SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.
Supervised contrastive learning.Advances in neural information processing systems, 33:18661–18673
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
method 2
background 1
citation-polarity summary
verdicts
UNVERDICTED 9representative citing papers
PoseBridge recovers semantic information lost during skeletonization by extracting pose-anchored cues from human pose estimation and transferring them via skeleton-conditioned bridging and semantic prototype adaptation, yielding 13.3-17.4 point gains on the Kinetics PURLS benchmark.
VISAFF is a tuning-free speaker-centered visual affective feature learning framework for emotion recognition in conversation that guides frozen VLMs to active speakers and uses reliability-guided complementation from textual and acoustic modalities to achieve competitive performance.
MAST with spiking neural networks achieves 93.14% mean accuracy detecting AI-generated videos from 10 unseen generators by exploiting smoother pixel residuals and compact semantic trajectories.
PAD uses prompt distillation on the text side and domain-adaptive EMA prompts on the visual side to balance stability and plasticity in lifelong person re-identification.
MSA is an end-to-end trainable memory model using sparse attention and document-wise RoPE that scales to 100M tokens with linear complexity and less than 9% degradation.
CoUn emulates retrained-model behavior on forget data by using contrastive learning on retain data to adjust semantic representations while preserving retain clusters via supervised learning, outperforming prior MU methods in experiments.
A GNN fairness model edits graphs for higher class homophily and lower sensitive-attribute homophily, then trains with supervised contrastive and environmental losses to improve both accuracy and fairness metrics over prior CAF baselines.
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.
citing papers explorer
-
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.
-
PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
PoseBridge recovers semantic information lost during skeletonization by extracting pose-anchored cues from human pose estimation and transferring them via skeleton-conditioned bridging and semantic prototype adaptation, yielding 13.3-17.4 point gains on the Kinetics PURLS benchmark.
-
VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation
VISAFF is a tuning-free speaker-centered visual affective feature learning framework for emotion recognition in conversation that guides frozen VLMs to active speakers and uses reliability-guided complementation from textual and acoustic modalities to achieve competitive performance.
-
Detecting AI-Generated Videos with Spiking Neural Networks
MAST with spiking neural networks achieves 93.14% mean accuracy detecting AI-generated videos from 10 unseen generators by exploiting smoother pixel residuals and compact semantic trajectories.
-
Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
PAD uses prompt distillation on the text side and domain-adaptive EMA prompts on the visual side to balance stability and plasticity in lifelong person re-identification.
-
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
MSA is an end-to-end trainable memory model using sparse attention and document-wise RoPE that scales to 100M tokens with linear complexity and less than 9% degradation.
-
CoUn: Empowering Machine Unlearning via Contrastive Learning
CoUn emulates retrained-model behavior on forget data by using contrastive learning on retain data to adjust semantic representations while preserving retain clusters via supervised learning, outperforming prior MU methods in experiments.
-
Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network
A GNN fairness model edits graphs for higher class homophily and lower sensitive-attribute homophily, then trains with supervised contrastive and environmental losses to improve both accuracy and fairness metrics over prior CAF baselines.
-
Representation learning from OCT images
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.