Hao Peng

Identifiers

• name variant Hao Peng 0.60 · backfill

Papers (64)

1. Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning cs.LG · 2026 · author #4
2. FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents cs.CL · 2026 · author #12
3. ExTax: Explainable Disinformation Detection via Persuasion, Emotion, and Narrative Role Taxonomies cs.CL · 2026 · author #10
4. MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning cs.AI · 2026 · author #6
5. CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists cs.AI · 2026 · author #10
6. Towards a Universal Causal Reasoner cs.CL · 2026 · author #5
7. RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably cs.CL · 2026 · author #8
8. Useful Memories Become Faulty When Continuously Updated by LLMs cs.AI · 2026 · author #7
9. SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety cs.CR · 2026 · author #8
10. Unintended Negative Impacts of Promotional Language in Patent Evaluation cs.CL · 2026 · author #3
11. StoryAlign: Evaluating and Training Reward Models for Story Generation cs.CL · 2026 · author #2
12. TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation cs.IR · 2026 · author #2
13. Kwai Summary Attention Technical Report cs.CL · 2026 · author #5
14. FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation cs.AI · 2026 · author #7
15. Structural Diversity Drives Disruptive Scientific Innovation cs.SI · 2026 · author #9
16. Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning cs.CL · 2026 · author #7
17. Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR cs.LG · 2026 · author #4
18. GLM-5: from Vibe Coding to Agentic Engineering cs.LG · 2026 · author #79
19. Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning cs.LG · 2026 · author #5
20. Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning cs.CV · 2026 · author #15
21. WisPaper: Your AI Scholar Search Engine cs.IR · 2025 · author #8
22. SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory cs.CL · 2025 · author #2
23. Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark cs.AI · 2025 · author #65
24. GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models cs.CL · 2025 · author #56
25. Activation-Guided Local Editing for Jailbreaking Attacks cs.CR · 2025 · author #3
26. The endoscopic character identity for even special orthogonal groups math.RT · 2025 · author #1
27. The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models cs.LG · 2025 · author #12
28. The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning cs.LG · 2025 · author #5
29. RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning cs.CL · 2025 · author #5
30. Process Reinforcement through Implicit Rewards cs.LG · 2025 · author #20
31. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks cs.CL · 2024 · author #4
32. Scaling Diffusion Language Models via Adaptation from Autoregressive Models cs.CL · 2024 · author #11
33. CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment cs.CR · 2024 · author #8
34. OpenHands: An Open Platform for AI Software Developers as Generalist Agents cs.SE · 2024 · author #22
35. Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling cs.LG · 2019 · author #1
36. Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification cs.IR · 2019 · author #1
37. Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks cs.SI · 2019 · author #1
38. Social Influence and Unfollowing Accelerate the Emergence of Echo Chambers cs.CY · 2019 · author #3
39. Text Generation with Exemplar-based Adaptive Decoding cs.CL · 2019 · author #1
40. Understanding Beauty via Deep Facial Features cs.CV · 2019 · author #3
41. Multi-materials beam hardening artifacts correction for computed tomography (CT) based on X-ray spectrum estimation physics.med-ph · 2018 · author #5
42. Graph Convolutional Neural Networks via Motif-based Attention cs.LG · 2018 · author #1
43. Rational Recurrences cs.CL · 2018 · author #1
44. Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention cs.CV · 2018 · author #4
45. Backpropagating through Structured Argmax using a SPIGOT cs.CL · 2018 · author #1
46. Joint Analysis of Individual-level and Summary-level GWAS Data by Leveraging Pleiotropy q-bio.GN · 2018 · author #3
47. Learning Joint Semantic Parsers from Disjoint Data cs.CL · 2018 · author #1
48. A unified image reconstruction framework for quantitative dual- and triple-energy CT imaging of material compositions physics.med-ph · 2018 · author #5
49. "You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates cs.SI · 2018 · author #2
50. Performance Dynamics and Success in Online Games cs.SI · 2018 · author #2
51. Improving Orbit Prediction Accuracy through Supervised Machine Learning astro-ph.EP · 2018 · author #1
52. Deep Multitask Learning for Semantic Dependency Parsing cs.CL · 2017 · author #1
53. Asynchronous Distributed Variational Gaussian Processes for Regression stat.ML · 2017 · author #1
54. A Gb/s Parallel Block-based Viterbi Decoder for Convolutional Codes on GPU cs.DC · 2016 · author #1
55. A Convolutional Attention Network for Extreme Summarization of Source Code cs.LG · 2016 · author #2
56. A Comparative Study on Regularization Strategies for Embedding-based Neural Networks cs.CL · 2015 · author #1
57. Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path cs.CL · 2015 · author #5
58. Discriminative Neural Sentence Modeling by Tree-Based Convolution cs.CL · 2015 · author #2
59. Building Program Vector Representations for Deep Learning cs.SE · 2014 · author #4
60. EigenGP: Gaussian Process Models with Adaptive Eigenfunctions cs.LG · 2014 · author #1
61. An extension of Motzkin-Straus Theorem to non-uniform hypergraphs and its applications math.CO · 2013 · author #2
62. On Frankl and Furedi's conjecture for 3-uniform hypergraphs math.CO · 2012 · author #2
63. Nonperturbative tuning of an improved relativistic heavy-quark action with application to bottom spectroscopy hep-lat · 2012 · author #7
64. An Anti-attack Model Based on Complex Network Theory in P2P networks cs.NI · 2011 · author #1

Mentions

• 2606.04923 #4 · arxiv_oai · confidence 0.70 Hao Peng
• 1504.01106 #2 · backfill · confidence 0.70 Hao Peng
• 2511.16275 #2 · arxiv_oai · confidence 0.70 Hao Peng
• 1409.3358 #4 · backfill · confidence 0.70 Hao Peng
• 1401.0362 #1 · backfill · confidence 0.70 Hao Peng
• 1312.4135 #2 · backfill · confidence 0.70 Hao Peng
• 2602.01058 #5 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.27333 #12 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.27045 #10 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.26567 #6 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.26029 #10 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.24873 #5 · arxiv_oai · confidence 0.70 Hao Peng
• 1211.7056 #2 · backfill · confidence 0.70 Hao Peng
• 2605.05704 #8 · arxiv_oai · confidence 0.70 Hao Peng
• 1206.2554 #7 · backfill · confidence 0.70 Hao Peng
• 1108.5530 #1 · backfill · confidence 0.70 Hao Peng
• 2410.17891 #11 · arxiv_oai · confidence 0.70 Hao Peng
• 2601.06943 #15 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.05249 #2 · arxiv_oai · confidence 0.70 Hao Peng
• 1905.03919 #3 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.15514 #8 · arxiv_oai · confidence 0.70 Hao Peng
• 2505.15134 #5 · arxiv_oai · confidence 0.70 Hao Peng
• 2412.15204 #4 · arxiv_oai · confidence 0.70 Hao Peng
• 2605.04831 #2 · backfill · confidence 0.70 Hao Peng
• 2604.10678 #7 · backfill · confidence 0.70 Hao Peng
• 1602.03001 #2 · backfill · confidence 0.70 Hao Peng

Frequent Coauthors

• Philip S. Yu 7 shared papers
• Juanzi Li 5 shared papers
• Noah A. Smith 5 shared papers
• Dylan Zhang 4 shared papers
• Ge Li 4 shared papers
• Jianxin Li 4 shared papers
• Lifan Yuan 4 shared papers
• Lili Mou 4 shared papers
• Qiran Gong 4 shared papers
• Sam Thomson 4 shared papers
• Zhi Jin 4 shared papers
• Bin Chong 3 shared papers
• Bin Xu 3 shared papers
• Chenhao Tan 3 shared papers
• Jiajie Zhang 3 shared papers
• Jie Tang 3 shared papers
• Senzhang Wang 3 shared papers
• Shangqing Tu 3 shared papers
• Shulin Cao 3 shared papers
• Xiaozhi Wang 3 shared papers