3 citations · 11 across the 17 of their papers we have counts for
18 papers
MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
Jingxuan Wu, Yuzhe Yang, Yiqiao Huang +6
An assistant that serves the same user over a long horizon has to answer from what that user has revealed: which preferences still hold, which were revised, and which constraints a…
Figures as Programs: Recursive Generation of Editable Scientific Figures
Yepeng Liu, Dasen Dai, Chengzhi Liu +7
Scientific methodology figures are essential for communicating complex methods clearly, yet creating them remains labor-intensive and typically requires multiple rounds of refineme…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +355
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Chengzhi Liu, Yuzhe Yang, Sophia Xiao Pu +14
Multimodal large language models are increasingly deployed as long-horizon agents, where memory must do more than recall: it must track an evolving world, revise what has gone stal…
Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
Sophia Xiao Pu, Zhaotian Weng, Chengzhi Liu +4
Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning…
Auditing Agent Harness Safety
Chengzhi Liu, Yichen Guo, Yepeng Liu +8
LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a c…
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Zhen Zhang, Changyi Yang, Zijie Xia +11
Tokens are the fundamental units of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite it…
Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
Feilong Tang, Chengzhi Liu, Zhongxing Xu +9
Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations…
PG-SAM: Prior-Guided SAM with Medical for Multi-organ Segmentation
Yiheng Zhong, Zihong Luo, Chengzhi Liu +7
Segment Anything Model (SAM) demonstrates powerful zero-shot capabilities; however, its accuracy and robustness significantly decrease when applied to medical image segmentation. E…
MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation
Haochen Xue, Feilong Tang, Ming Hu +13
Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, th…
Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation
Xinkun Wang, Yifang Wang, Senwei Liang +7
This paper discusses how ophthalmologists often rely on multimodal data to improve diagnostic accuracy. However, complete multimodal data is rare in real-world applications due to…
Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis
Chengzhi Liu, Zile Huang, Zhe Chen +6
Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data…
Better Sampling, towards Better End-to-end Small Object Detection
Zile Huang, Chong Zhang, Mingyu Jin +3
While deep learning-based general object detection has made significant strides in recent years, the effectiveness and efficiency of small object detection remain unsatisfactory. T…
Goal-guided Generative Prompt Injection Attack on Large Language Models
Chong Zhang, Mingyu Jin, Qinkai Yu +3
Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or…
MC-DBN: A Deep Belief Network-Based Model for Modality Completion
Zihong Luo, Zheng Tao, Yuxuan Huang +2
Recent advancements in multi-modal artificial intelligence (AI) have revolutionized the fields of stock market forecasting and heart rate monitoring. Utilizing diverse data sources…
MTSA-SNN: A Multi-modal Time Series Analysis Model Based on Spiking Neural Network
Chengzhi Liu, Zheng Tao, Zihong Luo +1
Time series analysis and modelling constitute a crucial research area. Traditional artificial neural networks struggle with complex, non-stationary time series data due to high com…
Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities
Hua Tang, Chong Zhang, Mingyu Jin +5
Large language models (LLMs) have been applied in many fields and have developed rapidly in recent years. As a classic machine learning task, time series forecasting has recently b…
Alternative Telescopic Displacement: An Efficient Multimodal Alignment Method
Jiahao Qin, Yitao Xu, Zong Lu +1
In the realm of multimodal data integration, feature alignment plays a pivotal role. This paper introduces an innovative approach to feature alignment that revolutionizes the fusio…