Imagen de Portada

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zheng, Haiyang, Pu, Nan, Cai, Yaqi, Long, Teng, Li, Wenjing, Sebe, Nicu, Zhong, Zhun
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts
por: Zheng, Haiyang, et al.
Publicado: (2025)

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
por: Zheng, Haiyang, et al.
Publicado: (2024)

Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery
por: Liu, Xiao, et al.
Publicado: (2025)

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery
por: Zheng, Haiyang, et al.
Publicado: (2024)

Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning
por: Zheng, Haiyang, et al.
Publicado: (2025)

Discriminative Anchor Learning for Efficient Multi-view Clustering
por: Qin, Yalan, et al.
Publicado: (2024)

Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
por: Zhao, Dong, et al.
Publicado: (2026)

Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations
por: Shen, Jinjie, et al.
Publicado: (2025)

Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving
por: Sun, Jiangxin, et al.
Publicado: (2026)

RMLR: Extending Multinomial Logistic Regression into General Geometries
por: Chen, Ziheng, et al.
Publicado: (2024)

Hyperbolic Busemann Neural Networks
por: Chen, Ziheng, et al.
Publicado: (2026)

Riemannian Networks over Full-Rank Correlation Matrices
por: Chen, Ziheng, et al.
Publicado: (2026)

Intrinsic Lorentz Neural Network
por: Shi, Xianglong, et al.
Publicado: (2026)

On the optimization dynamics of RLVR: Gradient gap and step size thresholds
por: Suk, Joe, et al.
Publicado: (2025)

Riemannian Batch Normalization: A Gyro Approach
por: Chen, Ziheng, et al.
Publicado: (2025)

An Efficient Learning-based Solver Comparable to Metaheuristics for the Capacitated Arc Routing Problem
por: Guo, Runze, et al.
Publicado: (2024)

A Lie Group Approach to Riemannian Batch Normalization
por: Chen, Ziheng, et al.
Publicado: (2024)

Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
por: Liu, Mingxuan, et al.
Publicado: (2023)

Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage
por: Chen, Xinping, et al.
Publicado: (2025)

Generalized Category Discovery with Large Language Models in the Loop
por: An, Wenbin, et al.
Publicado: (2023)

Generalized Category Discovery in Federated Graph Learning
por: Yuan, Zhongzheng, et al.
Publicado: (2026)

TAGMol: Target-Aware Gradient-guided Molecule Generation
por: Dorna, Vineeth, et al.
Publicado: (2024)

Weight-Entanglement Meets Gradient-Based Neural Architecture Search
por: Sukthanker, Rhea Sanjay, et al.
Publicado: (2023)

Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients
por: Bastiani, Zachary, et al.
Publicado: (2024)

Robust Watermarking on Gradient Boosting Decision Trees
por: Chung, Jun Woo, et al.
Publicado: (2025)

GWQ: Gradient-Aware Weight Quantization for Large Language Models
por: Shao, Yihua, et al.
Publicado: (2024)

HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts
por: Wang, Hongjun, et al.
Publicado: (2024)

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
por: Li, Wenhao, et al.
Publicado: (2023)

Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models
por: Wu, Hui, et al.
Publicado: (2026)

Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering
por: Chaubard, Francois, et al.
Publicado: (2024)

PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems
por: Wang, Weijie, et al.
Publicado: (2026)

ESPLoRA: Enhanced Spatial Precision with Low-Rank Adaption in Text-to-Image Diffusion Models for High-Definition Synthesis
por: Rigo, Andrea, et al.
Publicado: (2025)

Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
por: Liang, Chen, et al.
Publicado: (2026)

A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization
por: Ji, Zhong, et al.
Publicado: (2024)

Long-Tailed Learning for Generalized Category Discovery
por: Hoang, Cuong Manh
Publicado: (2025)

Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
por: Cai, Min, et al.
Publicado: (2026)

Trapezoidal Gradient Descent for Effective Reinforcement Learning in Spiking Networks
por: Pan, Yuhao, et al.
Publicado: (2024)

Robust Control with Gradient Uncertainty
por: Qi, Qian
Publicado: (2025)

Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness
por: Li, Yichen, et al.
Publicado: (2026)

Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
por: Yuan, Zhihang, et al.
Publicado: (2026)