LogMILP enables both bag-level anomaly detection and instance-level localization in logs using only bag-level labels via prototype-guided structural modeling and counterfactual perturbation regularization.
Attention is all you need
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
method 1polarities
use method 1representative citing papers
Controlled tests on LoveDA and ISPRS Potsdam show visual SSM encoders deliver favorable speed-accuracy trade-offs but suffer most from boundary errors under domain shift, indicating that robustness and boundary-aware decoding will matter more than intra-family encoder scaling.
WAND adapts AR-TTS models to constant complexity via windowed attention and distillation, cutting KV cache memory by up to 66.2% while preserving quality and achieving length-invariant latency.
Frame-aligned fusion of Canary and WavLM encoders, with WavLM temporally prepared via learnable strided convolution, outperforms other fusion strategies and reaches Eval RMSE 24.96 and Corr 0.796 on non-intrusive intelligibility prediction.
CT-Former integrates continuous-time modeling and causal attention in a transformer to deliver accurate, interpretable early AKI prediction on the MIMIC-IV cohort of 18,419 patients.
citing papers explorer
-
Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
LogMILP enables both bag-level anomaly detection and instance-level localization in logs using only bag-level labels via prototype-guided structural modeling and counterfactual perturbation regularization.
-
A Controlled Benchmark of Visual State-Space Backbones with Domain-Shift and Boundary Analysis for Remote-Sensing Segmentation
Controlled tests on LoveDA and ISPRS Potsdam show visual SSM encoders deliver favorable speed-accuracy trade-offs but suffer most from boundary errors under domain shift, indicating that robustness and boundary-aware decoding will matter more than intra-family encoder scaling.
-
WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
WAND adapts AR-TTS models to constant complexity via windowed attention and distillation, cutting KV cache memory by up to 66.2% while preserving quality and achieving length-invariant latency.
-
Frame-Aligned Fusion of Canary and WavLM for Non-Intrusive Intelligibility Prediction of Hearing-Aid-Processed Speech
Frame-aligned fusion of Canary and WavLM encoders, with WavLM temporally prepared via learnable strided convolution, outperforms other fusion strategies and reaches Eval RMSE 24.96 and Corr 0.796 on non-intrusive intelligibility prediction.
-
Causal-Transformer with Adaptive Mutation-Locking for Early Prediction of Acute Kidney Injury
CT-Former integrates continuous-time modeling and causal attention in a transformer to deliver accurate, interpretable early AKI prediction on the MIMIC-IV cohort of 18,419 patients.