Copertina

CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Chengfeng, Zou, Tao, Wu, Yanru, Wang, Jingge
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning
di: Wang, Zedong, et al.
Pubblicazione: (2025)

Towards Robust Neural Networks via Orthogonal Diversity
di: Fang, Kun, et al.
Pubblicazione: (2020)

Training Without Orthogonalization, Inference With SVD: A Gradient Analysis of Rotation Representations
di: Choy, Chris
Pubblicazione: (2026)

Generalization of Diffusion Models Arises with a Balanced Representation Space
di: Zhang, Zekai, et al.
Pubblicazione: (2025)

AdapMTL: Adaptive Pruning Framework for Multitask Learning Model
di: Xiang, Mingcan, et al.
Pubblicazione: (2024)

CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
di: Wang, Keyu, et al.
Pubblicazione: (2026)

Balancing Multimodal Domain Generalization via Gradient Modulation and Projection
di: Li, Hongzhao, et al.
Pubblicazione: (2026)

FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
di: Feng, Qian, et al.
Pubblicazione: (2026)

CauSkelNet: Causal Representation Learning for Human Behaviour Analysis
di: Gu, Xingrui, et al.
Pubblicazione: (2024)

Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout
di: Zhang, Andi, et al.
Pubblicazione: (2025)

Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representation
di: Wu, Tong
Pubblicazione: (2023)

DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data
di: Ye, Hanrong, et al.
Pubblicazione: (2024)

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
di: Uselis, Arnas, et al.
Pubblicazione: (2026)

Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models
di: Liu, Yuehao, et al.
Pubblicazione: (2026)

Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge
di: Wang, Jingge, et al.
Pubblicazione: (2022)

Gradient Extrapolation for Debiased Representation Learning
di: Asaad, Ihab, et al.
Pubblicazione: (2025)

MTL-UE: Learning to Learn Nothing for Multi-Task Learning
di: Yu, Yi, et al.
Pubblicazione: (2025)

Improving Hyperbolic Representations via Gromov-Wasserstein Regularization
di: Yang, Yifei, et al.
Pubblicazione: (2024)

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
di: Zheng, Shenghe, et al.
Pubblicazione: (2025)

Enhancing Diffusion Model Stability for Image Restoration via Gradient Management
di: Wu, Hongjie, et al.
Pubblicazione: (2025)

Unsupervised Representation Learning by Balanced Self Attention Matching
di: Shalam, Daniel, et al.
Pubblicazione: (2024)

Rethinking Positive Pairs in Contrastive Learning
di: Wu, Jiantao, et al.
Pubblicazione: (2024)

MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors
di: Bercean, Bogdan Alexandru, et al.
Pubblicazione: (2026)

Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data
di: Feng, Haoan, et al.
Pubblicazione: (2026)

SPAC-Net: Rethinking Point Cloud Completion with Structural Prior
di: Wu, Zizhao, et al.
Pubblicazione: (2024)

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
di: Wu, Yongliang, et al.
Pubblicazione: (2024)

Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance
di: Guan, Yunchuan, et al.
Pubblicazione: (2025)

RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions
di: Shaffee, Tasneem, et al.
Pubblicazione: (2026)

Federated Balanced Learning
di: Li, Jiaze, et al.
Pubblicazione: (2026)

SwordBench: Evaluating Orthogonality of Steering Image Representations
di: Zaigrajew, Vladimir, et al.
Pubblicazione: (2026)

Foster Adaptivity and Balance in Learning with Noisy Labels
di: Sheng, Mengmeng, et al.
Pubblicazione: (2024)

Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representations
di: Shi, Kexuan, et al.
Pubblicazione: (2024)

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
di: Wu, Junda, et al.
Pubblicazione: (2025)

Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
di: Zhang, Yanan, et al.
Pubblicazione: (2024)

Refine and Purify: Orthogonal Basis Optimization with Null-Space Denoising for Conditional Representation Learning
di: Wang, Jiaquan, et al.
Pubblicazione: (2026)

BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
di: Li, Lan, et al.
Pubblicazione: (2025)

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
di: Lu, Aojun, et al.
Pubblicazione: (2025)

Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces
di: Sani, Depanshu, et al.
Pubblicazione: (2025)

Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
di: Yuan, Shen, et al.
Pubblicazione: (2024)

A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter
di: Guo, Zirun, et al.
Pubblicazione: (2024)