11 papers · 1 filter
SolveEdit: Benchmarking Visual Problem Solving in Generative Models
Wenjie Shu, Yexin Liu, Harold Haodong Chen +9
Machine intelligence is often evaluated through abstract reasoning problems, yet many real-world problems are visual, such as arranging objects, repairing layouts, or tracing route…
GenRouter: Unified Workflow Routing for Agentic Image Generation
Harold Haodong Chen, Zhiyu Hou, Wen-Jie Shu +4
The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfill…
No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
Haojian Huang, Harold Haodong Chen, Meng Luo +6
We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. Unlike previous benchmarks th…
Show, Don't Tell: Morphing Latent Reasoning into Image Generation
Harold Haodong Chen, Xinxiang Yin, Wen-Jie Shu +6
Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation--a hallmark of human…
LoopViT: Scaling Visual ARC with Looped Transformers
Wen-Jie Shu, Xuerui Qiu, Rui-Jie Zhu +3
Recent advances in visual reasoning have leveraged vision transformers to tackle the ARC-AGI benchmark. However, we argue that the feed-forward architecture, where computational de…
TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
Harold Haodong Chen, Disen Lan, Wen-Jie Shu +10
The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consi…
Structure-Aware Prototype Guided Trusted Multi-View Classification
Haojian Huang, Jiahao Shi, Zhe Liu +4
Trustworthy multi-view classification (TMVC) addresses the challenge of achieving reliable decision-making in complex scenarios where multi-source information is heterogeneous, inc…
ScalingAR: Scaling Confidence for Autoregressive Image Generation
Harold Haodong Chen, Xianfeng Wu, Wen-Jie Shu +4
Test-time strategies have shown remarkable success in improving large language models, but their application to next-token prediction (NTP) autoregressive (AR) image generation rem…
Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
Harold Haodong Chen, Haojian Huang, Qifeng Chen +2
Recent advancements in video generation have enabled the creation of high-quality, visually compelling videos. However, generating videos that adhere to the laws of physics remains…
Temporal Regularization Makes Your Video Generator Stronger
Harold Haodong Chen, Haojian Huang, Xianfeng Wu +5
Temporal quality is a critical aspect of video generation, as it ensures consistent motion and realistic dynamics across frames. However, achieving high temporal coherence and dive…
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
Xianfeng Wu, Yajing Bai, Haoze Zheng +8
Recent advances in text-to-image generation have primarily relied on extensive datasets and parameter-heavy architectures. These requirements severely limit accessibility for resea…