11 papers
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
Ke Zhao, Zixiang Di, Hong Qian +9
Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented…
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
Chang Wu, Junfeng Fang, Houcheng Jiang +5
Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deploym…
DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios
Tongzhou Yu, Mingjia Li, Hong Qian +6
Human creativity has emerged as a critical competency in the era of large language models. Assessing creativity in complex, open-ended environments is a grand challenge in data min…
IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization
Mingjia Li, Jin Wu, Hong Qian +7
Contextualized assessment offers high ecological validity for evaluating creativity but introduces a critical challenge: observed performance may be confounded with cognitive profi…
CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
Hong Qian, Yuanhao Liu, Zihan Zhou +7
While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative s…
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…