WC
Wenhao Chai
cs.CVcs.AIcs.LGcs.CLcs.SEcs.ROcs.MMAthletic PerformanceComprehensionComputer Graphics
On Valency
published · living versionsW_wngsqjyw·v1 · currentpublished
DConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding
with Shidong Cao, Jing Ma, Yuchen Tian, Lun Du +1
1 version
W_9bfw4gjt·v1published
W_472urbcs·v1published
Preprints & journals
70 papers in the corpus · 2022–2026DConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding2610.30920v1 · Shidong Cao, Jing Ma, Wenhao Chai et al.2026 · 0 citationsarXivon Valency
FrontierCS 2: A Benchmark for Computer Science R&D2610.29932v1 · Qiuyang Mang, Wenhao Chai, Runyuan He et al.2026 · 0 citationsarXivon Valency
From Evidence to Action: How Tool-Using Agents Fail2610.07753v1 · Hongzhan Lin, Shidong Cao, Ziyang Luo et al.2026 · 0 citationsarXiv
InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems2610.05775v1 · Enxin Song, Suhao Yu, Yifei Xu et al.2026 · 0 citationsarXiv
EasyPPO: Stabilizing the Critic Is Key2609.36802v1 · Xuanyi Zhou, Qiuyang Mang, Huanzhi Mao et al.2026 · 0 citationsarXiv
An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond2609.24170v1 · Wenbo Zhang, Kaixuan Wang, Yutao Ouyang et al.2026 · 0 citationsarXiv
When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis2609.15309v1 · Kaiyuan Liu, Qiuyang Mang, Bo Peng et al.2026 · 0 citationsarXiv
MatrAIx: Simulating the World with 8.3 Billion Persona Agents2608.04205v1 · Xiaomin Li, Yuexing Hao, Jianheng Hou et al.2026 · 2 citationsarXiv
Learning What to Remember: Test-Time Training via Context Distillation2608.01672v1 · Zixuan Wang, Xingyu Dang, Rui-Jie Zhu et al.2026 · 0 citationsarXiv
RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies2607.04434v3 · Tianxing Chen, Yue Chen, Zixuan Li et al.2026 · 0 citationsarXiv
WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark2606.06538v1 · Yida Yin, Harish Krishnakumar, Chung Peng Lee et al.2026 · 0 citationsarXiv
DeployBench: Benchmarking LLM Agents for Research Artifact Deployment2606.05238v2 · Yuanli Wang, Yaoyao Qian, Yue Zhang et al.2026 · 0 citationsarXiv
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale2605.14445v1 · Runyuan He, Qiuyang Mang, Shang Zhou et al.2026 · 0 citationsarXiv
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation2605.15177v2 · Shang Zhou, Wenhao Chai, Kaiyuan Liu et al.2026 · 0 citationsarXiv
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI2605.08678v3 · Bohan Lyu, Yucheng Yang, Siqiao Huang et al.2026 · 0 citationsarXiv
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images2604.09531v2 · Guanyu Zhou, Yida Yin, Wenhao Chai et al.2026 · 0 citationsarXiv
Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling2602.09084v2 · Ruijie Ye, Jiayi Zhang, Zhuoxin Liu et al.2026 · 0 citationsarXiv
UEval: A Benchmark for Unified Multimodal Generation2601.22155v1 · Bo Li, Yida Yin, Wenhao Chai et al.2026 · 0 citationsarXiv
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces2601.11868v1 · Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini et al.2026 · 2 citationsarXiv
Reasoning Matters for 3D Visual Grounding2601.08811v1 · Hsiang-Wei Huang, Kuang-Ming Chen, Wenhao Chai et al.2026 · 0 citationsarXiv
BabyVision: Visual Reasoning Beyond Language2601.06521v2 · Liang Chen, Weichu Xie, Yiyan Liang et al.2026 · 1 citationarXiv
MovieChat+: Question-Aware Sparse Memory for Long Video Question Answering.40892653 · Song, Enxin, Chai, Wenhao, Ye, Tian et al.2025 · 16 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(1):374-389
SAMURAI: Motion-Aware Memory for Training-Free Visual Object Tracking With SAM 2.41528905 · Yang, Cheng-Yen, Huang, Hsiang-Wei, Chai, Wenhao et al.2026 · 6 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026;35:970-982
UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning2510.19078v1 · Zhongyu Jiang, Wenhao Chai, Lei Li et al.2025 · 1 citationarXiv
VideoNSA: Native Sparse Attention Scales Video Understanding2510.02295v2 · Enxin Song, Wenhao Chai, Shusheng Yang et al.2025 · 0 citationsarXiv
A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision.40138241 · Zhao, Zhonghan, Chai, Wenhao, Hao, Shengyu et al.2025 · 29 citationsIEEE transactions on visualization and computer graphics. 2025;31(10):9368-9386
AutoCode: LLMs as Problem Setters for Competitive Programming2510.12803v1 · Shang Zhou, Zihan Zheng, Kaiyuan Liu et al.2025 · 0 citationsarXiv
Dense Video Understanding with Gated Residual Tokenization2509.14199v2 · Haichao Zhang, Wenhao Chai, Shwai He et al.2025 · 0 citationsarXiv
AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding2507.02591v3 · Weili Xu, Enxin Song, Wenhao Chai et al.2025 · 0 citationsarXiv
ToSA: Token Merging with Spatial Awareness2506.20066v1 · Hsiang-Wei Huang, Wenhao Chai, Kuang-Ming Chen et al.2025 · 2 citationsarXiv
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?2506.11928v1 · Zihan Zheng, Zerui Cheng, Zeyu Shen et al.2025 · 1 citationarXiv
GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning2505.23399v2 · Jusheng Zhang, Yijia Fan, Wenjun Lin et al.2025 · 0 citationsarXiv
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model2505.23606v5 · Qingyu Shi, Jinbin Bai, Zhuoran Zhao et al.2025 · 1 citationarXiv
TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action2505.01583v2 · Jen-Hao Cheng, Yi-Hao Peng, Huapeng Zhou et al.2025 · 0 citationsarXiv
Science-T2I: Addressing Scientific Illusions in Image Synthesis2504.13129v2 · Jialuo Li, Wenhao Chai, Xingyu Fu et al.2025 · 3 citationsarXiv
An Empirical Study of GPT-4o Image Generation Capabilities2504.05979v2 · Sixiang Chen, Jinbin Bai, Zhuoran Zhao et al.2025 · 0 citationsarXiv
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing2504.02826v4 · Xiangyu Zhao, Peiyuan Zhang, Kexian Tang et al.2025 · 11 citationsarXiv
EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments2503.08604v2 · Dongping Li, Tielong Cai, Tianci Tang et al.2025 · 0 citationsarXiv
Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field2502.16303v1 · Wenhao Hu, Wenhao Chai, Shengyu Hao et al.2025 · 2 citationsarXiv
PackDiT: Joint Human Motion and Text Generation via Mutual Prompting2501.16551v1 · Zhongyu Jiang, Wenhao Chai, Zhuoran Zhou et al.2025 · 0 citationsarXiv
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory2411.11922v2 · Cheng-Yen Yang, Hsiang-Wei Huang, Wenhao Chai et al.2024 · 13 citationsarXiv
LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound2410.15074v1 · Xuechen Guo, Wenhao Chai, Shi-Yan Li et al.2024 · 20 citationsarXiv
Ego3DT: Tracking Every 3D Object in Ego-centric Videos2410.08530v1 · Shengyu Hao, Wenhao Chai, Zhonghan Zhao et al.2024 · 7 citationsarXiv
PAD: Personalized Alignment of LLMs at Decoding-Time2410.04070v7 · Ruizhe Chen, Xiaotian Zhang, Meng Luo et al.2024 · 1 citationarXiv
AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement2407.14900v2 · Yunlong Lin, Tian Ye, Sixiang Chen et al.2024 · 26 citationsarXiv
RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark2407.13930v1 · Yuan-Hao Ho, Jen-Hao Cheng, Sheng Yao Kuan et al.2024 · 17 citationsarXiv
Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check2407.13937v1 · Sheng-Yao Kuan, Jen-Hao Cheng, Hsiang-Wei Huang et al.2024 · 7 citationsarXiv
STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft2406.11247v1 · Zhonghan Zhao, Wenhao Chai, Xuan Wang et al.2024 · 0 citationsarXiv
CityCraft: A Real Crafter for 3D City Generation2406.04983v1 · Jie Deng, Wenhao Chai, Junsheng Huang et al.2024 · 2 citationsarXiv
MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection2404.04910v3 · Hou-I Liu, Christine Wu, Jen-Hao Cheng et al.2024 · 11 citationsarXiv
Career total: 86 works. 70 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.