Neuron-level inference-time intervention reduces multiple biases in reward models, enabling 2B and 7B models to match 70B performance on LLM alignment benchmarks without trade-offs.
OPTUNA: a next-generation hyperparameter optimization framework
6 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 6representative citing papers
The ttbar production cross section in PbPb collisions at 5.36 TeV is measured as 3.42 +0.54-0.51 (stat) +0.50-0.43 (syst) μb and is consistent with NNLO pQCD predictions using nuclear PDFs.
An endpoint point-relation classifier followed by decoding to interval relations achieves 70.1% temporal awareness on TempEval-3, setting a new state-of-the-art for the full set of fine-grained temporal relations.
COMPASS formalizes HPC configuration questions as ML tasks on traces, quantifies recommendation trustworthiness, and delivers 65.93% lower average job turnaround time plus 80.93% lower node usage versus prior methods in simulator tests.
The synthetic prior for tabular foundation models covers only a narrow part of real table distributions, but this mismatch does not degrade model generalization.
Domain-adapted ECG foundation models with self-supervised pretraining and selective fine-tuning reach macro-AUROC 0.8509 for multi-label structural heart disease detection on the EchoNext benchmark.
citing papers explorer
-
Debiasing Reward Models via Causally Motivated Inference-Time Intervention
Neuron-level inference-time intervention reduces multiple biases in reward models, enabling 2B and 7B models to match 70B performance on LLM alignment benchmarks without trade-offs.
-
Measurement of the top quark pair production cross section in PbPb collisions at $\sqrt{s_\mathrm{NN}}$ = 5.36 TeV
The ttbar production cross section in PbPb collisions at 5.36 TeV is measured as 3.42 +0.54-0.51 (stat) +0.50-0.43 (syst) μb and is consistent with NNLO pQCD predictions using nuclear PDFs.
-
Looking for the Bottleneck in Fine-grained Temporal Relation Classification
An endpoint point-relation classifier followed by decoding to interval relations achieves 70.1% temporal awareness on TempEval-3, setting a new state-of-the-art for the full set of fine-grained temporal relations.
-
COMPASS: A Unified Decision-Intelligence System for Navigating Performance Trade-off in HPC
COMPASS formalizes HPC configuration questions as ML tasks on traces, quantifies recommendation trustworthiness, and delivers 65.93% lower average job turnaround time plus 80.93% lower node usage versus prior methods in simulator tests.
-
Mind the Gap? A Distributional Comparison of Real and Synthetic Priors for Tabular Foundation Models
The synthetic prior for tabular foundation models covers only a narrow part of real table distributions, but this mismatch does not degrade model generalization.
-
Domain-Adapted Fine-Tuning of ECG Foundation Models for Multi-Label Structural Heart Disease Screening
Domain-adapted ECG foundation models with self-supervised pretraining and selective fine-tuning reach macro-AUROC 0.8509 for multi-label structural heart disease detection on the EchoNext benchmark.