17 papers
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World
Yuanyang Yin, Gongxuan Wang, Yifan Zhan +3
Interactive world models must support persistent memory, responsive interaction, and long-horizon generation, yet these requirements place conflicting demands on the model. Maintai…
WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents
Yao Zhang, Shijie Tang, Zeyu Li +2
Web agents hold great potential for automating complex computer tasks, yet their interactions involve long-horizon, sequential decision-making with irreversible actions. In such se…
AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
Haokun Chen, Jianing Li, Yao Zhang +4
Multimodal Large Language Models (MLLMs) achieve impressive performance once optimized on massive datasets. Such datasets often contain sensitive or copyrighted content, raising si…
Deep Research Brings Deeper Harm
Shuo Chen, Zonggen Li, Zhen Han +7
Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detai…
Bag of Tricks for Subverting Reasoning-based Safety Guardrails
Shuo Chen, Zhen Han, Haokun Chen +6
Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs'…
GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning
Yao Zhang, Yu Wu, Haowei Zhang +6
Process Reward Models (PRMs) aim to improve multi-step reasoning in Large Language Models (LLMs) by supervising intermediate steps and identifying errors. However, building effecti…