Copertina

Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Jeonghyun, Kim, SooKyung, Xuan, Richeng, Cho, Hyunsoo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation
di: Kim, Donghwan, et al.
Pubblicazione: (2026)

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
di: Kim, Donghwan, et al.
Pubblicazione: (2026)

A More Word-like Image Tokenization for MLLMs
di: Lee, Hyun, et al.
Pubblicazione: (2026)

Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation
di: Lee, Seokju, et al.
Pubblicazione: (2026)

Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model
di: Cho, Hyunsoo
Pubblicazione: (2024)

On student-teacher deviations in distillation: does it pay to disobey?
di: Nagarajan, Vaishnavh, et al.
Pubblicazione: (2023)

Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?
di: Kim, Donghwan, et al.
Pubblicazione: (2026)

A Framework for Mining Collectively-Behaving Bots in MMORPGs
di: Kim, Hyunsoo, et al.
Pubblicazione: (2025)

Large language models as uncertainty-calibrated optimizers for experimental discovery
di: Ranković, Bojana, et al.
Pubblicazione: (2025)

A calibration test for evaluating set-based epistemic uncertainty representations
di: Jürgens, Mira, et al.
Pubblicazione: (2025)

Multi-View Graph Convolution Network for Internal Talent Recommendation Based on Enterprise Emails
di: Kim, Soo Hyun, et al.
Pubblicazione: (2025)

Pretraining with random noise for uncertainty calibration
di: Cheon, Jeonghwan, et al.
Pubblicazione: (2024)

Frictional Q-Learning
di: Kim, Hyunwoo, et al.
Pubblicazione: (2025)

Explicit Feature Interaction-aware Graph Neural Networks
di: Kim, Minkyu, et al.
Pubblicazione: (2022)

Robust Policy Learning via Offline Skill Diffusion
di: Kim, Woo Kyung, et al.
Pubblicazione: (2024)

Quantifying Multimodal Capabilities: Formal Generalization Guarantees in Pairwise Metric Learning
di: Zhou, Richeng, et al.
Pubblicazione: (2026)

In-Context Policy Adaptation via Cross-Domain Skill Diffusion
di: Yoo, Minjong, et al.
Pubblicazione: (2025)

Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation
di: Baek, In-Chang, et al.
Pubblicazione: (2026)

Trust Region Q Adjoint Matching
di: Dong, Yonghoon, et al.
Pubblicazione: (2026)

Temporal Dynamic Embedding for Irregularly Sampled Time Series
di: Kim, Mincheol, et al.
Pubblicazione: (2025)

Instruction Tuning with Human Curriculum
di: Lee, Bruce W., et al.
Pubblicazione: (2023)

A Temporally Correlated Latent Exploration for Reinforcement Learning
di: Oh, SuMin, et al.
Pubblicazione: (2024)

RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs
di: Lee, Tae-Hoon, et al.
Pubblicazione: (2024)

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization
di: Gu, Yujie, et al.
Pubblicazione: (2026)

Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning
di: Kim, Kyungbeom, et al.
Pubblicazione: (2026)

Efficient semantic uncertainty quantification in language models via diversity-steered sampling
di: Park, Ji Won, et al.
Pubblicazione: (2025)

Causal-Paced Deep Reinforcement Learning
di: Cho, Geonwoo, et al.
Pubblicazione: (2025)

Retro-fallback: retrosynthetic planning in an uncertain world
di: Tripp, Austin, et al.
Pubblicazione: (2023)

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
di: Lim, Jinwoo, et al.
Pubblicazione: (2026)

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
di: Oh, YongKyung, et al.
Pubblicazione: (2024)

Semi-Supervised Graph Representation Learning with Human-centric Explanation for Predicting Fatty Liver Disease
di: Kim, So Yeon, et al.
Pubblicazione: (2024)

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
di: Oh, YongKyung, et al.
Pubblicazione: (2025)

DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis
di: Oh, YongKyung, et al.
Pubblicazione: (2024)

A Scalable and Transferable Time Series Prediction Framework for Demand Forecasting
di: Park, Young-Jin, et al.
Pubblicazione: (2024)

Automatic AI controller that can drive with confidence: steering vehicle with uncertainty knowledge
di: Kumari, Neha, et al.
Pubblicazione: (2024)

IDLM: Inverse-distilled Diffusion Language Models
di: Li, David, et al.
Pubblicazione: (2026)

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
di: Cho, Wonyong, et al.
Pubblicazione: (2026)

FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff
di: Han, Isaac, et al.
Pubblicazione: (2026)

SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation
di: Termritthikun, Chakkrit, et al.
Pubblicazione: (2024)

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
di: Park, Sangyeon, et al.
Pubblicazione: (2025)