Ximeng Sun

55 papers A* 8A 3Journal 40Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models.
CoRR
Yihao Liang, Ze Wang, Hao Chen, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Emad Barsoum, Zicheng Liu, Niraj K. Jha
2026 J jnl
Learning from Online Videos at Inference Time for Computer-Use Agents.
Trans. Mach. Learn. Res.
Yujian Liu, Ze Wang, Hao Chen, Ximeng Sun, Xiaodong Yu, Jialian Wu, Jiang Liu, Emad Barsoum, Zicheng Liu, Shiyu Chang
2026 J jnl
Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement Learning.
CoRR
Zhikun Xu, Xiaodong Yu, Ben Zhou, Jiang Liu, Jialian Wu, Ze Wang, Ximeng Sun, Hao Chen, Zicheng Liu
2026 J jnl
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents.
CoRR
Kaijie Zhu, Yuzhou Nie, Yijiang Li, Yiming Huang, Jialian Wu, Jiang Liu, Ximeng Sun, Zhenfei Yin, Lun Wang, Zicheng Liu, Emad Barsoum, William Yang Wang, Wenbo Guo
2026 J jnl
VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking.
CoRR
Jingyang Lin, Jialian Wu, Jiang Liu, Ximeng Sun, Ze Wang, Xiaodong Yu, Jiebo Luo, Zicheng Liu, Emad Barsoum
2025 J jnl
APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation.
CoRR
Yuzhen Zhou, Jiajun Li, Yusheng Su, Gowtham Ramesh, Zilin Zhu, Xiang Long, Chenyang Zhao, Jin Pan, Xiaodong Yu, Ze Wang, Kangrui Du, Jialian Wu, Ximeng Sun, Jiang Liu, Qiaolin Yu, Hao Chen, Zicheng Liu, Emad Barsoum
2025 — conf
Agent Laboratory: Using LLM Agents as Research Assistants.
EMNLP (Findings)
Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Michael Moor, Zicheng Liu, Emad Barsoum
2025 J jnl
Agent Laboratory: Using LLM Agents as Research Assistants.
CoRR
Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, Emad Barsoum
2025 J jnl
CaptionQA: Is Your Caption as Useful as the Image Itself?
CoRR
Shijia Yang, Yunong Liu, Bohan Zhai, Ximeng Sun, Zicheng Liu, Emad Barsoum, Manling Li, Chenfeng Xu
2025 J jnl
Directional Reasoning Injection for Fine-Tuning MLLMs.
CoRR
Chao Huang, Zeliang Zhang, Jiang Liu, Ximeng Sun, Jialian Wu, Xiaodong Yu, Ze Wang, Chenliang Xu, Emad Barsoum, Zicheng Liu
2025 J jnl
ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning.
CoRR
Yuxiang Guo, Jiang Liu, Ze Wang, Hao Chen, Ximeng Sun, Yang Zhao, Jialian Wu, Xiaodong Yu, Zicheng Liu, Emad Barsoum
2025 J jnl
Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation.
CoRR
Ze Wang, Hao Chen, Benran Hu, Jiang Liu, Ximeng Sun, Jialian Wu, Yusheng Su, Xiaodong Yu, Emad Barsoum, Zicheng Liu
2025 J jnl
Instella: Fully Open Language Models with Stellar Performance.
CoRR
Jiang Liu, Jialian Wu, Xiaodong Yu, Yusheng Su, Prakamya Mishra, Gowtham Ramesh, Sudhanshu Ranjan, Chaitanya Manem, Ximeng Sun, Ze Wang, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum
2025 J jnl
KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation.
CoRR
Xingrui Wang, Jiang Liu, Ze Wang, Xiaodong Yu, Jialian Wu, Ximeng Sun, Yusheng Su, Alan L. Yuille, Zicheng Liu, Emad Barsoum
2025 J jnl
Latent Visual Reasoning.
CoRR
Bangzheng Li, Ximeng Sun, Jiang Liu, Ze Wang, Jialian Wu, Xiaodong Yu, Hao Chen, Emad Barsoum, Muhao Chen, Zicheng Liu
2025 J jnl
Learning from Online Videos at Inference Time for Computer-Use Agents.
CoRR
Yujian Liu, Ze Wang, Hao Chen, Ximeng Sun, Xiaodong Yu, Jialian Wu, Jiang Liu, Emad Barsoum, Zicheng Liu, Shiyu Chang
2025 J jnl
MOVi: Training-free Text-conditioned Multi-Object Video Generation.
CoRR
Aimon Rahman, Jiang Liu, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Yusheng Su, Vishal M. Patel, Zicheng Liu, Emad Barsoum
2025 — conf
Self-Taught Agentic Long Context Understanding.
ACL (1)
Yufan Zhuang, Xiaodong Yu, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Jingbo Shang, Zicheng Liu, Emad Barsoum
2025 J jnl
Self-Taught Agentic Long Context Understanding.
CoRR
Yufan Zhuang, Xiaodong Yu, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Jingbo Shang, Zicheng Liu, Emad Barsoum
2025 A* conf
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer.
CVPR
Hao Chen, Ze Wang, Xiang Li, Ximeng Sun, Fangyi Chen, Jiang Liu, Jindong Wang, Bhiksha Raj, Zicheng Liu, Emad Barsoum
2025 J jnl
The "Carpet-like" Mechanism of NaD1 on
J. Chem. Inf. Model.
Yueru Zhao, Ximeng Sun, Mengmeng Yuan, Zhixuan Fang, Hua Yu
2025 J jnl
Unleashing Hour-Scale Video Training for Long Video-Language Understanding.
CoRR
Jingyang Lin, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Xiaodong Yu, Hao Chen, Jiebo Luo, Zicheng Liu, Emad Barsoum
2025 J jnl
XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models.
CoRR
Xingrui Wang, Jiang Liu, Chao Huang, Xiaodong Yu, Ze Wang, Ximeng Sun, Jialian Wu, Alan L. Yuille, Emad Barsoum, Zicheng Liu
2024 J jnl
DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition With Limited Annotations.
IEEE Trans. Pattern Anal. Mach. Intell.
Ping Hu, Ximeng Sun, Stan Sclaroff, Kate Saenko
2024 A conf
Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths.
WACV
Ximeng Sun, Rameswar Panda, Chun-Fu Richard Chen, Naigang Wang, Bowen Pan, Aude Oliva, Rogério Feris, Kate Saenko
2024 A* conf
Koala: Key Frame-Conditioned Long Video-LLM.
CVPR
Reuben Tan, Ximeng Sun, Ping Hu, Jui-Hsien Wang, Hanieh Deilamsalehy, Bryan A. Plummer, Bryan C. Russell, Kate Saenko
2024 J jnl
Koala: Key frame-conditioned long video-LLM.
CoRR
Reuben Tan, Ximeng Sun, Ping Hu, Jui-Hsien Wang, Hanieh Deilamsalehy, Bryan A. Plummer, Bryan C. Russell, Kate Saenko
2024 J jnl
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer.
CoRR
Hao Chen, Ze Wang, Xiang Li, Ximeng Sun, Fangyi Chen, Jiang Liu, Jindong Wang, Bhiksha Raj, Zicheng Liu, Emad Barsoum
2023 J jnl
CLAMP: Contrastive LAnguage Model Prompt-tuning.
CoRR
Piotr Teterwak, Ximeng Sun, Bryan A. Plummer, Kate Saenko, Ser-Nam Lim
2023 A* conf
DIME-FM : DIstilling Multimodal and Efficient Foundation Models.
ICCV
Ximeng Sun, Pengchuan Zhang, Peizhao Zhang, Hardik Shah, Kate Saenko, Xide Xia
2023 J jnl
DIME-FM: DIstilling Multimodal and Efficient Foundation Models.
CoRR
Ximeng Sun, Pengchuan Zhang, Peizhao Zhang, Hardik Shah, Kate Saenko, Xide Xia
2023 J jnl
DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations.
CoRR
Ping Hu, Ximeng Sun, Stan Sclaroff, Kate Saenko
2023 J jnl
Label Budget Allocation in Multi-Task Learning.
CoRR
Ximeng Sun, Kihyuk Sohn, Kate Saenko, Clayton Mellina, Xiao Bian
2022 A* conf
DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations.
NeurIPS
Ximeng Sun, Ping Hu, Kate Saenko
2022 J jnl
DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations.
CoRR
Ximeng Sun, Ping Hu, Kate Saenko
2021 A* conf
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition.
ICCV
Rameswar Panda, Chun-Fu (Richard) Chen, Quanfu Fan, Ximeng Sun, Kate Saenko, Aude Oliva, Rogério Feris
2021 J jnl
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition.
CoRR
Rameswar Panda, Chun-Fu Chen, Quanfu Fan, Ximeng Sun, Kate Saenko, Aude Oliva, Rogério Feris
2021 J jnl
All at Once Network Quantization via Collaborative Knowledge Transfer.
CoRR
Ximeng Sun, Rameswar Panda, Chun-Fu Chen, Naigang Wang, Bowen Pan, Kailash Gopalakrishnan, Aude Oliva, Rogério Feris, Kate Saenko
2021 A* conf
Dynamic Network Quantization for Efficient Video Inference.
ICCV
Ximeng Sun, Rameswar Panda, Chun-Fu (Richard) Chen, Aude Oliva, Rogério Feris, Kate Saenko
2021 J jnl
Dynamic Network Quantization for Efficient Video Inference.
CoRR
Ximeng Sun, Rameswar Panda, Chun-Fu Chen, Aude Oliva, Rogério Feris, Kate Saenko
2020 J jnl
A Temporally-Aware Interpolation Network for Video Frame Inpainting.
IEEE Trans. Pattern Anal. Mach. Intell.
Ryan Szeto, Ximeng Sun, Kunyi Lu, Jason J. Corso
2020 A* conf
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning.
NeurIPS
Ximeng Sun, Rameswar Panda, Rogério Feris, Kate Saenko
2020 J jnl
Revisiting Few-shot Activity Detection with Class Similarity Control.
CoRR
Huijuan Xu, Ximeng Sun, Eric Tzeng, Abir Das, Kate Saenko, Trevor Darrell
2020 A conf
TwoStreamVAN: Improving Motion Modeling in Video Generation.
WACV
Ximeng Sun, Huijuan Xu, Kate Saenko
2019 J jnl
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning.
CoRR
Ximeng Sun, Rameswar Panda, Rogério Schmidt Feris
2019 A* conf
Domain Agnostic Learning with Disentangled Representations.
ICML
Xingchao Peng, Zijun Huang, Ximeng Sun, Kate Saenko
2019 J jnl
Domain Agnostic Learning with Disentangled Representations.
CoRR
Xingchao Peng, Zijun Huang, Ximeng Sun, Kate Saenko
2019 J jnl
Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition.
CoRR
Ping Hu, Ximeng Sun, Kate Saenko, Stan Sclaroff
2018 — conf
A Temporally-Aware Interpolation Network for Video Frame Inpainting.
ACCV (3)
Ximeng Sun, Ryan Szeto, Jason J. Corso
2018 J jnl
A Temporally-Aware Interpolation Network for Video Frame Inpainting.
CoRR
Ximeng Sun, Ryan Szeto, Jason J. Corso
2018 J jnl
A Two-Stream Variational Adversarial Network for Video Generation.
CoRR
Ximeng Sun, Huijuan Xu, Kate Saenko
2018 J jnl
Similarity R-C3D for Few-shot Temporal Activity Detection.
CoRR
Huijuan Xu, Bingyi Kang, Ximeng Sun, Jiashi Feng, Kate Saenko, Trevor Darrell
2008 J jnl
Model-driven assessment of system dependability.
Softw. Syst. Model.
Sadaf Mustafiz, Ximeng Sun, Jörg Kienzle, Hans Vangheluwe
2007 — conf
Domain-Specific Modelling With Atom3.
ICSOFT (PL/DPS/KE/MUSE)
Hans Vangheluwe, Ximeng Sun, Eric Bodden
2006 A conf
Model-Driven Assessment of Use Cases for Dependable Systems.
MoDELS
Sadaf Mustafiz, Ximeng Sun, Jörg Kienzle, Hans Vangheluwe