Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series
arXiv:2511.01354v1 Announce Type: cross Abstract: Recently, the demand for small and efficient reasoning models to support real-world applications has driven…
How Similar Are Grokipedia and Wikipedia? A Multi-Dimensional Textual and Structural Comparison
arXiv:2510.26899v2 Announce Type: replace-cross Abstract: The launch of Grokipedia, an AI-generated encyclopedia developed by Elon Musk’s xAI, was presented as…
CATArena: Evaluation of LLM Agents through Iterative Tournament Competitions
arXiv:2510.26852v1 Announce Type: new Abstract: Large Language Model (LLM) agents have evolved from basic text generation to autonomously completing complex…
Faithful and Fast Influence Function via Advanced Sampling
arXiv:2510.26776v2 Announce Type: replace-cross Abstract: How can we explain the influence of training data on black-box models? Influence functions (IFs)…
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
arXiv:2510.27462v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) on long chain-of-thought (CoT) trajectories has emerged as a crucial technique for…
CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
arXiv:2510.27442v1 Announce Type: cross Abstract: Vision Transformers (ViTs) have demonstrated strong potential in medical imaging; however, their high computational demands…
On the limitation of evaluating machine unlearning using only a single training seed
arXiv:2510.26714v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) aims to remove the influence of certain data points from a trained…
Towards Piece-by-Piece Explanations for Chess Positions with SHAP
arXiv:2510.25775v1 Announce Type: new Abstract: Contemporary chess engines offer precise yet opaque evaluations, typically expressed as centipawn scores. While effective…
Completion $neq$ Collaboration: Scaling Collaborative Effort with Agents
arXiv:2510.25744v2 Announce Type: replace-cross Abstract: Current evaluations of agents remain centered around one-shot task completion, failing to account for the…
SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuning
arXiv:2510.26457v1 Announce Type: cross Abstract: Identifying and addressing security issues during the early phase of the development lifecycle is critical…