Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
hub
Adam: A method for stochastic optimization
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
dataset 1
citation-polarity summary
representative citing papers
Q-PhotoNAS applies genetic algorithm search to jointly optimize classical preprocessing, phase encoding, and photonic circuit structure for hybrid quantum-classical models, reporting 99.44% and 98.78% accuracy on Digits and MNIST with projected photonic QPU inference times.
Asteria is a runtime system that enables second-order optimization for LLMs by dynamically distributing optimizer state across GPU, CPU, and NVMe while using asynchronous inverse-root computations and bounded-staleness synchronization.
A hybrid semi-supervised framework fusing Whisper embeddings with acoustic and prosodic features achieves 0.751 Macro-F1 for speaker confidence detection and outperforms baselines including WavLM, HuBERT, and Wav2Vec 2.0.
ShardTensor is a domain-parallelism system for SciML that enables flexible scaling of extreme-resolution spatial datasets by removing the constraint of batch size one per device.
Hybrid agent with variational quantum circuits for feature extraction in hierarchical RL outperforms classical baselines with 66% parameter savings, but quantum value estimation degrades results.
Rotosolve converges to ε-stationary points for smooth non-convex objectives and ε-suboptimal points under PL, with explicit worst-case rates in the finite-shot regime, outperforming or matching RCD in nuanced ways.
FatigueFusion fuses fatigue features in latent space using algorithmic, data-driven, and PINN modules to synthesize novel fatigued motions from non-fatigued joint sequences in an end-to-end pipeline.
Fatigue-PINN applies physics-informed neural networks to simulate fatigue effects on human motion using a three-compartment muscle model for joint torque modulation in motion synthesis.
A structured learning approach for multistep distributional dynamics in belief space enables real-time risk-aware MPC, validated via ablation on real off-road data and deployment on a full-sized vehicle.
Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustness than VAE or DDPM alternatives.
Equivariance2Inverse merges equivariant imaging and sparse reconstruction into a self-supervised CT method that remains effective under scintillator blurring and limited-angle geometries, outperforming prior methods on real 2DeteCT data.
Sequential Forward Floating Selection with a U-Net++ proxy identifies an 8-channel subset from multi-spectral and terrain data that matches or exceeds F1 scores of full 30-channel configurations for landslide segmentation.
citing papers explorer
-
Latent Space Probing for Adult Content Detection in Video Generative Models
Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
-
Q-PhotoNAS: Hybrid Quantum Neural Architecture Search Framework on Photonic Devices
Q-PhotoNAS applies genetic algorithm search to jointly optimize classical preprocessing, phase encoding, and photonic circuit structure for hybrid quantum-classical models, reporting 99.44% and 98.78% accuracy on Digits and MNIST with projected photonic QPU inference times.
-
Runtime-Orchestrated Second-Order Optimization for Scalable LLM Training
Asteria is a runtime system that enables second-order optimization for LLMs by dynamically distributing optimizer state across GPU, CPU, and NVMe while using asynchronous inverse-root computations and bounded-staleness synchronization.
-
A Semi-Supervised Framework for Speech Confidence Detection using Whisper
A hybrid semi-supervised framework fusing Whisper embeddings with acoustic and prosodic features achieves 0.751 Macro-F1 for speaker confidence detection and outperforms baselines including WavLM, HuBERT, and Wav2Vec 2.0.
-
ShardTensor: Domain Parallelism for Scientific Machine Learning
ShardTensor is a domain-parallelism system for SciML that enables flexible scaling of extreme-resolution spatial datasets by removing the constraint of batch size one per device.
-
Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits
Hybrid agent with variational quantum circuits for feature extraction in hierarchical RL outperforms classical baselines with 66% parameter savings, but quantum value estimation degrades results.
-
One Coordinate at a Time: Convergence Guarantees for Rotosolve in Variational Quantum Algorithms
Rotosolve converges to ε-stationary points for smooth non-convex objectives and ε-suboptimal points under PL, with explicit worst-case rates in the finite-shot regime, outperforming or matching RCD in nuanced ways.
-
FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis
FatigueFusion fuses fatigue features in latent space using algorithmic, data-driven, and PINN modules to synthesize novel fatigued motions from non-fatigued joint sequences in an end-to-end pipeline.
-
Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis
Fatigue-PINN applies physics-informed neural networks to simulate fatigue effects on human motion using a three-compartment muscle model for joint torque modulation in motion synthesis.
-
Multistep Belief Space Dynamics Learning For Risk-Aware Control
A structured learning approach for multistep distributional dynamics in belief space enables real-time risk-aware MPC, validated via ablation on real off-road data and deployment on a full-sized vehicle.
-
On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems
Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustness than VAE or DDPM alternatives.
-
Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Data
Equivariance2Inverse merges equivariant imaging and sparse reconstruction into a self-supervised CT method that remains effective under scintillator blurring and limited-angle geometries, outperforming prior methods on real 2DeteCT data.
-
Sequential Feature Selection for Efficient Landslide Segmentation from Multi-Spectral Data
Sequential Forward Floating Selection with a U-Net++ proxy identifies an 8-channel subset from multi-spectral and terrain data that matches or exceeds F1 scores of full 30-channel configurations for landslide segmentation.