arXiv:2609.39934v1 Announce Type: cross
Abstract: Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable proba...
By Jinshi Liu, Jiahao Li, Pan Liu, Yanfeng Li, Rui Qian, Zhao Tong, Yue Sun, Tao Tan
arXiv:2605. 18852v2 Announce Type: replace-cross Abstract: Selecting a final checkpoint for multimodal large language models (MLLMs) is challenging when late-stage candidates are closely matched and downstream evaluation signals are noisy.
By Qinwu Xu, Zhuoheng Li, Jessie Salas
arXiv:2610.07518v1 Announce Type: cross
Abstract: Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of...
By Ziqun Bao, Xinyu Zhang, Yuchen Shao, Chengcheng Wan
arXiv:2609.37169v1 Announce Type: cross
Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...
By Zhehao Huang, Changxin Tian, Qingyuan Yang, Kunlong Chen, Ziqi Liu, Zhiqiang Zhang, Xiaolin Huang, Jun Zhou
arXiv:2607. 20046v1 Announce Type: cross Abstract: With the widespread deployment of deep neural networks (DNNs) in safety-critical domains, reducing the cost of model validation under limited testing budgets has become increasingly important.
By Chunyu Liu, Mingyuan Li, Yang Li, Wenmin Li, Fei Gao, Tengfei Tu, Su-Juan Qin
arXiv:2609.06107v1 Announce Type: new
Abstract: Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which do...
By Hao Liang, Mingrui Chen, Hengyi Feng, Meiyi Qiang, Wentao Zhang
The paper introduces a benchmark for predicting a program’s final output and checkpoint state using only its source code and input, extending CRUXEval-style tasks with both short‑ and long‑trace inputs and checkpoints inside and after loops. It evaluates 400 cases from 371 Python and C++ programs across seven settings from four model families, achieving up to 93.0% accuracy on short‑trace final output and 77.0% on long‑trace final output, with reasoning‑enabled settings outperforming non‑reasoning ones by 33.1 to 55.2 percentage points. The study also shows that longer‑trace inputs can change correctness outcomes and that the benchmark reveals errors that short‑output scores alone would miss.
By Xiaohong Chen, David Bucur, Chenglong Ma, Yi Zhang, Lingming Zhang, Sriram Vishwanath, Grigore Rosu
arXiv:2609.08966v1 Announce Type: new
Abstract: Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the...
By Sohir Maskey, Philipp Scholl, Jonas Knupp, Pit Neitemeier, Sascha Wirges
arXiv:2608. 10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment.
By Joyjeet Singh
The paper introduces entry-state sharpening, a data‑free pre‑training step that prepares a language model’s checkpoint in a sharper, lower‑entropy state before test‑time reinforcement learning (TTRL). By reducing policy entropy, the model can more efficiently use its limited adaptation budget, leading to higher endpoint conversion efficiency across tasks such as MATH, GPQA, and AMC. Experiments with different data‑free objectives (e.g., R‑Zero vs. SPIRAL) demonstrate that the choice of pre‑training objective strongly influences the checkpoint’s readiness for TTRL, and a label‑free self‑distillation intervention can further sharpen the entry state.
By Zhanming Zhang, Vinoth Selvendran
arXiv:2609.13714v1 Announce Type: new
Abstract: An updated model can improve an aggregate metric while degrading a slice that matters to a downstream user. We study checkpoint selection subject to no...
By Shengwei Zhang, Tao Wu, Fei Qian
The paper introduces the concept of intervention fidelity in latent world models, measuring whether a model’s open‑loop transitions align with actual environment interventions. Experiments on TD‑MPC2, Cheetah, and DreamerV3 show that high reward fit does not guarantee fidelity, and that self‑supervised models can outperform task‑anchored ones in preserving intervention effects. The authors propose a capture‑gated audit to localize failures and argue that fidelity must be directly audited on the model’s native interface.
By Donna Vakalis