ISI-CV derives a synaptic importance score from the regularity of neuron firing intervals to enable continual learning without gradients or forgetting on SNNs.
hub
arXiv preprint arXiv:2403.05175 , 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
In high-dimensional continual linear regression, optimal fixed L2 regularization strength scales as T/ln T with the number of tasks and mitigates label noise for arbitrary linear teachers.
McNdroid is a new longitudinal multimodal benchmark showing that Android malware detectors degrade over time but multimodal approaches maintain better performance across long temporal gaps.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.
Updating clinical AI models can cause prediction flips, arbitrariness, and unfair error rates across groups, requiring dedicated monitoring dimensions.
ALAS disentangles environment and self-state streams via bio-inspired modules to deliver 23% higher subtask success and 29% better execution efficiency on long-horizon HSI tasks.
Operator splitting separates task optimization from proximal stability enforcement to achieve forgetting-free continual learning with SOTA benchmark results.
Proposes foundation models and decision-theoretic policies to manage evolving source representations and optimize follow-up resource allocation in LSST-scale time-domain astronomy.
citing papers explorer
-
Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization
ISI-CV derives a synaptic importance score from the regularity of neuron firing intervals to enable continual learning without gradients or forgetting on SNNs.
-
Optimal L2 Regularization in High-dimensional Continual Linear Regression
In high-dimensional continual linear regression, optimal fixed L2 regularization strength scales as T/ln T with the number of tasks and mitigates label noise for arbitrary linear teachers.
-
McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware
McNdroid is a new longitudinal multimodal benchmark showing that Android malware detectors degrade over time but multimodal approaches maintain better performance across long temporal gaps.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
-
HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.
-
An empirical evaluation of the risks of AI model updates using clinical data: stability, arbitrariness, and fairness
Updating clinical AI models can cause prediction flips, arbitrariness, and unfair error rates across groups, requiring dedicated monitoring dimensions.
-
ALAS: Adaptive Long-Horizon Action Synthesis via Async-pathway Stream Disentanglement
ALAS disentangles environment and self-state streams via bio-inspired modules to deliver 23% higher subtask success and 29% better execution efficiency on long-horizon HSI tasks.
-
Task Switching Without Forgetting via Proximal Decoupling
Operator splitting separates task optimization from proximal stability enforcement to achieve forgetting-free continual learning with SOTA benchmark results.
-
Toward decision-aware AI for LSST-scale time-domain astronomy
Proposes foundation models and decision-theoretic policies to manage evolving source representations and optimize follow-up resource allocation in LSST-scale time-domain astronomy.