AutoSelection discovers data recipes from a 90K instruction pool that outperform full-data training and other selectors on reasoning tasks for SFT across multiple models.
Practical bayesian optimization of machine learning algorithms.Advances in neural information processing systems, 25
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6roles
background 2polarities
background 2representative citing papers
A knowledge-first approach to LLM-driven automatic heuristic design in combinatorial optimization yields better discovery efficiency, transfer, and generalization than code-centric baselines by formalizing a distortion-compression trade-off.
FLUID is a continuous-time transformer using Liquid Attention Networks to model attention as stable ODE solutions that interpolate between discrete SDPA and CT-RNNs, with an explicit sink gate and liquid hyper-connections for better information flow.
An LLM-driven dual-loop controller claims 72.5% stable-phase improvement over default and 153.3% over the strongest non-LLM baseline, but the comparison protocol inflates the gaps by scoring baselines during continued exploration.
A bilevel method learns composite pretraining loss weights online via gradient alignment with a downstream objective, matching tuned baselines at roughly 30% extra cost over one training run.
The paper derives provably tighter instantaneous regret bounds for GP-UCB and proposes (ε,δ)-optimal stopping criteria for Bayesian optimization based on those bounds.
citing papers explorer
-
From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning
AutoSelection discovers data recipes from a 90K instruction pool that outperform full-data training and other selectors on reasoning tasks for SFT across multiple models.
-
Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs
A knowledge-first approach to LLM-driven automatic heuristic design in combinatorial optimization yields better discovery efficiency, transfer, and generalization than code-centric baselines by formalizing a distortion-compression trade-off.
-
FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning
FLUID is a continuous-time transformer using Liquid Attention Networks to model attention as stable ODE solutions that interpolate between discrete SDPA and CT-RNNs, with an explicit sink gate and liquid hyper-connections for better information flow.
-
TuxBot: Semantic-Aware Online OS Tuning with Large Language Models
An LLM-driven dual-loop controller claims 72.5% stable-phase improvement over default and 153.3% over the strongest non-LLM baseline, but the comparison protocol inflates the gaps by scoring baselines during continued exploration.
-
When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
A bilevel method learns composite pretraining loss weights online via gradient alignment with a downstream objective, matching tuned baselines at roughly 30% extra cost over one training run.
-
Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
The paper derives provably tighter instantaneous regret bounds for GP-UCB and proposes (ε,δ)-optimal stopping criteria for Bayesian optimization based on those bounds.