hour-Scale Video Training for Long Video-Language Understanding
par: Lin, Jingyang, et autres
Publié: (2025)

Agent Laboratory: Using LLM Agents as Research Assistants
par: Schmidgall, Samuel, et autres
Publié: (2025)

Self-Taught Agentic Long Context Understanding
par: Zhuang, Yufan, et autres
Publié: (2025)

DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
par: Huang, Chao, et autres
Publié: (2025)

TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games
par: Mishra, Prakamya, et autres
Publié: (2025)

MOVi: Training-free Text-conditioned Multi-Object Video Generation
par: Rahman, Aimon, et autres
Publié: (2025)

DART: aDaptive Accept RejecT for non-linear top-K subset identification
par: Agarwal, Mridul, et autres
Publié: (2020)

HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
par: Liang, Yihao, et autres
Publié: (2026)

Instella: Fully Open Language Models with Stellar Performance
par: Liu, Jiang, et autres
Publié: (2025)

Reliable Use of Lemmas via Eligibility Reasoning and Section$-$Aware Reinforcement Learning
par: Xu, Zhikun, et autres
Publié: (2026)

Stabilizing Efficient Reasoning with Step-Level Advantage Selection
par: Wang, Han, et autres
Publié: (2026)

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
par: Chen, Hao, et autres
Publié: (2024)

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering
par: Joshi, Vinay, et autres
Publié: (2025)

CaptionQA: Is Your Caption as Useful as the Image Itself?
par: Yang, Shijia, et autres
Publié: (2025)

APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
par: Zhou, Yuzhen, et autres
Publié: (2025)

TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents
par: Zhu, Kaijie, et autres
Publié: (2026)

AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
par: Ray, Pretam, et autres
Publié: (2026)

Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion
par: Singh, Shivam, et autres
Publié: (2026)

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
par: An, Zihao, et autres
Publié: (2026)

SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers
par: Manem, Chaitanya, et autres
Publié: (2025)

SpecVLM: Fast Speculative Decoding in Vision-Language Models
par: Huang, Haiduo, et autres
Publié: (2025)

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
par: Dong, Daize, et autres
Publié: (2026)

DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
par: Singh, Aditya Kumar, et autres
Publié: (2026)

Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
par: Cui, Qinpeng, et autres
Publié: (2024)

An Alternative Trajectory for Generative AI
par: Belova, Margarita, et autres
Publié: (2026)

Uncertainty-Aware Transformers: Conformal Prediction for Language Models
par: Vellore, Abhiram, et autres
Publié: (2026)

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
par: Miao, Zichen, et autres
Publié: (2024)

DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity
par: Zhu, Haowei, et autres
Publié: (2026)

MedLM: Exploring Language Models for Medical Question Answering Systems
par: Yagnik, Niraj, et autres
Publié: (2024)

On the Memorization of Consistency Distillation for Diffusion Models
par: Jiang, Bingqing, et autres
Publié: (2026)

COMFORT: A Continual Fine-Tuning Framework for Foundation Models Targeted at Consumer Healthcare
par: Li, Chia-Hao, et autres
Publié: (2024)

PAGE: Domain-Incremental Adaptation with Past-Agnostic Generative Replay for Smart Healthcare
par: Li, Chia-Hao, et autres
Publié: (2024)

DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors
par: Li, Chia-Hao, et autres
Publié: (2023)