Copertina

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Pengxiang, Yan, Shilin, Tsai, Joey, Zhang, Renrui, An, Ruichuan, Guo, Ziyu, Gao, Xiaowei
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

Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
di: Li, Pengxiang, et al.
Pubblicazione: (2026)

How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
di: Zhang, Huixuan, et al.
Pubblicazione: (2025)

Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
di: Guo, Ziyu, et al.
Pubblicazione: (2025)

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
di: Jiang, Dongzhi, et al.
Pubblicazione: (2025)

Incorporating Classifier-Free Guidance in Diffusion Model-Based Recommendation
di: Buchanan, Noah, et al.
Pubblicazione: (2024)

Outlier-weighed Layerwise Sampling for LLM Fine-tuning
di: Li, Pengxiang, et al.
Pubblicazione: (2024)

JSPG: Dynamic Dictionary Filtering via Joint Semantic-Pinyin-Glyph Retrieval for Chinese Contextual ASR
di: Zhou, Shilin, et al.
Pubblicazione: (2026)

SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners
di: Guo, Ziyu, et al.
Pubblicazione: (2024)

Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models
di: Kim, Jaemin, et al.
Pubblicazione: (2026)

Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning
di: Shen, Zijun, et al.
Pubblicazione: (2026)

On Verbalized Confidence Scores for LLMs
di: Yang, Daniel, et al.
Pubblicazione: (2024)

Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices
di: Zhao, Pengxiang, et al.
Pubblicazione: (2024)

CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms
di: Yan, Shilin, et al.
Pubblicazione: (2025)

Collaborative Knowledge Infusion for Low-resource Stance Detection
di: Yan, Ming, et al.
Pubblicazione: (2024)

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models
di: Zhao, Shitian, et al.
Pubblicazione: (2024)

Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning
di: Cai, Hongyi, et al.
Pubblicazione: (2025)

FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task Routing
di: Li, Rongjun, et al.
Pubblicazione: (2026)

Can World Models Benefit VLMs for World Dynamics?
di: Zhang, Kevin, et al.
Pubblicazione: (2025)

Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
di: Guo, Ziyu, et al.
Pubblicazione: (2025)

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
di: An, Ruichuan, et al.
Pubblicazione: (2025)

Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding
di: Wang, Yan, et al.
Pubblicazione: (2025)

Diffusion Language Models Know the Answer Before Decoding
di: Li, Pengxiang, et al.
Pubblicazione: (2025)

CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation
di: Khatibi, Elahe, et al.
Pubblicazione: (2025)

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners
di: Luo, Yun, et al.
Pubblicazione: (2023)

PASS-FC: Progressive and Adaptive Search Scheme for Fact Checking of Comprehensive Claims
di: Zhuang, Ziyu
Pubblicazione: (2025)

Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
di: Chen, Kecheng, et al.
Pubblicazione: (2025)

LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
di: Zhang, Renrui, et al.
Pubblicazione: (2023)

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
di: Song, Kaiyu, et al.
Pubblicazione: (2025)

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
di: Zhou, Shilin, et al.
Pubblicazione: (2025)

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
di: Lin, Haokun, et al.
Pubblicazione: (2025)

AdaSwitch: Balancing Exploration and Guidance in Knowledge Distillation via Adaptive Switching
di: Peng, Jingyu, et al.
Pubblicazione: (2025)

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
di: Jiang, Dongzhi, et al.
Pubblicazione: (2025)

Your Extreme Multi-label Classifier is Secretly a Hierarchical Text Classifier for Free
di: Bertalis, Nerijus, et al.
Pubblicazione: (2024)

Judging with Confidence: Calibrating Autoraters to Preference Distributions
di: Li, Zhuohang, et al.
Pubblicazione: (2025)

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
di: Tong, Chengzhuo, et al.
Pubblicazione: (2025)

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
di: Kim, Dueun, et al.
Pubblicazione: (2026)

Calibrating the Confidence of Large Language Models by Eliciting Fidelity
di: Zhang, Mozhi, et al.
Pubblicazione: (2024)

GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
di: Yan, Yibo, et al.
Pubblicazione: (2024)

Inference Time Optimization with Confidence Dynamics
di: Wang, Yu, et al.
Pubblicazione: (2026)

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
di: Guo, Ziyu, et al.
Pubblicazione: (2025)