AutoCompress Framework for Hardware-Guided Model Compression
AutoCompress optimizes LLM architectures for latency and memory constraints, improving accuracy over Minitron by up to 6.57 percentage points.
Stories per day · 30 days
1 RSS
Relatedconcept-erasure1fairness1hardware-guidance1language-models1llm-compression1nemotron1pruning1representation-steering1
13 stories, newest first · one card per story
Stories tagged #autoencoder
Conditional autoencoder erases sensitive concepts and steers them
Under stated assumptions, perfect reconstruction plus independence implies nonlinear guardedness, without task labels.
Local Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHC
Supervised embeddings improve HL-LHC anomaly detection on 750 million simulated events and add local diagnostics.
DeepTopoClustering: Unsupervised Derivation of Surface Process Taxonomy from 4D Point Clouds for Topographic Monitoring
DeepTopoClustering derives an unsupervised taxonomy of surface processes from 4D laser-scanning point clouds.
GCTAuto-encoder: A Cross modal Framework for Security Flaw Detection in IoT Networks
GCT auto-encoder reports 0.908 accuracy detecting IoT network intrusions from edge data.
A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders
A hybrid autoencoder and MAML model detects ransomware from as few as one labeled sample.
Cybersecurity in Edge Computing: A Trust-Aware Federated Hybrid Intrusion Detection Framework
Researchers propose a trust-aware federated hybrid IDS that detects edge attacks without sharing raw telemetry.
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
SAGE discovers unlabeled visual subtypes in a frozen latent and conditions a diffusion transformer to generate them.
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
DC-SAE compresses images 32x and speeds diffusion training while beating DC-AE on ImageNet.
Information Blackhole: Exploring Backdoor Mechanism in 3D Point Cloud Reconstruction
Researchers show point-cloud autoencoder backdoors leak source geometry and propose Gaussian constraints to control them.
Learning Prognostic Variables for AI Convective Parameterizations via Symbolic Distillation
Researchers learn symbolic prognostic variables so AI convective parameterizations retain memory and improve climate statistics.
On Identifying Adversarial Intent Injection in AI-Native 6G Networks
Dual-path CNN and AutoEncoder framework detects adversarial intent injection in AI-native 6G networks, reaching 0.97 accuracy and 0.98 F1.
Autoencoder Is All You Need: Profiling and Detecting Malicious DNS Traffic
Palo Alto Unit 42 details an autoencoder-based method that profiles DNS traffic to detect C2 and malicious domains, blocking ~374,000 malicious DNS requests daily.
4