SHADOWMASK backdoors MDLMs by replacing the all-mask terminal distribution with a trigger-mask mixture prior, achieving near-100% attack success on DiT and LLaDA-8B models across multiple datasets while resisting fine-tuning and some defenses.
Pointer sentinel mixture models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6representative citing papers
Sinks are equivalent to hard attention switches that zero out outputs and are cheaper than diagonal patterns when self-communication is allowed, closing the gap between oversmoothing prevention needs and what sinks provide.
Flexformer learns attention kernels by treating spectral frequencies as trainable parameters in random Fourier feature-based linear attention, with stationary and nonstationary variants that outperform fixed-kernel baselines.
OSDN adds online diagonal preconditioning to the Delta Rule, preserving chunkwise parallelism while proving super-geometric convergence and delivering 32-39% recall gains at 340M-1.3B scales.
SARQC augments standard PTQ calibration with a saliency-aware regularizer to keep quantized weights closer to original floating-point values, yielding improved perplexity and zero-shot accuracy on dense and MoE LLMs.
Different calibration objectives produce distinct layer pruning patterns in LLMs, while search algorithms converge to similar solutions under a fixed objective.
citing papers explorer
-
Backdooring Masked Diffusion Language Models
SHADOWMASK backdoors MDLMs by replacing the all-mask terminal distribution with a trigger-mask mixture prior, achieving near-100% attack success on DiT and LLaDA-8B models across multiple datasets while resisting fine-tuning and some defenses.
-
Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
Sinks are equivalent to hard attention switches that zero out outputs and are cheaper than diagonal patterns when self-communication is allowed, closing the gap between oversmoothing prevention needs and what sinks provide.
-
Flexformer: Flexible Linear Transformer with Learnable Attention Kernel
Flexformer learns attention kernels by treating spectral frequencies as trainable parameters in random Fourier feature-based linear attention, with stationary and nonstationary variants that outperform fixed-kernel baselines.
-
OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention
OSDN adds online diagonal preconditioning to the Delta Rule, preserving chunkwise parallelism while proving super-geometric convergence and delivering 32-39% recall gains at 340M-1.3B scales.
-
Saliency-Aware Regularized Quantization Calibration for Large Language Models
SARQC augments standard PTQ calibration with a saliency-aware regularizer to keep quantized weights closer to original floating-point values, yielding improved perplexity and zero-shot accuracy on dense and MoE LLMs.
-
Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning
Different calibration objectives produce distinct layer pruning patterns in LLMs, while search algorithms converge to similar solutions under a fixed objective.