4 citations · 11 across the 19 of their papers we have counts for
19 papers
Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems
Yiran Zhao, Lu Zhou, Liming Fang +4
LLM-based multi-agent systems (MAS) are increasingly considered for high-stakes decision-making, yet outcome-based fairness audits can miss where risks arise within the decision tr…
LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting
Yufei Chen, Yiran Zhao, Xiaogang Xu +3
LLM-based forecasting systems have improved on real-world tasks such as financial markets and sports outcomes, largely through stronger search and tool use. Many systems still ask…
LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
Xiaogang Xu, Jiaqi Tang, Jianmin Chen +12
Large language models (LLMs) now support forecasting systems that combine language-based reasoning with temporal data, evidence retrieval, external tools, and iterative prediction.…
PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data
Zhenchao Tang, Xiaogang Xu, Tianxu Lv +16
Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that cellular perturba…
ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs
Jiale Cui, Yueyao Yuan, Kaixi Zhong +3
The rapid advancement of Auto-Research has surfaced a fundamental evaluation challenge: how can we measure the alignment, logical coherence, and evolutionary completeness of its re…
Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning
Jianmin Chen, Jiaqi Tang, Wei Wei +9
Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthen, models may gradually rely…
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
Runhui Huang, Qihui Zhang, Zhe Liu +3
In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning. I…
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
Runhui Huang, Jie Wu, Rui Yang +2
In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal…
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
Chiyu Zhang, Huiqin Yang, Bendong Jiang +8
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, whe…
Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs
Yiran Zhao, Lu Zhou, Xiaogang Xu +3
As artificial intelligence (AI) is increasingly deployed across domains, ensuring fairness has become a core challenge. However, the field faces a "Tower of Babel'' dilemma: fairne…
Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
Chiyu Zhang, Lu Zhou, Xiaogang Xu +3
Existing black-box jailbreak attacks achieve certain success on non-reasoning models but degrade significantly on recent SOTA reasoning models. To improve attack ability, inspired…
DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
Huiwen Wu, Deyi Zhang, Xiaohan Li +3
The emergence of the Large Language Model (LLM) has shown their superiority in a wide range of disciplines, including language understanding and translation, relational logic reaso…
GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformation
Yating Ma, Xiaogang Xu, Liming Fang +1
Current Transferable Adversarial Examples (TAE) are primarily generated by adding Adversarial Noise (AN). Recent studies emphasize the importance of optimizing Data Augmentation (D…
Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning
Huiwen Wu, Xiaohan Li, Xiaogang Xu +3
The development of Large Language Models (LLMs) has significantly advanced various AI applications in commercial and scientific research fields, such as scientific literature summa…
Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
Chiyu Zhang, Lu Zhou, Xiaogang Xu +2
With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks p…
Distinguish Any Fake Videos: Unleashing the Power of Large-scale Data and Motion Features
Lichuan Ji, Yingqi Lin, Zhenhua Huang +5
The development of AI-Generated Content (AIGC) has empowered the creation of remarkably realistic AI-generated videos, such as those involving Sora. However, the widespread adoptio…
Boosting Image Restoration via Priors from Pre-trained Models
Xiaogang Xu, Shu Kong, Tao Hu +2
Pre-trained models with large-scale training data, such as CLIP and Stable Diffusion, have demonstrated remarkable performance in various high-level computer vision tasks such as i…
Restoration-Oriented Video Frame Interpolation with Region-Distinguishable Priors from SAM
Yan Han, Xiaogang Xu, Yingqi Lin +3
In existing restoration-oriented Video Frame Interpolation (VFI) approaches, the motion estimation between neighboring frames plays a crucial role. However, the estimation accuracy…
Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance
Yingqi Lin, Xiaogang Xu, Jiafei Wu +2
Low-Light Enhancement (LLE) is aimed at improving the quality of photos/videos captured under low-light conditions. It is worth noting that most existing LLE methods do not take ad…