6 papers
CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences
Fangzhou Lin, Peiran Li, Lingyu Xu +12
Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edits and do not fully capture th…
CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
Fangzhou Lin, Shuo Xing, Peiran Li +6
Parallel reasoning, where a generator samples many candidate solutions and an aggregator selects the best, is one of the most effective forms of test-time scaling in large language…
AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference
Fangzhou Lin, Peiran Li, Shuo Xing +6
Large language models struggle to accumulate evidence across multiple rounds of user interaction, failing to update their beliefs in a manner consistent with Bayesian inference. Ex…
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
Hongzhe Du, Weikai Li, Min Cai +5
Post-training is essential for the success of large language models (LLMs), transforming pre-trained base models into more useful and aligned post-trained models. While plenty of w…
The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Shivam Agarwal, Zimin Zhang, Lifan Yuan +2
Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled da…
Automated Molecular Concept Generation and Labeling with Large Language Models
Zimin Zhang, Qianli Wu, Botao Xia +4
Artificial intelligence (AI) is transforming scientific research, with explainable AI methods like concept-based models (CMs) showing promise for new discoveries. However, in molec…