11 papers
REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
Li-Ming Zhan, Bo Liu, Chengqiang Xie +2
The paper introduces REAL, a method that trains vector-quantized autoencoders on transformer activations to pinpoint attention heads or layers that most influence a target behavior…
MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models
Lionel Z. Wang, Ka Chung Ng, Yiming Ma +1
Fake news significantly influences decision-making processes by misleading individuals, organizations, and even governments. Large language models (LLMs), as part of generative AI,…
VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
Jinxiang Lai, Wenzhe Zhao, Zexin Lu +7
Visual content generation has advanced from single-image to multi-image workflows, yet existing agents remain largely plan-driven and lack systematic reflection mechanisms to corre…
VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation
Jinxiang Lai, Zexin Lu, Jiajun He +11
Visual content creation tasks demand a nuanced understanding of design conventions and creative workflows-capabilities challenging for general models, while workflow-based agents l…
Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation
Yuanhuiyi Lyu, Chi Kit Wong, Chenfei Liao +5
Recent works have made notable advancements in enhancing unified models for text-to-image generation through the Chain-of-Thought (CoT). However, these reasoning methods separate t…
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning
Yujie Feng, Xujia Wang, Zexin Lu +7
Continual learning (CL) is crucial for deploying large language models (LLMs) in dynamic real-world environments without costly retraining. While recent model ensemble and model me…