Cover Image

Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Jucheng, Ro, Yeonju
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration
by: Shen, Jucheng, et al.
Published: (2025)

One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer
by: Shen, Jucheng, et al.
Published: (2026)

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention
by: Ro, Yeonju, et al.
Published: (2025)

Beyond Static Uncertainty: Modeling Temporal Uncertainty Dynamics for Probabilistic Time Series Forecasting
by: Wang, Yijun, et al.
Published: (2026)

One-Shot Federated Learning with Classifier-Free Diffusion Models
by: Zaland, Obaidullah, et al.
Published: (2025)

DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning
by: Hu, Jucheng, et al.
Published: (2025)

Smooth Dynamic Cutoffs for Machine Learning Interatomic Potentials
by: Han, Kevin, et al.
Published: (2026)

FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping
by: Jaiswal, Ajay, et al.
Published: (2024)

Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
by: Li, Fengzhi, et al.
Published: (2026)

Beyond Static Tools: Evaluating Large Language Models for Cryptographic Misuse Detection
by: Masood, Zohaib, et al.
Published: (2024)

Wearable Foundation Models Should Go Beyond Static Encoders
by: Wu, Yu Yvonne, et al.
Published: (2026)

Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
by: Cai, Ruisi, et al.
Published: (2024)

DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy
by: Park, Sungjae, et al.
Published: (2025)

ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
by: Meng, Xiang, et al.
Published: (2024)

One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
by: Yang, Mingzhao, et al.
Published: (2023)

DLM-One: Diffusion Language Models for One-Step Sequence Generation
by: Chen, Tianqi, et al.
Published: (2025)

Scaling Beyond Masked Diffusion Language Models
by: Sahoo, Subham Sekhar, et al.
Published: (2026)

Beyond Static Models: Hypernetworks for Adaptive and Generalizable Forecasting in Complex Parametric Dynamical Systems
by: Vlachas, Pantelis R., et al.
Published: (2025)

Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations
by: Barami, Tal, et al.
Published: (2025)

Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models
by: Mendieta, Matias, et al.
Published: (2024)

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
by: Xu, Xiang, et al.
Published: (2025)

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
by: Oldfield, James, et al.
Published: (2025)

DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models
by: Zhang, Shenyu, et al.
Published: (2025)

One-Shot Hierarchical Federated Clustering
by: Cai, Shenghong, et al.
Published: (2026)

Threshold-Guided Optimization for Visual Generative Models
by: Bai, Jinbin, et al.
Published: (2026)

The Evaluation Game: Beyond Static LLM Benchmarking
by: Wang, Paul, et al.
Published: (2026)

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs
by: Zhao, Yusheng, et al.
Published: (2025)

ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning
by: Su, Mingluo, et al.
Published: (2026)

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
by: Meng, Xiang, et al.
Published: (2024)

Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies
by: Lu, Muyun, et al.
Published: (2026)

FeatureCuts: Feature Selection for Large Data by Optimizing the Cutoff
by: Hu, Andy, et al.
Published: (2025)

Dynamic Regret Reduces to Kernelized Static Regret
by: Jacobsen, Andrew, et al.
Published: (2025)

Federated One-Shot Ensemble Clustering
by: Duan, Rui, et al.
Published: (2024)

Multiresolution Analysis and Statistical Thresholding on Dynamic Networks
by: Romero, Raphaël, et al.
Published: (2025)

GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory
by: Baek, David D., et al.
Published: (2024)

LoRA Diffusion: Zero-Shot LoRA Synthesis for Diffusion Model Personalization
by: Smith, Ethan, et al.
Published: (2024)

Zero-Shot Uncertainty Quantification using Diffusion Probabilistic Models
by: Shu, Dule, et al.
Published: (2024)

Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models
by: Benita, Roi, et al.
Published: (2026)

Multi-Modal One-Shot Federated Ensemble Learning for Medical Data with Vision Large Language Model
by: Wang, Naibo, et al.
Published: (2025)

SymDrift: One-Shot Generative Modeling under Symmetries
by: Darouich, Samir, et al.
Published: (2026)