1 citations · 3 across the 11 of their papers we have counts for
12 papers
PRO-CUA: Process-Reward Optimization for Computer Use Agents
Yifei He, Rui Yang, Hao Bai +2
Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and l…
WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering
Yifei He, Pranit Chawla, Yaser Souri +2
Computer use agents (CUAs) can operate real-world digital interfaces but remain difficult to train due to the high cost of graphical user interface (GUI) interaction and the scarci…
MergeBench: A Benchmark for Merging Domain-Specialized LLMs
Yifei He, Siqi Zeng, Yuzheng Hu +3
Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without t…
Efficiently Editing Mixture-of-Experts Models with Compressed Experts
Yifei He, Yang Liu, Chen Liang +1
Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typic…
Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
Siqi Zeng, Yifei He, Meitong Liu +5
Task arithmetic, representing downstream tasks through linear operations on task vectors, has emerged as a simple yet powerful paradigm for transferring knowledge across diverse se…
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
Samuele Poppi, Zheng-Xin Yong, Yifei He +4
Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily remove…
Scaling Laws for Multilingual Language Models
Yifei He, Alon Benhaim, Barun Patra +6
We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual…
Semi-Supervised Reward Modeling via Iterative Self-Training
Yifei He, Haoxiang Wang, Ziyan Jiang +2
Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language mode…
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
Yifei He, Yuzheng Hu, Yong Lin +2
Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing…
Robust Multi-Task Learning with Excess Risks
Yifei He, Shiji Zhou, Guojun Zhang +5
Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing met…
Gradual Domain Adaptation: Theory and Algorithms
Yifei He, Haoxiang Wang, Bo Li +1
Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way. Though widely applied, UDA faces a great challenge…
Greedy Modality Selection via Approximate Submodular Maximization
Runxiang Cheng, Gargi Balasubramaniam, Yifei He +2
Multimodal learning considers learning from multi-modality data, aiming to fuse heterogeneous sources of information. However, it is not always feasible to leverage all available m…