8 papers
MemForm: Benchmarking Memory Formation Poisoning in LLM Agents
Haowen Pan, Pengyang Shao, Yunshan Ma +4
Long-term memory enables LLM agents to learn from past interactions but exposes memory formation to adversarial influence. Existing studies primarily organize memory poisoning by a…
AlphaPADI: Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete Diffusion
Yanzheng Jin, Pengyang Shao, Yunshan Ma +5
Formulaic alpha discovery seeks symbolic expressions that predict cross-sectional asset returns. In deployment, multiple formulas are combined into an alpha pool, where each formul…
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation
Nai-Xin Zhai, Weihua Cheng, Dexu Yu +9
Video generation is central to AI-powered content creation. Aligning generated videos with human preferences is a key criterion for evaluating generation quality. Despite significa…
SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment
Dexu Yu, Youhua Li, Zhaoyang Guan +12
Agent skills have become a practical way to extend large language model agents, but the growing skill ecosystem still lacks a reliable way to judge whether a skill is worth deployi…
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
Tianyi Jiang, Arctanx An, Hengyi Feng +12
Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a sing…
BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
Pengyang Shao, Naixin Zhai, Lei Chen +4
As Large Language Models (LLMs) increasingly shape online content, removing targeted information from well-trained LLMs (also known as LLM unlearning) has become critical for web g…
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
Naixin Zhai, Pengyang Shao, Binbin Zheng +4
Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typically treat all tokens i…
Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks
Yunfeng Diao, Naixin Zhai, Changtao Miao +4
Recent advancements in image synthesis, particularly with the advent of GAN and Diffusion models, have amplified public concerns regarding the dissemination of disinformation. To a…