1 citations · 1 across the 22 of their papers we have counts for
25 papers
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang +6
Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assign…
CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning
Xin Yan, Zhengbo Jiao, Jiaqi Liu +11
Reinforcement learning enables computer-use agents to improve through interaction with real software environments, including websites and desktop applications. However, conventiona…
SpikeOPD: Stable On-Policy Distillation for Autoregressive Spiking Language Models
Enqiao Lu, Xingrui Yu, Yiwei Fu +7
Spiking neural networks (SNNs) offer a path to energy-efficient language modeling through sparse encoding and event-driven computation, but training capable spiking language models…
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Pengfei Zhou, Hexin Wang, Zhengfeiyang Zhang +5
A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this strategy is inefficient: scaling world models also requires a rec…
SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks
Tao Yu, Yifei Qu, Zhiqing Cui +14
Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA e…
Improving Generalization Robustness of Multimodal RLVR
Pengfei Zhou, Zhiwei Tang, Xiaopeng Peng +11
Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing th…
Unified Hallucination Fuzzing for Multimodal Large Language Models
Pengfei Zhou, Jiajun Song, Zhiwei Tang +12
Hallucination remains a persistent challenge for Multimodal Large Language Models (MLLMs), severely limiting their reliability in high-stakes applications. Existing evaluations, pr…
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
Tong Bai, Zhenglin Wan, Pengfei Zhou +3
Large skill libraries are now standard equipment for LLM agents, and which subset reaches the prompt decides what the agent can do. Enumeration and top- embedding retrieval both…
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Pengfei Zhou, Zhiwei Tang, Yixing Ma +8
Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Con…
Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents
Chubin Zhang, Zhenglin Wan, Xingrui Yu +5
Tool-augmented agents are typically evaluated by their gains under reliable external feedback. Yet these gains leave open a key counterfactual: when feedback is unreliable, would t…
Calibration Is Not Control: Intervention Value for LLM-Agent Oversight
Chubin Zhang, Zhenglin Wan, Xingrui Yu +5
Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can differ in whether intervention helps.…
GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs
Weidong Tang, Jierui Li, Yueling Hou +7
True general intelligence requires not only a model of the physical world but also a social world model: the capacity to infer how individual mental states interact and crystallize…
Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents
Zhijie Ding, Weinan Hong, Zicheng Zhu +6
Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents must decide when to intervene…
A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models
Ying Lu, Peng-Fei Zhou, Qi-Xuan Fang +3
Dense linear maps carry much of the parameter and computational burden of modern neural networks, yet their dense form leaves the organization of learned couplings implicit. Quantu…
On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
Suorong Yang, Jie Zong, Lihang Wang +6
Data augmentation has been widely employed to improve the generalization of deep neural networks. Most existing methods apply fixed or random transformations. However, we find that…
RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
Wangbo Zhao, Yizeng Han, Zhiwei Tang +7
Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse att…
MDK12-Bench: A Comprehensive Evaluation of Multimodal Large Language Models on Multidisciplinary Exams
Pengfei Zhou, Xiaopeng Peng, Fanrui Zhang +18
Multimodal large language models (MLLMs), which integrate language and visual cues for problem-solving, are crucial for advancing artificial general intelligence (AGI). However, cu…
Neural-Driven Image Editing
Pengfei Zhou, Jie Xia, Xiaopeng Peng +15
Traditional image editing typically relies on manual prompting, making it labor-intensive and inaccessible to individuals with limited motor control or language abilities. Leveragi…
Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans
Yansheng Qiu, Li Xiao, Zhaopan Xu +3
The goal of achieving Artificial General Intelligence (AGI) is to imitate humans and surpass them. Models such as OpenAI's o1, o3, and DeepSeek's R1 have demonstrated that large la…
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
Ziqiao Wang, Wangbo Zhao, Yuhao Zhou +9
Diffusion Transformers (DiTs) deliver state-of-the-art image quality, yet their training remains notoriously slow. A recent remedy -- representation alignment (REPA) that matches D…
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
Zekai Li, Xinhao Zhong, Samir Khaki +49
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance co…
MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models
Pengfei Zhou, Fanrui Zhang, Xiaopeng Peng +17
Multimodal reasoning, which integrates language and visual cues into problem solving and decision making, is a fundamental aspect of human intelligence and a crucial step toward ar…
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
Zhaopan Xu, Pengfei Zhou, Jiaxin Ai +6
Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recent…
ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges
Jiaxin Ai, Pengfei Zhou, Zhaopan Xu +8
As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuri…