BC
Boxi Cao
cs.CLcs.AIcs.LGcs.CVcs.SEstat.MLcs.DBcs.IRcs.SD
On Valency
published · living versionsW_z323wazn·v1 · currentpublished
OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling
with Jiawei Chen, Ruoxi Xu, Zhuoqun Li, Ruotong Pan +10
1 version
Preprints & journals
32 papers in the corpus · 2021–2026OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling2610.29472v1 · Jiawei Chen, Ruoxi Xu, Boxi Cao et al.2026 · 0 citationsarXivon Valency
From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents2608.16002v2 · Zhengzhao Ma, Boxi Cao, Yaojie Lu et al.2026 · 0 citationsarXiv
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations2607.19865v1 · Jiazhen Jiang, Boxi Cao, Lingyong Yan et al.2026 · 0 citationsarXiv
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction2607.02881v1 · Zhuoqun Li, Boxi Cao, Jiawei Chen et al.2026 · 0 citationsarXiv
OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models2607.03050v1 · Shijie Cao, Qingyu Zhang, Boxi Yu et al.2026 · 0 citationsarXiv
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models2606.23404v1 · Jun Zhang, Jiasheng Zheng, Boxi Cao et al.2026 · 0 citationsarXiv
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?2606.04455v1 · Xinyu Lu, Tianshu Wang, Pengbo Wang et al.2026 · 0 citationsarXiv
Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination2605.31058v1 · Jiasheng Zheng, Boxi Cao, Boxi Yu et al.2026 · 0 citationsarXiv
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents2605.29559v1 · Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu et al.2026 · 0 citationsarXiv
MetaphorVU: Towards Metaphorical Video Understanding2605.25461v1 · Zhuoqun Li, Boxi Cao, Guiping Jiang et al.2026 · 0 citationsarXiv
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards2605.14539v1 · Mengjie Ren, Jie Lou, Boxi Cao et al.2026 · 0 citationsarXiv
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models2604.16902v3 · Xinru Yan, Boxi Cao, Yaojie Lu et al.2026 · 0 citationsarXiv
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces2604.08362v3 · Jiawei Chen, Ruoxi Xu, Boxi Cao et al.2026 · 0 citationsarXiv
P^2O: Joint Policy and Prompt Optimization2603.21877v4 · Xinyu Lu, Kaiqi Zhang, Jinglin Yang et al.2026 · 0 citationsarXiv
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards2603.09117v3 · Zhengzhao Ma, Xueru Wen, Boxi Cao et al.2026 · 0 citationsarXiv
Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning2504.00472v1 · Ruoxi Xu, Yunjie Ji, Boxi Cao et al.2025 · 0 citationsarXiv
Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering2411.11504v1 · Xinyan Guan, Yanjiang Liu, Xinyu Lu et al.2024 · 1 citationarXiv
Multi-Facet Counterfactual Learning for Content Quality Evaluation2410.07693v1 · Jiasheng Zheng, Hongyu Lin, Boxi Cao et al.2024 · 0 citationsarXiv
StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation2408.03281v2 · Boxi Cao, Mengjie Ren, Hongyu Lin et al.2024 · 0 citationsarXiv
Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models2407.11470v2 · Jiasheng Zheng, Boxi Cao, Zhengzhao Ma et al.2024 · 1 citationarXiv
Towards Scalable Automated Alignment of LLMs: A Survey2406.01252v3 · Boxi Cao, Keming Lu, Xinyu Lu et al.2024 · 0 citationsarXiv
URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression2404.16248v1 · Zhuoqun Li, Hongyu Lin, Tianshu Wang et al.2024 · 0 citationsarXiv
Towards Universal Dense Blocking for Entity Resolution2404.14831v2 · Tianshu Wang, Hongyu Lin, Xianpei Han et al.2024 · 1 citationarXiv
Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation2404.06809v3 · Ruotong Pan, Boxi Cao, Hongyu Lin et al.2024 · 7 citationsarXiv
Learning In-context Learning for Named Entity Recognition2305.11038v3 · Jiawei Chen, Yaojie Lu, Hongyu Lin et al.2023 · 40 citationsarXiv
Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models2305.09144v2 · Boxi Cao, Qiaoyu Tang, Hongyu Lin et al.2023 · 4 citationsarXiv
The Life Cycle of Knowledge in Big Language Models: A Survey2303.07616v1 · Boxi Cao, Hongyu Lin, Xianpei Han et al.2023 · 17 citationsMachine Intelligence Research. vol. 21, no. 2, pp. 217-238, 2024
A Roadmap for Big Model2203.14101v4 · Sha Yuan, Hanyu Zhao, Shuai Zhao et al.2022 · 1 citationarXiv
Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View2203.12258v1 · Boxi Cao, Hongyu Lin, Xianpei Han et al.2022 · 20 citationsarXiv
Pre-training to Match for Unified Low-shot Relation Extraction2203.12274v1 · Fangchao Liu, Hongyu Lin, Xianpei Han et al.2022 · 24 citationsarXiv
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark2112.13610v2 · Yuan Yao, Qingxiu Dong, Jian Guan et al.2021 · 9 citationsarXiv
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases2106.09231v1 · Boxi Cao, Hongyu Lin, Xianpei Han et al.2021 · 77 citationsarXiv
Career total: 43 works. 32 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.