Yuxuan Tang

Yifan Feng, Yuxuan Tang

We consider a preference learning setting where every participant chooses an ordered list of $k$ most preferred items among a displayed set of candidates. (The set can be different for every participant.) We identify a distance-based ranking model for the population's preferences and their (ranked) choice behavior. The ranking model resembles the Mallows model but uses a new distance function called Reverse Major Index (RMJ). We find that despite the need to sum over all permutations, the RMJ-based ranking distribution aggregates into (ranked) choice probabilities with simple closed-form expression. We develop effective methods to estimate the model parameters and showcase their generalization power using real data, especially when there is a limited variety of display sets.

Frank F. Xu, Yufan Song, Boxuan Li et al. · cmu

We interact with computers on an everyday basis, be it in everyday life or work, and many aspects of work can be done entirely with access to a computer and the Internet. At the same time, thanks to improvements in large language models (LLMs), there has also been a rapid development in AI agents that interact with and affect change in their surrounding environments. But how performant are AI agents at accelerating or even autonomously performing work-related tasks? The answer to this question has important implications both for industry looking to adopt AI into their workflows and for economic policy to understand the effects that adoption of AI may have on the labor market. To measure the progress of these LLM agents' performance on performing real-world professional tasks, in this paper we introduce TheAgentCompany, an extensible benchmark for evaluating AI agents that interact with the world in similar ways to those of a digital worker: by browsing the Web, writing code, running programs, and communicating with other coworkers. We build a self-contained environment with internal web sites and data that mimics a small software company environment, and create a variety of tasks that may be performed by workers in such a company. We test baseline agents powered by both closed API-based and open-weights language models (LMs), and find that the most competitive agent can complete 30% of tasks autonomously. This paints a nuanced picture on task automation with LM agents--in a setting simulating a real workplace, a good portion of simpler tasks could be solved autonomously, but more difficult long-horizon tasks are still beyond the reach of current systems. We release code, data, environment, and experiments on https://the-agent-company.com.

Yuxuan Tang, Yifan Feng

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from richer forms of human feedback, such as multiwise comparisons and top-$k$ rankings. We propose Ranked Choice Preference Optimization (RCPO), a unified framework that bridges preference optimization with (ranked) choice modeling via maximum likelihood estimation. The framework is flexible, supporting both utility-based and rank-based choice models. It subsumes several existing pairwise methods (e.g., DPO, SimPO), while providing principled training objectives for richer feedback formats. We instantiate this framework with two representative ranked choice models (Multinomial Logit and Mallows-RMJ). Empirical studies on Llama-3-8B-Instruct and Gemma-2-9B-it across AlpacaEval 2 and Arena-Hard benchmarks show that RCPO consistently outperforms competitive baselines. RCPO shows how directly leveraging ranked preference data, combined with the right choice models, yields more effective alignment. It offers a versatile and extensible foundation for incorporating (ranked) choice modeling into LLM training.

Aihua Mao, Yuxuan Tang, Jiangtao Huang et al.

In this paper we study the task of a single-view image-guided point cloud completion. Existing methods have got promising results by fusing the information of image into point cloud explicitly or implicitly. However, given that the image has global shape information and the partial point cloud has rich local details, We believe that both modalities need to be given equal attention when performing modality fusion. To this end, we propose a novel dual-channel modality fusion network for image-guided point cloud completion(named DMF-Net), in a coarse-to-fine manner. In the first stage, DMF-Net takes a partial point cloud and corresponding image as input to recover a coarse point cloud. In the second stage, the coarse point cloud will be upsampled twice with shape-aware upsampling transformer to get the dense and complete point cloud. Extensive quantitative and qualitative experimental results show that DMF-Net outperforms the state-of-the-art unimodal and multimodal point cloud completion works on ShapeNet-ViPC dataset.