Kaitong Cai

According to our database, Kaitong Cai authored at least 31 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2026

Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE.

Hejin Huang, Jusheng Zhang, Kaitong Cai, Jian Wang, Rong Pan

CoRR, March, 2026

AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents.

Zhixing Zhang, Jesen Zhang, Hao Liu, Qinhan Lv, Jing Yang, Kaitong Cai, Keze Wang

CoRR, February, 2026

Process-of-Thought Reasoning for Videos.

Jusheng Zhang, Kaitong Cai, Jian Wang, Yongsen Zheng, Kwok-Yan Lam, Keze Wang

CoRR, February, 2026

Spectral Gating Networks.

Jusheng Zhang, Yijia Fan, Kaitong Cai, Jing Yang, Yongsen Zheng, Kwok-Yan Lam, Liang Lin, Keze Wang

CoRR, February, 2026

Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems.

Jusheng Zhang, Yijia Fan, Kaitong Cai, Jing Yang, Jiawei Yao, Jian Wang, Guanlong Qu, Ziliang Chen, Keze Wang

CoRR, January, 2026

LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction.

Jusheng Zhang, Ningyuan Liu, Yijia Fan, Zihao Huang, Qinglin Zeng, Kaitong Cai, Jian Wang, Keze Wang

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Top-Down Semantic Refinement for Image Captioning.

Jusheng Zhang, Kaitong Cai, Jing Yang, Jian Wang, Chengpei Tang, Keze Wang

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale.

Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Jian Wang, Keze Wang

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Cost-Effective Communication: An Auction-based Method for Language Agent Interaction.

Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Chengpei Tang, Jian Wang, Keze Wang

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability.

Kaitong Cai, Jusheng Zhang, Yijia Fan, Jing Yang, Keze Wang

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains.

Jesen Zhang, Ningyuan Liu, Kaitong Cai, Sidi Liu, Jing Yang, Ziliang Chen, Xiaofei Sun, Keze Wang

CoRR, December, 2025

CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation.

Qinglin Zeng, Kaitong Cai, Ruiqi Chen, Qinhan Lv, Keze Wang

CoRR, December, 2025

RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks.

Ningyuan Liu, Jing Yang, Kaitong Cai, Keze Wang

CoRR, December, 2025

FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models.

Kaitong Cai, Jusheng Zhang, Jing Yang, Yijia Fan, Pengtao Xie, Jian Wang, Keze Wang

CoRR, December, 2025

SirenPose: Dynamic Scene Reconstruction via Geometric Supervision.

Kaitong Cai, Jensen Zhang, Jing Yang, Keze Wang

CoRR, December, 2025

LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction.

Jensen Zhang, Ningyuan Liu, Yijia Fan, Zihao Huang, Qinglin Zeng, Kaitong Cai, Jian Wang, Keze Wang

CoRR, December, 2025

PTTA: A Pure Text-to-Animation Framework for High-Quality Creation.

Ruiqi Chen, Kaitong Cai, Yijia Fan, Keze Wang

CoRR, December, 2025

STORM: Search-Guided Generative World Models for Robotic Manipulation.

Wenjun Lin, Jensen Zhang, Kaitong Cai, Keze Wang

CoRR, December, 2025

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models.

Jusheng Zhang, Xiaoyang Guo, Kaitong Cai, Qinhan Lv, Yijia Fan, Wenhao Chai, Jian Wang, Keze Wang

CoRR, December, 2025

MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models.

Jusheng Zhang, Kaitong Cai, Xiaoyang Guo, Sidi Liu, Qinhan Lv, Ruiqi Chen, Jing Yang, Yijia Fan, Xiaofei Sun, Jian Wang, Ziliang Chen, Liang Lin, Keze Wang

CoRR, December, 2025

Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification.

Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang

CoRR, December, 2025

Guardian: Decoupling Exploration from Safety in Reinforcement Learning.

Kaitong Cai, Jusheng Zhang, Jing Yang, Keze Wang

CoRR, October, 2025

Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints.

Jing Yang, Kaitong Cai, Yijia Fan, Yufeng Yang, Keze Wang

CoRR, October, 2025

Learning Dynamics of VLM Finetuning.

Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang

CoRR, October, 2025

Failure-Driven Workflow Refinement.

Jusheng Zhang, Kaitong Cai, Qinglin Zeng, Ningyuan Liu, Stephen Fan, Ziliang Chen, Keze Wang

CoRR, October, 2025

CF-VLM:CounterFactual Vision-Language Fine-tuning.

Jusheng Zhang, Kaitong Cai, Yijia Fan, Jian Wang, Keze Wang

CoRR, June, 2025

Kolmogorov-Arnold Fourier Networks.

Jusheng Zhang, Yijia Fan, Kaitong Cai, Keze Wang

CoRR, February, 2025

MAT-Agent: Adaptive Multi-Agent Training Optimization.

Jusheng Zhang, Kaitong Cai, Yijia Fan, Ningyuan Liu, Keze Wang

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration.

Jusheng Zhang, Yijia Fan, Kaitong Cai, Xiaofei Sun, Keze Wang

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off.

Jusheng Zhang, Yijia Fan, Kaitong Cai, Zimeng Huang, Xiaofei Sun, Jian Wang, Chengpei Tang, Keze Wang

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

CCG: Rare-Label Prediction via Neural SEM-Driven Causal Game.

Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025