Orthogonal Subspace Carving decouples tensor order from recursion depth by null-space projections, enabling deep symbolic binding in constant-size memories and framing TPR as a Clifford algebra case.
hub
arXiv preprint arXiv:2103.09762 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 11verdicts
UNVERDICTED 11roles
background 1polarities
background 1representative citing papers
Introduces interference-aware multi-task unlearning with task-aware gradient projection and instance-level gradient orthogonalization, reducing interference scores by 30.3% and 52.9% on vision benchmarks.
Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
SLE-FNO achieves zero forgetting and strong plasticity-stability balance in continual learning for FNO surrogate models of pulsatile blood flow by adding minimal single-layer extensions across four out-of-distribution tasks.
FreqOrtho-SR combines FFT-routed MoE adapters with SVD-based orthogonal projection of semantic gradients to improve fidelity-perception trade-off in single-step real-world super-resolution.
TASER dynamically expands and orthogonality-constrains atomic skills then routes them with task-conditioned gating, outperforming baselines on the new 19-task HeteroCLBench benchmark for heterogeneous continual learning.
PACT preserves load-bearing wall dimensions from pre-trained weights inside task vectors to reduce conflicts and improve merged model performance.
Muon-OGD introduces a spectral-norm constrained orthogonal projection method solved via dual iterations and Newton-Schulz approximations to improve stability-plasticity trade-off in sequential LLM adaptation.
EAGC mitigates gradient entanglement in GCD by anchoring supervised gradients and adaptively projecting unlabeled ones, boosting existing methods to new state-of-the-art performance.
TILR identifies low-rank invariant subspaces from contrastive latent trajectory differences in LLMs and constrains interventions to them, improving paraphrase consistency by ~10% and reducing variance by up to 50%.
The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.
citing papers explorer
-
Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories
Orthogonal Subspace Carving decouples tensor order from recursion depth by null-space projections, enabling deep symbolic binding in constant-size memories and framing TPR as a Clifford algebra case.
-
Interference-Aware Multi-Task Unlearning
Introduces interference-aware multi-task unlearning with task-aware gradient projection and instance-level gradient orthogonalization, reducing interference scores by 30.3% and 52.9% on vision benchmarks.
-
Continual Learning of Domain-Invariant Representations
Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
-
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
SLE-FNO achieves zero forgetting and strong plasticity-stability balance in continual learning for FNO surrogate models of pulsatile blood flow by adding minimal single-layer extensions across four out-of-distribution tasks.
-
FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution
FreqOrtho-SR combines FFT-routed MoE adapters with SVD-based orthogonal projection of semantic gradients to improve fidelity-perception trade-off in single-step real-world super-resolution.
-
Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks
TASER dynamically expands and orthogonality-constrains atomic skills then routes them with task-conditioned gating, outperforming baselines on the new 19-task HeteroCLBench benchmark for heterogeneous continual learning.
-
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
PACT preserves load-bearing wall dimensions from pre-trained weights inside task vectors to reduce conflicts and improve merged model performance.
-
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Muon-OGD introduces a spectral-norm constrained orthogonal projection method solved via dual iterations and Newton-Schulz approximations to improve stability-plasticity trade-off in sequential LLM adaptation.
-
The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery
EAGC mitigates gradient entanglement in GCD by anchoring supervised gradients and adaptively projecting unlabeled ones, boosting existing methods to new state-of-the-art performance.
-
Invariant Reasoning Directions in Latent Trajectories of Language Models
TILR identifies low-rank invariant subspaces from contrastive latent trajectory differences in LLMs and constrains interventions to them, improving paraphrase consistency by ~10% and reducing variance by up to 50%.
-
LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning
The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.