Chen Xing — accepted AI-conference papers

2025

MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs

Kaustubh Deshpande, Ved Sirdeshmukh, Johannes Baptist Mols, Lifeng Jin, Ed-Yeremai Hernandez-Cardona, Dean Lee +4

ACL 2025finding

We present MultiChallenge, a pioneering benchmark evaluating large language models (LLMs) on conducting multi-turn conversations with human users, a crucial yet underexamined capability for their applications. MultiChallenge identifies four categories of challenges in multi-turn conversations that a…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement

XIANGYU PENG, Congying Xia, Xinyi Yang, Caiming Xiong, Chien-Sheng Wu, Chen Xing

ICLR 2025oral

Post-training Large Language Models (LLMs) with explicit reasoning trajectories can enhance their reasoning abilities. However, acquiring such high-quality trajectory data typically demands meticulous supervision from humans or superior models, which can be either expensive or license-constrained. I…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability

Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, Ran Xu +2

ACL 2024long

This paper presents FoFo, a pioneering benchmark for evaluating large language models’ (LLMs) ability to follow complex, domain-specific formats, a crucial yet under-examined capability for their application as AI agents. Despite LLMs’ advancements, existing benchmarks fail to assess their format-fo…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗

2024

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou +34

EMNLP 2024main

Claim: This work is not advocating the use of LLMs for paper (meta-)reviewing. Instead, wepresent a comparative analysis to identify and distinguish LLM activities from human activities. Two research goals: i) Enable better recognition of instances when someone implicitly uses LLMs for reviewing act…

Cited by 29 Source ↗PDF ↗code ↗Scholar ↗

2024

Lemur: Harmonizing Natural Language and Code for Language Agents

Yiheng Xu, Hongjin SU, Chen Xing, Boyu Mi, Qian Liu, Weijia Shi +10

ICLR 2024spotlight

We introduce Lemur and Lemur-Chat, openly accessible language models optimized for both natural language and coding capabilities to serve as the backbone of versatile language agents. The evolution from language chat models to functional language agents demands that models not only master human inte…

Cited by 48 Source ↗PDF ↗code ↗Scholar ↗

2023

GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation

Can Qin, Ning Yu, Chen Xing, Shu Zhang, Zeyuan Chen, Stefano Ermon +3

ICCV 2023poster

Text-to-image (T2I) models based on diffusion processes have achieved remarkable success in controllable image generation using user-provided captions. However, the tight coupling between the current text encoder and image decoder in T2I models makes it challenging to replace or upgrade. Such change…

Cited by 26 PDF ↗code ↗Scholar ↗

2023

Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting

Zahra Fatemi, Chen Xing, Wenhao Liu, Caimming Xiong

ACL 2023short

Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated focus of the gender-neutral data, catastrophic forgetting would…

Cited by 44 Source ↗PDF ↗code ↗Scholar ↗

2023

Mask-Free OVIS: Open-Vocabulary Instance Segmentation Without Manual Mask Annotations

Vibashan VS, Ning Yu, Chen Xing, Can Qin, Mingfei Gao, Juan Carlos Niebles +2

CVPR 2023poster

Existing instance segmentation models learn task-specific information using manual mask annotations from base (training) categories. These mask annotations require tremendous human effort, limiting the scalability to annotate novel (new) categories. To alleviate this problem, Open-Vocabulary (OV) me…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗

2023

Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning

XIANGYU PENG, Chen Xing, Prafulla Kumar Choubey, Chien-Sheng Wu, Caiming Xiong

ICLR 2023poster

Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient training data, prompt tuning performs comparably to full-model…

Cited by 16 Source ↗PDF ↗Scholar ↗

2023

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding

Le Xue, Mingfei Gao, Chen Xing, Roberto Martín-Martín, Jiajun Wu, Caiming Xiong +3

CVPR 2023poster

The recognition capabilities of current state-of-the-art 3D models are limited by datasets with a small number of annotated data and a pre-defined set of categories. In its 2D counterpart, recent advances have shown that similar problems can be significantly alleviated by employing knowledge from ot…

Cited by 281 Source ↗PDF ↗code ↗Scholar ↗

2022

DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents

Mingfei Gao, Le Xue, Chetan Ramaiah, Chen Xing, Ran Xu, Caiming Xiong

COLING 2022main

We propose, DocQueryNet, a value retrieval method with arbitrary queries for form-like documents to reduce human effort of processing forms. Unlike previous methods that only address a fixed set of field items, our method predicts target value for an arbitrary query based on the understanding of the…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2022

Open Vocabulary Object Detection with Pseudo Bounding-Box Labels

Mingfei Gao, Chen Xing, Juan Carlos Niebles, Junnan Li, Ran Xu, Wenhao Liu +1

ECCV 2022poster

"Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent open vocabulary and zero-shot detection methods attempt to det…

Cited by 100 Source ↗PDF ↗code ↗Scholar ↗

2021

Taking Notes on the Fly Helps Language Pre-Training

Qiyu Wu, Chen Xing, Yatao Li, Guolin Ke, Di He, Tie-Yan Liu

ICLR 2021poster

How to make unsupervised language pre-training more efficient and less resource-intensive is an important research direction in NLP. In this paper, we focus on improving the efficiency of language pre-training methods through providing better data utilization. It is well-known that in language data…

Cited by 18 Source ↗PDF ↗Scholar ↗

2020

Distance-Based Learning from Errors for Confidence Calibration

Chen Xing, Sercan Arik, Zizhao Zhang, Tomas Pfister

ICLR 2020poster

Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based learning from errors (DBLE). DBLE bases its confidence estimation on distances in the representation space. In DBLE, we f…

Cited by 49 Source ↗Scholar ↗

2020

On Layer Normalization in the Transformer Architecture

Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing +4

ICML 2020poster

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyper-parameter tunings. I…

Cited by 1272 Source ↗PDF ↗Scholar ↗

2019

Adaptive Cross-Modal Few-shot Learning

Chen Xing, Negar Rostamzadeh, Boris Oreshkin, Pedro O O. Pinheiro

NeurIPS 2019poster

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For c…

Cited by 318 Source ↗PDF ↗code ↗Scholar ↗