Get started
Author

Guanjun Jiang

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
2026 · Jingwei Ni, Yihao Liu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2
PDF
Live-OPSD: On-Policy Self-Distillation for Proactive Streaming Large Video Models
2026 · Du, Kaixuan, Wan, Xin, et al. · arXiv (Cornell University)
PDF
ImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image Generation
2026 · Han, Shuo, Wang, Zhilin, et al. · arXiv (Cornell University)
PDF
A Lightweight Velocity Correction Framework for Improving Instruction Following in Few-Step Text-to-Image Generation
2026 · Gao, Yating, Zhu, Zhenlong, et al. · arXiv (Cornell University)
PDF
Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents
2026 · Zhang, Tong, Liu, Zhou, et al. · arXiv (Cornell University)
PDF
RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
2026 · Zhao, Fanyu, Cao, Ruike, et al. · arXiv (Cornell University)
PDF
Iapetus: Content-Aware Hierarchical Scheduling for Collaborative ViT Inference in LEO Satellite Networks
2026 · Chen, Yan, Zhang, Yunxiang, et al. · arXiv (Cornell University)
PDF
SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation
2026 · Wang, Wen, Bao, Jiahua, et al. · arXiv (Cornell University)
PDF
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
2026 · Chen, Jiangwang, Song, Zixin, et al. · arXiv (Cornell University)
PDF
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
2026 · Huang, Siyuan, Cheng, Pengyu, et al. · arXiv (Cornell University)
PDF
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
2026 · Wu, Chang, Fang, Junfeng, et al. · arXiv (Cornell University)
PDF
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
2026 · Huang, Zhilin, Gao, Hang, et al. · arXiv (Cornell University)
PDF
A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine
2026 · Lu, Jingyu, Wang, Yuhan, et al. · arXiv (Cornell University)
PDF
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
2026 · Chen, Tao, Jiang, Gangwei, et al. · arXiv (Cornell University)
PDF
From Item-Only to Query-Item: Query-Conditioned Generative Search with QGS in Quark
2026 · Song, Yanglong, Yang, Zihao, et al. · arXiv (Cornell University)
PDF
RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance
2026 · Jiang, Hengjun, Sun, Liansheng, et al. · arXiv (Cornell University)
PDF
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
2026 · Chen, Jiangwang, Zhang, Bowen, et al. · arXiv (Cornell University)
PDF
Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
2026 · Miao, Yanting, Sun, Yutao, et al. · arXiv (Cornell University)
PDF
ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression
2026 · Ke, Xiaojie, Zhang, Shuai, et al. · arXiv (Cornell University)
PDF
QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence
2026 · Lin, Zhichao, Liang, Zhichao, et al. · arXiv (Cornell University)
PDF
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
2026 · Li, Zhuo, Zhang, Yupeng, et al. · arXiv (Cornell University)
PDF
Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models
2026 · Qiu, Weijie, Guan, Dai, et al. · arXiv (Cornell University)
PDF
Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models
2026 · Wang, Junxin, Guan, Dai, et al. · arXiv (Cornell University)
PDF
QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models
2026 · Wu, Yao, Yin, Kangping, et al. · arXiv (Cornell University)
PDF
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
2026 · Cui, Sijia, Cheng, Pengyu, et al. · arXiv (Cornell University)
PDF
Works count: 41
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type