145 citations · 154 across the 18 of their papers we have counts for
20 papers
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
Zihan Ding, Longxu Dou, Qi Gao +26
Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workfl…
Reinforcement Learning: From Algorithms To Foundation Models
Zihan Ding
Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an agent should act to maximise lon…
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Yuqing Wang, Zhijie Lin, Ceyuan Yang +10
Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrained VAE for image generation…
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis
Kewei Xu, Xiaoben Lu, Shuofei Qiao +4
Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical…
PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework
Zihan Ding, Ziyuan Yang, Yi Zhang
The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation. However, existing methods re…
From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework
Zihan Ding, Ziyuan Yang, Yi Zhang
Multimodal controversy detection (MCD) identifies controversial content in videos and their associated user comments, to support risk management for social video platforms.Prior re…
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Chengshuai Shi, Wenzhe Li, Xinran Liang +10
Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has emerged as a promising frontier…
Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven Media
Zihan Ding, Xinyi Wang, Junlong Chen +2
Creators struggle to edit long-form, narrative-rich videos not because of UI complexity, but due to the cognitive demands of searching, storyboarding, and sequencing hours of foota…
Single-stream Policy Optimization
Zhongwen Xu, Zihan Ding
We revisit policy-gradient optimization for Large Language Models (LLMs) from a single-stream perspective. Prevailing group-based methods like GRPO reduce variance with on-the-fly…
LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
Seth Karten, Wenzhe Li, Zihan Ding +3
We present the LLM Economist, a novel framework that uses agent-based modeling to design and assess economic policies in strategic environments with hierarchical decision-making. A…
VRAG: Learning World Models for Interactive Video Generation
Taiye Chen, Xun Hu, Zihan Ding +1
Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video g…
Generative Diffusion Modeling: A Practical Handbook
Zihan Ding, Chi Jin
This handbook offers a unified perspective on diffusion models, encompassing diffusion probabilistic models, score-based generative models, consistency models, rectified flow, and…
DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
Zihan Ding, Chi Jin, Difan Liu +6
Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps require…
Reinforcement Learning in High-frequency Market Making
Yuheng Zheng, Zihan Ding
This paper establishes a new and comprehensive theoretical analysis for the application of reinforcement learning (RL) in high-frequency market making. We bridge the modern RL theo…
How to beat a Bayesian adversary
Zihan Ding, Kexin Jin, Jonas Latz +1
Deep neural networks and other modern machine learning models are often susceptible to adversarial attacks. Indeed, an adversary may often be able to change a model's prediction th…
FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
Wenzhe Li, Zihan Ding, Seth Karten +1
Recent advances in reinforcement learning (RL) heavily rely on a variety of well-designed benchmarks, which provide environmental platforms and consistent criteria to evaluate exis…
Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning
Zihan Ding, Amy Zhang, Yuandong Tian +1
We introduce Diffusion World Model (DWM), a conditional diffusion model capable of predicting multistep future states and rewards concurrently. As opposed to traditional one-step d…
Survey of Consciousness Theory from Computational Perspective
Zihan Ding, Xiaoxi Wei, Yidan Xu
Human consciousness has been a long-lasting mystery for centuries, while machine intelligence and consciousness is an arduous pursuit. Researchers have developed diverse theories f…
Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
Zihan Ding, Chi Jin
Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). Howeve…
Game-Theoretic Multiagent Reinforcement Learning
Yaodong Yang, Chengdong Ma, Zihan Ding +4
Tremendous advances have been made in multiagent reinforcement learning (MARL). MARL corresponds to the learning problem in a multiagent system in which multiple agents learn simul…