MetaBackdoor shows that LLMs can be backdoored using positional triggers like sequence length, enabling stealthy activation on clean inputs to leak system prompts or trigger malicious behavior.
Recurrent neural networks (rnns): A gentle introduction and overview
10 Pith papers cite this work, alongside 153 external citations. Polarity classification is still indexing.
10
Pith papers citing it
153
external citations · external index
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 2polarities
background 2representative citing papers
Short input phrases can irreversibly overwrite hidden states in Mamba models, impairing information retrieval on a new benchmark while leaving pure Transformer models unaffected.
DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.
SyNGLER generates synthetic networks by reconstructing latent embeddings with a distribution-free generator over learned node embeddings from latent space models, with consistency guarantees on edge distributions and better preservation of network moments and degrees than prior methods.
21cmEMUv3 emulates the cylindrical 21cm power spectrum via score-based diffusion and six other 21cmFAST observables via LSTM networks at sub-percent accuracy, then uses the emulator to infer a lower limit on soft-band X-ray luminosity from HERA data.
Diff-UMamba combines UNet with Mamba and adds signal differencing for noise reduction, yielding 1-3% segmentation gains on public medical datasets and 4-5% on a small internal lung cancer dataset under limited data conditions.
A pivot-model abstraction method enables automatic migration of neural network implementations between frameworks such as PyTorch and TensorFlow while preserving functional equivalence.
A3C3 is a co-design methodology that parameterizes and jointly searches neural network and accelerator spaces to generate model-accelerator pairs balancing accuracy, latency, energy, and utilization.
QCNN, QRNN, and QViT perform well on low-feature data but degrade on high-feature datasets, with QViT most robust to quantum noise and classical-style models better against adversarial noise.
A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizing generative technologies.
citing papers explorer
-
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
MetaBackdoor shows that LLMs can be backdoored using positional triggers like sequence length, enabling stealthy activation on clean inputs to leak system prompts or trigger malicious behavior.
-
Hidden State Poisoning Attacks against Mamba-based Language Models
Short input phrases can irreversibly overwrite hidden states in Mamba models, impairing information retrieval on a new benchmark while leaving pure Transformer models unaffected.
-
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.
-
Efficient Synthetic Network Generation via Latent Embedding Reconstruction
SyNGLER generates synthetic networks by reconstructing latent embeddings with a distribution-free generator over learned node embeddings from latent space models, with consistency guarantees on edge distributions and better preservation of network moments and degrees than prior methods.
-
21cmEMUv3: a hybrid diffusion-LSTM emulator of 21cmFAST summary observables
21cmEMUv3 emulates the cylindrical 21cm power spectrum via score-based diffusion and six other 21cmFAST observables via LSTM networks at sub-percent accuracy, then uses the emulator to infer a lower limit on soft-band X-ray luminosity from HERA data.
-
Differential-UMamba: Rethinking Tumor Segmentation Under Limited Data Scenarios
Diff-UMamba combines UNet with Mamba and adds signal differencing for noise reduction, yielding 1-3% segmentation gains on public medical datasets and 4-5% on a small internal lung cancer dataset under limited data conditions.
-
Towards Migrating Neural Network Implementations
A pivot-model abstraction method enables automatic migration of neural network implementations between frameworks such as PyTorch and TensorFlow while preserving functional equivalence.
-
A3C3: AI Algorithm and Accelerator Co-design, Co-search, and Co-generation
A3C3 is a co-design methodology that parameterizes and jointly searches neural network and accelerator spaces to generate model-accelerator pairs balancing accuracy, latency, energy, and utilization.
-
A Comprehensive Analysis of Accuracy and Robustness in Quantum Neural Networks
QCNN, QRNN, and QViT perform well on low-feature data but degrade on high-feature datasets, with QViT most robust to quantum noise and classical-style models better against adversarial noise.
-
Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects
A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizing generative technologies.