18 citations · 44 across the 7 of their papers we have counts for
10 papers
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
Yong Du, Tongbo Chen, Zhengxi Lu +5
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards,…
Second-Moment Stochastic Approximation Methods
Tao Jiang, Lin Xiao
Classical stochastic approximation methods rely on estimators of the first moment (mean) of a random regression function. We study methods that employ estimators of both the first…
Dense Process Supervision for Search Agents via Fact Utility Estimation
Rongzhi Zhu, Xiangyu Liu, Yi Liu +7
Reinforcement learning (RL) for search agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due to the unclear value of inter…
CommerceVibe: Learning to Design E-Commerce Creatives as Executable Visual Code via Dual-Feedback Reinforcement Learning
Yajiao Xu, Jin Zhang, Jiangbo Ai +4
High-quality e-commerce creatives are essential for presenting products and conveying marketing messages. Recent diffusion models enable scalable creative generation and produce vi…
CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks
Songqin Nong, Xiaoxuan Tang, Jingxuan Xu +4
As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studi…
Kimi K2: Open Agentic Intelligence
Kimi Team, Yifan Bai, Yiping Bao +195
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which…
Stochastic Approximation with Block Coordinate Optimal Stepsizes
Tao Jiang, Lin Xiao
We consider stochastic approximation with block-coordinate stepsizes and propose adaptive stepsize rules that aim to minimize the expected distance from the next iterate to an (unk…
MoBA: Mixture of Block Attention for Long-Context LLMs
Enzhe Lu, Zhejun Jiang, Jingyuan Liu +22
Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in comput…
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Kimi Team, Angang Du, Bofei Gao +93
Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learni…
Synthetic Data in AI: Challenges, Applications, and Ethical Implications
Shuang Hao, Wenfeng Han, Tao Jiang +5
In the rapidly evolving field of artificial intelligence, the creation and utilization of synthetic datasets have become increasingly significant. This report delves into the multi…