9 papers
WebWorld: The Browser as a World Model for Self-Improving Web Code
Jiajun Wu, Jian Yang, Yaxin Du +7
VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility under that judge is a poor pr…
InCoder-32B-Thinking: Industrial Code World Model for Thinking
Jian Yang, Wei Zhang, Jiajun Wu +22
Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reasoning traces showing how engineers reason about hardware constraints and…
InCoder-32B: Code Foundation Model for Industrial Scenarios
Jian Yang, Wei Zhang, Jiajun Wu +25
Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios tha…
Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
Nanxiang Jiang, Zhaoxin Fan, Baisen Wang +8
Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures…
CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language
Junhang Cheng, Fang Liu, Jia Li +3
Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming languages primarily fo…
Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
Zhijun Chen, Zeyu Ji, Qianren Mao +13
We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each query, harnessing the collective…
Rethinking what Matters: Effective and Robust Multilingual Realignment for Low-Resource Languages
Quang Phuoc Nguyen, David Anugraha, Felix Gaschi +2
Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for t…
Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling
Qianhui Zhao, Li Zhang, Fang Liu +8
In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid itera…
AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT Length
Junhang Cheng, Fang Liu, Chengru Wu +1
While Large Language Models (LLMs) have significantly advanced code generation efficiency, they face inherent challenges in balancing performance and inference costs across diverse…