HL
Hongyin Luo
cs.CLcs.AIcs.LGcs.CVcs.NEcs.SDeess.AScs.CYcs.RO
On Valency
published · living versionsW_hwbwe4b8·v1 · currentpublished
Adversarial Speculative Reasoning Improves Long Horizon Agents
with Wei Fang, Lijie Yang, Owen Stepan, Daniel Suit +3
1 version
Preprints & journals
35 papers in the corpus · 2016–2026Thought-Level Beam Search for Reasoning2608.08020v2 · Lijie Yang, Hongyin Luo, Jiawei Zhao et al.2026 · 0 citationsarXiv
TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG2601.06922v1 · Tianhua Zhang, Kun Li, Junan Li et al.2026 · 0 citationsarXiv
ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks2508.01943v2 · Philip Schroeder, Ondrej Biza, Thomas Weng et al.2025 · 0 citationsarXiv
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning2507.16784v1 · Hongyin Luo, Nathaniel Morgan, Tina Li et al.2025 · 0 citationsarXiv
RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning2505.22430v1 · Kun Li, Yunxiang Li, Tianhua Zhang et al.2025 · 0 citationsarXiv
Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion2505.18115v1 · Jacob Hansen, Wei Lin, Junmo Kang et al.2025 · 0 citationsarXiv
Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution2503.01695v1 · Kun Li, Tianhua Zhang, Yunxiang Li et al.2025 · 0 citationsarXiv
Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains2410.18415v1 · Kun Li, Tianhua Zhang, Xixin Wu et al.2024 · 9 citationsarXiv
Quantifying Generalization Complexity for Large Language Models2410.01769v2 · Zhenting Qi, Hongyin Luo, Xuliang Huang et al.2024 · 0 citationsarXiv
Addition is All You Need for Energy-efficient Language Models2410.00907v2 · Hongyin Luo, Wei Sun2024 · 3 citationsarXiv
Training Task Experts through Retrieval Based Distillation2407.05463v1 · Jiaxin Ge, Xueying Jia, Vijay Viswanathan et al.2024 · 0 citationsarXiv
Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts2406.12034v2 · Junmo Kang, Leonid Karlinsky, Hongyin Luo et al.2024 · 3 citationsarXiv
Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers2406.10991v1 · Tianhua Zhang, Kun Li, Hongyin Luo et al.2024 · 9 citationsarXiv
THREAD: Thinking Deeper with Recursive Spawning2405.17402v2 · Philip Schroeder, Nathaniel Morgan, Hongyin Luo et al.2024 · 0 citationsarXiv
RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation2404.00610v1 · Chi-Min Chan, Chunpu Xu, Ruibin Yuan et al.2024 · 22 citationsarXiv
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding2403.00425v2 · Zhaorun Chen, Zhuokai Zhao, Hongyin Luo et al.2024 · 4 citationsarXiv
Self-Specialization: Uncovering Latent Expertise within Large Language Models2310.00160v2 · Junmo Kang, Hongyin Luo, Yada Zhu et al.2023 · 2 citationsarXiv
Joint Audio and Speech Understanding2309.14405v3 · Yuan Gong, Alexander H. Liu, Hongyin Luo et al.2023 · 48 citationsarXiv
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning2309.10814v2 · Tianhua Zhang, Jiaxin Ge, Hongyin Luo et al.2023 · 4 citationsarXiv
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models2309.03883v2 · Yung-Sung Chuang, Yujia Xie, Hongyin Luo et al.2023 · 29 citationsarXiv
Entailment as Robust Self-Learner2305.17197v1 · Jiaxin Ge, Hongyin Luo, Yoon Kim et al.2023 · 2 citationsarXiv
SAIL: Search-Augmented Instruction Learning2305.15225v2 · Hongyin Luo, Yung-Sung Chuang, Yuan Gong et al.2023 · 9 citationsarXiv
Listen, Think, and Understand2305.10790v3 · Yuan Gong, Hongyin Luo, Alexander H. Liu et al.2023 · 43 citationsarXiv
Chain of Thought Prompt Tuning in Vision Language Models2304.07919v2 · Jiaxin Ge, Hongyin Luo, Siyuan Qian et al.2023 · 12 citationsarXiv
Interpretable Unified Language Checking2304.03728v1 · Tianhua Zhang, Hongyin Luo, Yung-Sung Chuang et al.2023 · 9 citationsarXiv
Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning2303.05670v1 · Hongyin Luo, James Glass2023 · 12 citationsarXiv
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings2204.10298v1 · Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo et al.2022 · 178 citationsarXiv
Mitigating Biases in Toxic Language Detection through Invariant Rationalization2106.07240v1 · Yung-Sung Chuang, Mingye Gao, Hongyin Luo et al.2021 · 19 citationsarXiv
Meta-learning for downstream aware and agnostic pretraining2106.03270v1 · Hongyin Luo, Shuyan Dong, Yung-Sung Chuang et al.2021 · 0 citationsMeta Learning and Its Applications to Natural Language Processing workshop at ACL 2021
Cooperative Self-training of Machine Reading Comprehension2103.07449v3 · Hongyin Luo, Shang-Wen Li, Mingye Gao et al.2021 · 6 citationsarXiv
Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks2101.09773v1 · Hongyin Luo, Shang-Wen Li, James Glass2021 · 5 citationsarXiv
Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption2005.11153v1 · Hongyin Luo, Shang-Wen Li, James Glass2020 · 9 citationsarXiv
Improving Neural Language Models by Segmenting, Attending, and Predicting the Future1906.01702v1 · Hongyin Luo, Lan Jiang, Yonatan Belinkov et al.2019 · 9 citationsarXiv
Adaptive Bidirectional Backpropagation: Towards Biologically Plausible Error Signal Transmission in Neural Networks1702.07097v4 · Hongyin Luo, Jie Fu, James Glass2017 · 6 citationsarXiv
DrMAD: Distilling Reverse-Mode Automatic Differentiation for Optimizing Hyperparameters of Deep Neural Networks1601.00917v5 · Jie Fu, Hongyin Luo, Jiashi Feng et al.2016 · 18 citationsarXiv
Career total: 61 works. 35 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.