10 papers
MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning
Xukun Luan, Jinyan Liu, Yuhui Gong +4
Vision-Language models (VLMs) achieve outstanding performance largely due to the amount of training data available on the internet. At the same time, data holders (e.g., artists) u…
MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations
Sky Ng, Brihi Joshi, Ishan Gupta +47
Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents maintain i…
PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications
Yifan Simon Liu, Qianfeng Wen, Yilan Fan +40
Real user studies are important for understanding how people interact with systems under test or already deployed. In practice, however, they are often costly, time-consuming, and…
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
Xiaomin Li, Yuexing Hao, Jianheng Hou +90
Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and inter…
When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
Yuan Tian, Bing Hu, Fang Wu +3
Think-with-image reasoning is emerging as a new inference paradigm for large vision-language models, but its safety implications remain poorly understood. Existing systems already…
PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
Yunhe Han, Yunqi Gao, Bing Hu +4
Speculative decoding can significantly accelerate LLM inference, especially given that its cloud-edge collaborative deployment offers cloud workload offloading, offline robustness,…
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Binghang Lu, Zheyuan Deng, Runyu Zhang +6
A central challenge in continual learning for large language models (LLMs) is catastrophic forgetting, where adapting to new tasks can substantially degrade performance on previous…
Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering
Xiaomin Li, Jianheng Hou, Zheyuan Deng +6
Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot:…
Multiplayer Nash Preference Optimization
Fang Wu, Xu Huang, Weihao Xuan +8
Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences. However, reward-based methods grou…
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Fang Wu, Aaron Tu, Weihao Xuan +21
Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…