Jia Li

collaborators

3 papers

cs.CL2026

$R^{3}$ -Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets

Peisong Wang, Zhiwei Ma, Bowen Liu +6

In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent benchmarks use independent per…

cs.LG2026

SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates

Ziming Yu, Shuyao Xiao, Xingyu Zhao +6

Zeroth-order (ZO) optimization enables backpropagation-free fine-tuning of large language models, but existing ZO methods suffer from high-variance gradient estimators, making conv…

math.MG2026

Finiteness of Equidistant Affine Subspaces

Jia Li

Let $0\leqslant k<n$, and let $\mathcal N(k,n)$ denote the supremum of the cardinalities of finite families of affine $k$-planes in $\R^n$ whose pairwise Euclidean separati…

R3-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets

SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates

Finiteness of Equidistant Affine Subspaces

$R^{3}$ -Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets