CK
Caixin Kang
cs.CVcs.AIcs.CLcs.CRcs.LGcs.SIArtificial IntelligenceBraincs.CYcs.GR
On Valency
published · living versionsW_m38fq7va·v1 · currentpublished
HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL
with Xiaoqiang Wang, Ting-En Lin, Yuchuan Wu, Pinyi Zhang +5
1 version
W_z5z9e3k5·v1published
Preprints & journals
21 papers in the corpus · 2022–2026Honeyed Words, Hidden Daggers: Benchmarking and Training LLMs to See Through Mock Politeness2610.26059v1 · Caixin Kang, Sitong Gong, Tianyu Yan et al.2026 · 0 citationsarXivon Valency
HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL2610.26426v1 · Xiaoqiang Wang, Ting-En Lin, Yuchuan Wu et al.2026 · 0 citationsarXivon Valency
What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds2610.20195v1 · Caixin Kang, Ke Wang, Yuchuan Wu et al.2026 · 0 citationsarXiv
GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience2608.02392v2 · Sitong Gong, Caixin Kang, Tianyu Yan et al.2026 · 0 citationsarXiv
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos2607.11523v1 · Gong Sitong, Tianyu Yan, Caixin Kang et al.2026 · 0 citationsarXiv
Brain-inspired spatial intelligence for embodied agents.42364983 · Ruan, Shouwei, Wang, Liyuan, Kang, Caixin et al.2026 · 1 citationNature communications. 2026;17(1)
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering2605.23216v2 · Mingfang Zhang, Jingjing Pan, Ashutosh Kumar et al.2026 · 0 citationsarXiv
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?2605.22109v1 · Caixin Kang, Tianyu Yan, Sitong Gong et al.2026 · 0 citationsarXiv
SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation2605.10079v1 · Liangyang Ouyang, Ruicong Liu, Caixin Kang et al.2026 · 0 citationsarXiv
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise2602.12783v3 · Yuejie Li, Ke Yang, Yueying Hua et al.2026 · 0 citationsProceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '26), July 20--24, 2026, Melbourne, VIC, Australia
Towards Interactive Intelligence for Digital Humans2512.13674v2 · Yiyi Cai, Xuangeng Chu, Xiwei Gao et al.2025 · 0 citationsarXiv
Real-World Adversarial Defense Against Patch Attacks Based on Diffusion Model.40768456 · Wei, Xingxing, Kang, Caixin, Dong, Yinpeng et al.2025 · 8 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(12):11124-11140
Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions2511.16221v2 · Caixin Kang, Yifei Huang, Liangyang Ouyang et al.2025 · 0 citationsarXiv
Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions2510.27195v2 · Caixin Kang, Yifei Huang, Liangyang Ouyang et al.2025 · 0 citationsarXiv
From reactive to cognitive: brain-inspired spatial intelligence for embodied agents2508.17198v1 · Shouwei Ruan, Liyuan Wang, Caixin Kang et al.2025 · 0 citationsarXiv
The Path to Reconciling Quality and Safety in Text-to-Image Generation: Dataset, Method, and Evaluation2504.14290v2 · Shouwei Ruan, Zhenyu Wu, Yao Huang et al.2025 · 0 citationsarXiv
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency2501.04931v2 · Shiji Zhao, Ranjie Duan, Fengxiang Wang et al.2025 · 10 citationsarXiv
OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations2412.02479v2 · Caixin Kang, Yubo Chen, Shouwei Ruan et al.2024 · 1 citationarXiv
DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks2306.09124v4 · Caixin Kang, Yinpeng Dong, Zhengyi Wang et al.2023 · 18 citationsarXiv
Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving2303.11040v1 · Yinpeng Dong, Caixin Kang, Jinlai Zhang et al.2023 · 144 citationsarXiv
ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints2210.03895v1 · Yinpeng Dong, Shouwei Ruan, Hang Su et al.2022 · 30 citationsarXiv
Career total: 26 works. 21 are in this corpus.
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.