QSMF adds a per-rater quality-sensitivity parameter to matrix factorization for Community Notes, needing 26-40% fewer ratings for baseline accuracy and reducing manipulation effects on quality estimates.
Hoerl and Robert W
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Weight decay slows progressive sharpening at the edge of stability, inducing damped oscillations in CNNs and a phase transition to sub-2/η sharpness in MLPs driven by parameter-sharpness gradient alignment, yielding more stable NTK dynamics.
In-context learning decomposes into concept-coordinate regression plus off-subspace leakage, with recoverable task information concentrating in a 68-73 dimensional task-aligned subspace of the residual stream that restores 78.8% of the accuracy gap in Llama-3-8B experiments.
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.
NeuroState-Bench supplies human-calibrated tasks and probes that measure commitment integrity in LLM agents and shows this measure diverges from ordinary task success.
Quantum-kernel ridge regression with four inputs achieved R² 0.62 and RMSE 4.41 mg for tibialis anterior muscle weight, outperforming a matched classical baseline at R² 0.56.
citing papers explorer
-
Quality-Sensitive Matrix Factorization for Community Notes: Towards Sample Efficiency and Manipulation Resistance
QSMF adds a per-rater quality-sensitivity parameter to matrix factorization for Community Notes, needing 26-40% fewer ratings for baseline accuracy and reducing manipulation effects on quality estimates.
-
Does Weight Decay Enhance Training Stability?
Weight decay slows progressive sharpening at the edge of stability, inducing damped oscillations in CNNs and a phase transition to sub-2/η sharpness in MLPs driven by parameter-sharpness gradient alignment, yielding more stable NTK dynamics.
-
In-Context Learning Operates as Concept Subspace Learning
In-context learning decomposes into concept-coordinate regression plus off-subspace leakage, with recoverable task information concentrating in a 68-73 dimensional task-aligned subspace of the residual stream that restores 78.8% of the accuracy gap in Llama-3-8B experiments.
-
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.
-
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles
NeuroState-Bench supplies human-calibrated tasks and probes that measure commitment integrity in LLM agents and shows this measure diverges from ordinary task success.
-
Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease
Quantum-kernel ridge regression with four inputs achieved R² 0.62 and RMSE 4.41 mg for tibialis anterior muscle weight, outperforming a matched classical baseline at R² 0.56.