4 citations · 9 across the 15 of their papers we have counts for
18 papers
How Far Do Persona Effects Generalize in Language Models?
Yufan Zhou, Yuxuan Liu, Enze Ma +6
Persona prompts ask language models to answer as particular kinds of people. We test whether relationships learned from these effects predict responses to new questions and remain…
MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
Tianze Xu, Yanzhao Zheng, Zhentao Zhang +10
Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes each prompt to a domain-matched t…
AlphaEval: Evaluating Agents in Production
Pengrui Lu, Bingyu Xu, Wenjun Zhang +24
The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure age…
Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
Tianze Xu, Yanzhao Zheng, Pengrui Lu +11
Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. Howeve…
ASI-Evolve: AI Accelerates AI
Weixian Xu, Tiantian Mi, Yixiu Liu +6
Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they…
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
SII-GAIR, Sand. ai, : +43
We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio…
ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development
Pengrui Lu, Shiqi Zhang, Yunzhong Hou +8
Recent coding agents can generate complete codebases from simple prompts, yet existing evaluations focus on issue-level bug fixing and lag behind end-to-end development. We introdu…
daVinci-Dev: Agent-native Mid-training for Software Engineering
Ji Zeng, Dayuan Fu, Tiantian Mi +14
Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously…
DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
Zhen Wang, Yufan Zhou, Zhongyan Luo +5
Simulating human profiles by instilling personas into large language models (LLMs) is rapidly transforming research in agentic behavioral simulation, LLM personalization, and human…
Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training
Dayuan Fu, Yunze Wu, Xiaojie Cai +13
Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, train…
InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research
Yunze Wu, Dayuan Fu, Weiye Si +13
AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills…
Context Engineering 2.0: The Context of Context Engineering
Qishuo Hua, Lyumanshan Ye, Dayuan Fu +6
Karl Marx once wrote that ``the human essence is the ensemble of social relations'', suggesting that individuals are not isolated entities but are fundamentally shaped by their int…
Neural Architecture Discovery via Autonomous Evolution
Yixiu Liu, Yang Nan, Weixian Xu +4
Recent progress in LLM agents has advanced the prospect of autonomous research. Yet whether AI can complete difficult long-horizon tasks, especially those that advance AI research…
ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry
Tianze Xu, Pengrui Lu, Lyumanshan Ye +2
The emergence of deep research systems presents significant capabilities in problem-solving, extending from basic queries to sophisticated research tasks. However, existing benchma…
Interaction as Intelligence: Deep Research With Human-AI Partnership
Lyumanshan Ye, Xiaojie Cai, Xinkai Wang +23
This paper introduces "Interaction as Intelligence" research series, presenting a reconceptualization of human-AI relationships in deep research tasks. Traditional approaches treat…
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
Yuxiang Zheng, Dayuan Fu, Xiangkun Hu +4
Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on…
"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction
Shuning Zhang, Lyumanshan Ye, Xin Yi +5
Memories, encompassing past inputs in context window and retrieval-augmented generation (RAG), frequently surface during human-LLM interactions, yet users are often unaware of thei…
Adanonymizer: Interactively Navigating and Balancing the Duality of Privacy and Output Performance in Human-LLM Interaction
Shuning Zhang, Xin Yi, Haobin Xing +3
Current Large Language Models (LLMs) cannot support users to precisely balance privacy protection and output performance during individual consultations. We introduce Adanonymizer,…