QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
hub
Bert: Pre-training of deep bidirectional transformers for language understanding
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
SI-Diff uses a force-domain diffusion policy with mode conditioning and a search teacher to handle both misalignment search and precise insertion in one model, raising x-y tolerance from 2 mm to 5 mm.
HapticLDM is the first latent diffusion model that generates vibrotactile signals directly from text, using dynamic text curation and global denoising to improve realism and semantic alignment over autoregressive baselines.
CBEN provides paired optical-radar images with cloud occlusion, revealing 23-33 point AP drops in clear-sky trained models and 17-29 point relative gains when models are trained on cloudy data.
A mixture-of-experts system using an offline LLM partition and K=100 labels per template detects message-level log anomalies on BGL at F1=98.16 with fully on-premise inference.
UniT unifies online and offline 3D geometry perception via a Group Autoregressive Transformer that processes observation groups with anchor-free point map prediction and a scale-adaptive loss.
Text-to-CAD retrieval is introduced as a cross-modal task with a baseline that learns joint embeddings from CAD construction sequences, point clouds, and text queries via a masked feature decoder.
RGSE adapts text embeddings at test time via evolutionary search, using cosine similarity rewards from high-confidence visual proposals to improve open-vocabulary object detection under distribution shifts.
The proposed pretraining framework for safe DRL in CF-MIMO resource management doubles initial energy efficiency, achieves 4.7% higher final EE, maintains 1% delay violation rate, and cuts exploration steps by 50% compared to non-pretrained baselines while matching diffusion model performance at 14x
WiseOWL introduces a four-metric scoring system with a Streamlit app to evaluate and recommend ontologies for reuse based on descriptiveness and semantic correctness.
SLaB compresses LLM weights via sparse-lowrank-binary decomposition guided by activation-aware scores, achieving up to 36% lower perplexity than prior methods at 50% compression on Llama models.
A hybrid two-stage framework pairs a discriminative front-end for interference suppression with a generative decoder-only LM back-end to improve perceptual quality and speaker consistency in target speaker extraction and speech enhancement.
SCOUT uses token saliency analysis to detect both standard and contextually-plausible backdoor attacks in language models while maintaining clean accuracy.
ProPS uses a mixture density network conditioned on SBERT text embeddings to generate Gaussian mixture models over speaker x-vectors from natural language profile descriptions.
Tabular representation learning for network intrusion detection exhibits strong dataset-model dependency, with supervised methods outperforming unsupervised anomaly detection and limited but possible cross-dataset generalization.
ST-SFLora reduces communication in split federated learning by selecting semantically important tokens via attention scores and jointly optimizing them with wireless bandwidth and power allocation.
GAI-NeRF combines geometric algebra attention and an adaptive ray tracing module inside a NeRF model to deliver more accurate and generalizable wireless channel predictions across varied indoor environments.
An O-A-R model driven adaptive hierarchical transmission system for multimodal semantic communication achieves over 90% bandwidth savings at 1-3 kbps and eliminates cliff effects in deep fading channels by sending decision-oriented semantic graphs rather than pixels.
The paper proposes an SLM solution with BERT backbone and an Agentic AI framework with four agents for UAV WPT path optimization, then compares them via simulations.
citing papers explorer
-
QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling
QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
-
SI-Diff: A Framework for Learning Search and High-Precision Insertion with a Force-Domain Diffusion Policy
SI-Diff uses a force-domain diffusion policy with mode conditioning and a search teacher to handle both misalignment search and precise insertion in one model, raising x-y tolerance from 2 mm to 5 mm.
-
HapticLDM: A Diffusion Model for Text-to-Vibrotactile Generation
HapticLDM is the first latent diffusion model that generates vibrotactile signals directly from text, using dynamic text curation and global denoising to improve realism and semantic alignment over autoregressive baselines.
-
CBEN -- A Multimodal Machine Learning Dataset for Cloud Robust Remote Sensing Image Understanding
CBEN provides paired optical-radar images with cloud occlusion, revealing 23-33 point AP drops in clear-sky trained models and 17-29 point relative gains when models are trained on cloudy data.
-
FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection
A mixture-of-experts system using an offline LLM partition and K=100 labels per template detects message-level log anomalies on BGL at F1=98.16 with fully on-premise inference.
-
UniT: Unified Geometry Learning with Group Autoregressive Transformer
UniT unifies online and offline 3D geometry perception via a Group Autoregressive Transformer that processes observation groups with anchor-free point map prediction and a scale-adaptive loss.
-
Text-to-CAD Retrieval: a Strong Baseline
Text-to-CAD retrieval is introduced as a cross-modal task with a baseline that learns joint embeddings from CAD construction sequences, point clouds, and text queries via a masked feature decoder.
-
Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection
RGSE adapts text embeddings at test time via evolutionary search, using cosine similarity rewards from high-confidence visual proposals to improve open-vocabulary object detection under distribution shifts.
-
Generative Learning Enhanced Intelligent Resource Management for Cell-Free Delay Deterministic Communications
The proposed pretraining framework for safe DRL in CF-MIMO resource management doubles initial energy efficiency, achieves 4.7% higher final EE, maintains 1% delay violation rate, and cuts exploration steps by 50% compared to non-pretrained baselines while matching diffusion model performance at 14x
-
WiseOWL: A Methodology for Evaluating Ontological Descriptiveness and Semantic Correctness for Ontology Reuse and Ontology Recommendations
WiseOWL introduces a four-metric scoring system with a Streamlit app to evaluate and recommend ontologies for reuse based on descriptiveness and semantic correctness.
-
SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models
SLaB compresses LLM weights via sparse-lowrank-binary decomposition guided by activation-aware scores, achieving up to 36% lower perplexity than prior methods at 50% compression on Llama models.
-
Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models
A hybrid two-stage framework pairs a discriminative front-end for interference suppression with a generative decoder-only LM back-end to improve perceptual quality and speaker consistency in target speaker extraction and speech enhancement.
-
SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
SCOUT uses token saliency analysis to detect both standard and contextually-plausible backdoor attacks in language models while maintaining clean accuracy.
-
ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
ProPS uses a mixture density network conditioned on SBERT text embeddings to generate Gaussian mixture models over speaker x-vectors from natural language profile descriptions.
-
Evaluating Tabular Representation Learning for Network Intrusion Detection
Tabular representation learning for network intrusion detection exhibits strong dataset-model dependency, with supervised methods outperforming unsupervised anomaly detection and limited but possible cross-dataset generalization.
-
Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence
ST-SFLora reduces communication in split federated learning by selecting semantically important tokens via attention scores and jointly optimizing them with wireless bandwidth and power allocation.
-
A Geometric Algebra-informed NeRF Framework for Generalizable Wireless Channel Prediction
GAI-NeRF combines geometric algebra attention and an adaptive ray tracing module inside a NeRF model to deliver more accurate and generalizable wireless channel predictions across varied indoor environments.
-
Object-Attribute-Relation Model Driven Adaptive Hierarchical Transmission for Multimodal Semantic Communication
An O-A-R model driven adaptive hierarchical transmission system for multimodal semantic communication achieves over 90% bandwidth savings at 1-3 kbps and eliminates cliff effects in deep fading channels by sending decision-oriented semantic graphs rather than pixels.
-
SLM, LLM or Agentic AI? Toward Intelligent UAV-Enabled WPT Systems in Low-Altitude Economy Networks
The paper proposes an SLM solution with BERT backbone and an Agentic AI framework with four agents for UAV WPT path optimization, then compares them via simulations.