On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Ziseok, Hwang, Minyeong, Lee, Wooyeol, Jo, Sanghyun, Ko, Jihyung, Park, Young Bin, Choi, Jae-Mun, Yang, Eunho, Kim, Kyungsu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ISAC: Training-Free Instance-to-Semantic Attention Control for Improving Multi-Instance Generation
by: Jo, Sanghyun, et al.
Published: (2025)

TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
by: Jo, Sanghyun, et al.
Published: (2025)

HybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generation
by: Hwang, Minyeong, et al.
Published: (2025)

Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing
by: Kim, Joowon, et al.
Published: (2025)

TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
by: Jo, Sanghyun, et al.
Published: (2024)

DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation
by: Jo, Sanghyun, et al.
Published: (2024)

EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
by: Jo, Sanghyun, et al.
Published: (2025)

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation
by: Jo, Sanghyun, et al.
Published: (2025)

Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images
by: Kim, JungEun, et al.
Published: (2024)

One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation
by: Jo, Sanghyun, et al.
Published: (2026)

OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment
by: Park, Junhyun, et al.
Published: (2025)

Automatic Channel Pruning for Multi-Head Attention
by: Lee, Eunho, et al.
Published: (2024)

DiffuseSlide: Training-Free High Frame Rate Video Generation Diffusion
by: Hwang, Geunmin, et al.
Published: (2025)

KoBLEX: Open Legal Question Answering with Multi-hop Reasoning
by: Lee, Jihyung, et al.
Published: (2025)

Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
by: Lee, Sanghyun, et al.
Published: (2025)

CountSteer: Steering Attention for Object Counting in Diffusion Models
by: Boo, Hyemin, et al.
Published: (2025)

Systematic Vulnerability Audit of Post-Hoc XAI under Common Corruptions: A Factor Analysis Across Vision Benchmarks
by: Kim, Minyeong
Published: (2026)

Systematic Vulnerability Audit of Post-Hoc XAI under Common Corruptions: A Factor Analysis Across Vision Benchmarks
by: Kim, Minyeong
Published: (2026)

Systematic Vulnerability Audit of Post-Hoc XAI under Common Corruptions: Analysis Pipeline
by: Kim, Minyeong
Published: (2026)

DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection
by: Ko, Donggeun, et al.
Published: (2024)

Programmable Electrochemical Thermopower via Cation Storage Mode and Structural Order
by: Eunho Choi, et al.
Published: (2026)

Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration
by: Choi, Seungyeon, et al.
Published: (2025)

6G-Enabled Digital Twin Framework for Real-Time Cyber-Physical Systems: An Experimental Validation with Industrial Bearing Fault Detection
by: Chakma, Vaskar, et al.
Published: (2025)

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement
by: Lee, Sanghyun, et al.
Published: (2025)

Representation Shift: Unifying Token Compression with FlashAttention
by: Choi, Joonmyung, et al.
Published: (2025)

HalLoc: Token-level Localization of Hallucinations for Vision Language Models
by: Park, Eunkyu, et al.
Published: (2025)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
by: Kim, Sanghyun, et al.
Published: (2024)

EVT: Efficient View Transformation for Multi-Modal 3D Object Detection
by: Lee, Yongjin, et al.
Published: (2024)

REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
by: Lee, Hankyeol, et al.
Published: (2026)

Forecasting Labor Demand: Predicting JOLT Job Openings using Deep Learning Model
by: Kim, Kyungsu
Published: (2025)

Unemployment Dynamics Forecasting with Machine Learning Regression Models
by: Kim, Kyungsu
Published: (2025)

DOSE : Drum One-Shot Extraction from Music Mixture
by: Hwang, Suntae, et al.
Published: (2025)

LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction
by: Piao, Shengmin, et al.
Published: (2025)

Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
by: Lee, Eunho, et al.
Published: (2026)

MRNet: Multifaceted Resilient Networks for Medical Image-to-Image Translation
by: Lee, Hyojeong, et al.
Published: (2024)

VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection
by: Ahn, Sunghyun, et al.
Published: (2024)

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
by: An, Sohyun, et al.
Published: (2023)

On a possible approach to the Twin Prime Conjecture
by: Lee, Eunho
Published: (2025)

DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
by: Choi, Joonmyung, et al.
Published: (2026)

Temporal Graph Learning Recurrent Neural Network for Traffic Forecasting
by: Lee, Sanghyun, et al.
Published: (2024)