4 citations · 5 across the 12 of their papers we have counts for
13 papers
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
Chong Zeng, Ziqian Zhong, Kexun Zhang +5
Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. Verifiers can be attacked into a…
SETA: Scaling Environments for Terminal Agents
Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru +19
Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs). Among these, the te…
Decentralized Multi-Agent Systems with Shared Context
Yuzhen Mao, Azalia Mirhoseini, Jerry Gu +3
Multi-agent systems (MAS) can scale large language model agents on long-horizon tasks by running them in parallel, yet existing designs waste much of this parallelism in bubbles: a…
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
Yuzhen Mao, Qitong Wang, Martin Ester +1
Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation duri…
Simplified Sparse Attention via Gist Tokens
Yuzhen Mao, Michael Y. Li, Emily B. Fox
Sparse attention can reduce the cost of long-context inference, but most variants introduce new architectural components. We introduce Simplified Sparse Attention (SSA), a simpler…
A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection
Ningkang Peng, Yuzhe Mao, Yuhao Zhang +5
Out-of-Distribution (OOD) detection is a cornerstone for the safe deployment of AI systems in the open world. However, existing methods treat OOD detection as a binary classificati…
Mem-α: Learning Memory Construction via Reinforcement Learning
Yu Wang, Ryuichi Takanobu, Zhiqi Liang +4
Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmente…
Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity
Victor Li, Baiting Chen, Yuzhen Mao +2
Calibrating blackbox machine learning models to achieve risk control is crucial to ensure reliable decision-making. A rich line of literature has been studying how to calibrate a m…
ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes
Amartya Mukherjee, Ruizhi Deng, He Zhao +3
This work introduces a novel approach to modeling temporal point processes using diffusion models with an asynchronous noise schedule. At each step of the diffusion process, the no…
IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
Yuzhen Mao, Martin Ester, Ke Li
One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space c…
EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
Haohui Wang, Yuzhen Mao, Yujun Yan +8
Non-IID transfer learning on graphs is crucial in many high-stakes domains. The majority of existing works assume stationary distribution for both source and target domains. Howeve…
Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks
Yuzhen Mao, Zhun Deng, Huaxiu Yao +3
As machine learning has been deployed ubiquitously across applications in modern data science, algorithmic fairness has become a great concern. Among them, imposing fairness constr…
Augmenting Knowledge Transfer across Graphs
Yuzhen Mao, Jianhui Sun, Dawei Zhou
Given a resource-rich source graph and a resource-scarce target graph, how can we effectively transfer knowledge across graphs and ensure a good generalization performance? In many…