ZK
Zhaolu Kang
cs.CLcs.AIcs.LGcs.CVcs.MMcs.CYcs.CEcs.CRcs.IRcs.MA
On Valency
published · living versionsW_8pxfrc8y·v1 · currentpublished
ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding
with Liang He, SiYuan Ma, Qishi Zhan, Yongqi Fan +3
1 version
W_3s9v4h9m·v1published
Preprints & journals
43 papers in the corpus · 2024–2026DRILL: Training World Models to Improve Policies, Not Predict Pixels2610.30814v1 · Zhaolu Kang, Tailong Luo, Lei Wei et al.2026 · 0 citationsarXiv
RECAP: Looking Once Is Not Enough for Vision-Language Reasoning2610.30834v1 · Zhaolu Kang, Tailong Luo, Chenxin Li et al.2026 · 0 citationsarXiv
TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models2610.30841v1 · Zhaolu Kang, Yidi Wang, Yile Li et al.2026 · 0 citationsarXiv
ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding2610.31338v1 · Liang He, SiYuan Ma, Qishi Zhan et al.2026 · 0 citationsarXivon Valency
EnactOpt: Diagnosis-Guided Harness Evolution for Embodied Agents2610.14977v1 · ZhiYuan Feng, Zhuoshi Pan, Zhaolu Kang et al.2026 · 0 citationsarXiv
Behavior Pack Optimization for Video MLLM Post-Training2610.03141v1 · Zhaolu Kang, Shiyu Liu, Tailong Luo et al.2026 · 0 citationsarXiv
Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning2609.10177v1 · Mingbo Yang, Wenqiang Wang, Zhaolu Kang et al.2026 · 0 citationsarXiv
SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis2609.03338v1 · Leqi Zheng, Jinbo Su, Yuying Li et al.2026 · 0 citationsarXivon Valency
Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards2609.03342v1 · Leqi Zheng, Jinbo Su, Fang Niu et al.2026 · 0 citationsarXiv
JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction2608.29616v3 · Zhaolu Kang, Yantao Liu, Tailong Luo et al.2026 · 0 citationsarXiv
Modality Fault Lines: Structural Corruptions Reveal Fragile Omni-Modal Reasoning2608.29278v2 · Zhaolu Kang, Meixin Wu, Yu Xue et al.2026 · 0 citationsarXiv
Adaptive Hierarchical Representation Alliance for Multimodal Learning2608.22863v3 · Chunlei Meng, Pengbin Feng, Jacqueline J. Pang et al.2026 · 0 citationsarXiv
COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models2608.21030v1 · Chenghua Zhu, Zhaolu Kang, Qifan Shi et al.2026 · 0 citationsarXiv
Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning2608.21501v1 · Qifan Shi, Zhaolu Kang, Chenghua Zhu2026 · 0 citationsarXiv
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations2607.28956v2 · Qiming Shi, Yulong Tao, Linbo Jin et al.2026 · 0 citationsarXiv
SKILL-KD: Contrastive Skill Distillation for LLM Agents2607.28048v4 · Qiming Shi, Yibo Dou, Jiawen Zhu et al.2026 · 0 citationsarXiv
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents2607.13591v3 · Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu et al.2026 · 0 citationsarXiv
When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detection2606.04098v2 · Tao Yu, Yujia Yang, Shenghua Chai et al.2026 · 0 citationsarXiv
SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering2606.00593v3 · Qiming Shi, Zhaolu Kang, Yunfan Zhou et al.2026 · 0 citationsarXiv
Beyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise Workflows2605.08761v1 · Tao Yu, Hao Wang, Changyu Li et al.2026 · 0 citationsarXiv
Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search2605.08762v1 · Tao Yu, yiming ding, Shenghua Chai et al.2026 · 0 citationsarXiv
Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration2605.00370v2 · Chunlei Meng, Pengbin Feng, Rong Fu et al.2026 · 0 citationsarXiv
Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations2604.16515v1 · Jiachen Qian, Zhaolu Kang2026 · 1 citationFindings of the Association for Computational Linguistics: ACL 2026, pages 16059-16073, 2026
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models2604.02967v1 · Kehan Jiang, Haonan Dong, Zhaolu Kang et al.2026 · 0 citationsarXiv
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons2604.02972v1 · Haonan Dong, Kehan Jiang, Haoran Ye et al.2026 · 0 citationsarXiv
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning2604.00344v1 · Eric Hanchen Jiang, Levina Li, Rui Sun et al.2026 · 0 citationsarXiv
ModalImmune: Immunity Driven Unlearning via Self Destructive Training2602.16197v3 · Rong Fu, WeiZhi Tang, Ziming Wang et al.2026 · 1 citationarXiv
Conflict-Aware Client Selection for Multi-Server Federated Learning2602.02458v1 · Mingwei Hong, Zheng Lin, Zehang Lin et al.2026 · 2 citationsarXiv
EDIS: Diagnosing LLM Reasoning via Entropy Dynamics2602.01288v2 · Chenghua Zhu, Siyan Wu, Xiangkang Zeng et al.2026 · 0 citationsarXiv
Multimodal Multi-Agent Empowered Legal Judgment Prediction2601.12815v5 · Zhaolu Kang, Junhao Gong, Qingxi Chen et al.2026 · 7 citationsarXiv
How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction2601.08626v6 · Zhaolu Kang, Yingjie He, Kehan Jiang et al.2026 · 0 citationsarXiv
QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models2601.08689v3 · Zhaolu Kang, Junhao Gong, Wenqing Hu et al.2026 · 0 citationsarXiv
WebCryptoAgent: Agentic Crypto Trading with Web Informatics2601.04687v2 · Ali Kurban, Wei Luo, Liangyu Zuo et al.2026 · 0 citationsarXiv
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning2601.03938v2 · Yujie Feng, Hao Wang, Jian Li et al.2026 · 1 citationarXiv
When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life2601.04043v2 · Xinyue Lou, Jinan Xu, Jingyi Yin et al.2026 · 1 citationarXiv
Beyond N-grams: A Hierarchical Reward Learning Framework for Clinically-Aware Medical Report Generation2512.02710v1 · Yuan Wang, Shujian Gao, Jiaxiang Liu et al.2025 · 1 citationarXiv
LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models2511.11334v3 · Jian Gao, Richeng Xuan, Zhaolu Kang et al.2025 · 0 citationsarXiv
Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes2510.19400v2 · Zhiyuan Feng, Zhaolu Kang, Qijie Wang et al.2025 · 1 citationInternational Conference on Learning Representations (ICLR), 2026
MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents2509.06477v2 · Pengxiang Zhao, Guangyi Liu, YaoZhen Liang et al.2025 · 0 citationsarXiv
ReasonAct: Progressive Training for Fine-Grained Video Reasoning in Small Models2508.01533v2 · Jiaxin Liu, Zhaolu Kang2025 · 3 citationsarXiv
MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models2506.17046v2 · Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai et al.2025 · 1 citationarXiv
JurisCTC: Enhancing Legal Judgment Prediction via Cross-Domain Transfer and Contrastive Learning2504.17264v1 · Zhaolu Kang, Hongtian Cai, Xiangyang Ji et al.2025 · 3 citationsarXiv
CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models2402.13607v3 · Fuwen Luo, Chi Chen, Zihao Wan et al.2024 · 5 citationsarXiv
Career total: 52 works. 43 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.