IK
Irwin King
cs.CLcs.LGcs.AIcs.CVcs.IRstat.MLcs.SIAlgorithmsArtificial Intelligencecs.SD
On Valency
published · living versionsW_w4wr4u5m·v1 · currentpublished
CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents
with Wenhao Yu, Zhengcheng Wang, Jiahong Liu, Zexuan Qiu +5
1 version
W_mhqps3r7·v1published
Preprints & journals
240 papers in the corpus · 1997–2026CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents2610.29965v1 · Wenhao Yu, Zhengcheng Wang, Jiahong Liu et al.2026 · 0 citationsarXivon Valency
Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT2610.30191v1 · Qingsen Ma, Dianyun Wang, Jiahong Liu et al.2026 · 0 citationsarXiv
: Unifying Scale-Specific Structures and Prototype Decomposition for Spatial-Temporal Forecasting2610.24516v1 · Chengyang Zhou, Zijian Zhang, Hao Miao et al.2026 · 0 citationsarXivon Valency
DecepEval: A Benchmark for Evaluating Deception in LLM Agents2610.07967v1 · Yiming Xu, Hongyue Yu, Beihua Yang et al.2026 · 0 citationsarXiv
Spec2Game: Can LLMs Generate Complete Playable Games from Detailed Specifications?2610.04253v1 · Yixue Cai, Yuzhe Zhao, Hanxiang Chao et al.2026 · 0 citationsarXiv
Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI2609.17969v1 · Jiahong Liu, Wenhao Yu, Zexuan Qiu et al.2026 · 0 citationsarXiv
PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents2609.06702v2 · Kun Li, Zexuan Qiu, Tianhua Zhang et al.2026 · 0 citationsarXiv
Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning2609.00759v1 · Jinhu Qi, Minda Hu, Wentao Zhang et al.2026 · 0 citationsarXiv
Learning Optimal Policies With Local Observations for Cooperative Multiagent Reinforcement Learning.41860915 · Kong, He, Xing, Qianli, Wang, Qi et al.2026 · 1 citationIEEE transactions on neural networks and learning systems. 2026;37(9):4740-4754
Recent Advances of Multimodal Continual Learning: A Comprehensive Survey.41886319 · Yu, Dianzhi, Zhang, Xinni, Chen, Yankai et al.2026 · 9 citationsIEEE transactions on neural networks and learning systems. 2026;37(9):4014-4034
4DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splatting2608.25956v1 · Yueen Ma, Zenglin Xu, Irwin King2026 · 0 citationsarXiv
StepKV: Step-Aware KV Cache Compression for LLM Agents2609.22158v2 · Boyu Feng, Jiahong Liu, Yifan Li et al.2026 · 0 citationsarXiv
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space2608.21096v1 · Jiahong Liu, Ram Samarth B B, Xinyu Fu et al.2026 · 0 citationsarXiv
SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis2608.17931v1 · Shicheng Ma, Wenqian Cui, Irwin King2026 · 0 citationsarXiv
Hyperbolic Multimodal Continual Learning2608.09572v1 · Jiahong Liu, Ming Shen, Xiaohao Liu et al.2026 · 0 citationsarXiv
Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey.41875004 · Li, Jindong, Fu, Yali, Liu, Jiahong et al.2026 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(8):9093-9113
TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning2607.26977v2 · Jinhu Qi, Wentao Zhang, Siu Man Ng et al.2026 · 0 citationsarXiv
Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents2609.17536v1 · Jiyue Jiang, Ziyi Li, He Hu et al.2026 · 0 citationsarXiv
Geometric Collapse: When Vision Models Fail to Verify Physical Causality2607.06871v1 · Wentao Zhang, Jinhu Qi, Weiqiang Jin et al.2026 · 0 citationsarXiv
A Survey on Vision--Language--Action Models for Embodied AI.42048203 · Ma, Yueen, Song, Zixing, Zhuang, Yuzheng et al.2026 · 48 citationsIEEE transactions on neural networks and learning systems. 2026;37(7):3031-3051
Generative Archetype-Grounded Item Representations for Sequential Recommendation2606.11023v1 · Yifan Li, Jiahong Liu, Xinni Zhang et al.2026 · 1 citationarXiv
From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents2606.20661v1 · Yifan Li, Shengbin Yue, Boyu Feng et al.2026 · 0 citationsarXiv
Bilevel Optimization over Saddle Points of Zero-Sum Markov Games2605.26654v1 · Zihao Zheng, Irwin King, Songtao Lu2026 · 0 citationsarXiv
Dynamic Mixture of Latent Memories for Self-Evolving Agents2605.21951v1 · Dianzhi Yu, Vireo Zhang, Hongru Wang et al.2026 · 0 citationsarXiv
A Survey of Audio Reasoning in Multimodal Foundation Models2605.21008v1 · Zhihan Guo, Wenqian Cui, Guan-Ting Lin et al.2026 · 0 citationsarXiv
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition2605.24005v2 · Yanyu Chen, Jiyue Jiang, Dianzhi Yu et al.2026 · 0 citationsarXiv
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security2605.23989v1 · Jinhu Qi, Muzhi Li, Jiahong Liu et al.2026 · 5 citationsAcademia AI and Applications, vol. 2, 2026
Towards Robotic Dexterous Hand Intelligence: A Survey2605.13925v2 · Weiguang Zhao, Tian Liang, Xihao Guo et al.2026 · 0 citationsarXiv
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory2605.10870v1 · Mingxi Zou, Zhihan Guo, Langzhang Liang et al.2026 · 0 citationsarXiv
Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM2605.05927v2 · Wenqian Cui, Xiao-Hui Li, Daxin Tan et al.2026 · 0 citationsarXiv
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey.41525590 · Li, Jindong, Li, Yongguang, Fu, Yali et al.2026 · 14 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(5):5405-5424
HC-GLAD: Dual hyperbolic contrastive learning for unsupervised graph-level anomaly detection.42019218 · Fu, Yali, Li, Jindong, Liu, Jiahong et al.2026 · 3 citationsNeural networks : the official journal of the International Neural Network Society. 2026;202:109009
Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation2604.04976v1 · Junwei Pan, Wei Xue, Chao Zhou et al.2026 · 0 citationsarXiv
Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI2603.14987v2 · Jinhu Qi, Yifan Li, Minghao Zhao et al.2026 · 0 citationsarXiv
X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting2603.09632v5 · Yueen Ma, Zenglin Xu, Irwin King2026 · 0 citationsarXiv
TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents2602.21230v1 · Yanyu Chen, Jiyue Jiang, Jiahong Liu et al.2026 · 1 citationarXiv
Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration2602.03647v1 · Bowei He, Minda Hu, Zenan Xu et al.2026 · 0 citationsarXiv
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning2602.01745v2 · Wenhao Yu, Shaohang Wei, Jiahong Liu et al.2026 · 1 citationarXiv
UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region Profiling2601.22746v1 · Pingping Liu, Jiamiao Liu, Zijian Zhang et al.2026 · 0 citationsarXiv
SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation2604.09551v1 · Chunxu Zhang, Shanqiang Huang, Zijian Zhang et al.2026 · 1 citationarXiv
Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs2601.12807v1 · Zixing Song, Irwin King2026 · 0 citationsarXiv
ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning2601.04973v1 · Minda Hu, Zexuan Qiu, Zenan Xu et al.2026 · 0 citationsarXiv
Towards Practical Automatic Piano Reduction using BERT with Semi-supervised Learning2512.21324v2 · Wan Ki Wong, Ka Ho To, Chuck-jee Chau et al.2025 · 0 citationsarXiv
ADRA-Bank: A Modular Benchmark for Academic Deep Research Agents2512.00986v3 · Zhihan Guo, Feiyang Xu, Yifan Li et al.2025 · 0 citationsarXiv
ConSurv: Multimodal Continual Learning for Survival Analysis2511.09853v2 · Dianzhi Yu, Conghao Xiong, Yankai Chen et al.2025 · 0 citationsarXiv
MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models2511.10262v3 · He Zhang, Wenqian Cui, Haoning Xu et al.2025 · 1 citationarXiv
PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction2510.05613v2 · Ziqiao Meng, Qichao Wang, Zhiyang Dou et al.2025 · 0 citationsarXiv
RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback2510.06186v2 · Chunyu Miao, Henry Peng Zou, Yangning Li et al.2025 · 0 citationsarXiv
Predicting drug responses of unseen cell types through transfer learning with foundation models.41044387 · Wang, Yixuan, Liu, Xinyuan, Fan, Yimin et al.2026 · 12 citationsNature computational science. 2026;6(1):39-52
From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development2509.23071v2 · Muzhi Li, Jinhu Qi, Yihong Wu et al.2025 · 0 citationsarXiv
Career total: 723 works. 240 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.