6 papers
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Zhaojian Yu, Penghao Yin, Shuzheng Gao +3
Training language models (LMs) remains a highly human-intensive process, even as frontier language model agents become increasingly capable at software engineering and other long-h…
VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding
Yinghao Wu, Zhuoyan Luo, Yiyao Yu +3
Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emph…
Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express
Ziyi Ding, Xiao-Ping Zhang
We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed linear probe recovers the evid…
Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing
Yan Li, Lin Liu, Xiaopeng Zhang +1
Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally cohere…
Z1: Efficient Test-time Scaling with Code
Zhaojian Yu, Yinghao Wu, Yilun Zhao +2
Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, yet this often entails longer contexts and numerous reasoning token c…
HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation
Zhaojian Yu, Yilun Zhao, Arman Cohan +1
We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented w…