pith. sign in

Xiangliang Zhang

Identifiers

  • name variant Xiangliang Zhang 0.60 · backfill

Papers (39)

  1. One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems cs.CL · 2026 · author #7
  2. DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment cs.LG · 2026 · author #9
  3. AIRGuard: Guarding Agent Actions with Runtime Authority Control cs.CR · 2026 · author #5
  4. JobBench: Aligning Agent Work With Human Will cs.AI · 2026 · author #16
  5. AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills cs.CR · 2026 · author #8
  6. Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty? cs.CV · 2026 · author #13
  7. AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive cs.AI · 2026 · author #4
  8. SkillGen: Verified Inference-Time Agent Skill Synthesis cs.LG · 2026 · author #7
  9. NARRA-Gym for Evaluating Interactive Narrative Agents cs.CL · 2026 · author #17
  10. Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning cs.AI · 2026 · author #10
  11. Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors cs.LG · 2026 · author #7
  12. Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data cs.LG · 2026 · author #4
  13. AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents cs.HC · 2026 · author #3
  14. PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models cs.CL · 2026 · author #12
  15. Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs cs.LG · 2026 · author #9
  16. Emergent Social Intelligence Risks in Generative Multi-Agent Systems cs.MA · 2026 · author #15
  17. A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning cs.AI · 2026 · author #9
  18. AI Alignment Breaks at the Edge cs.CL · 2026 · author #7
  19. ProbeLLM: Automating Principled Diagnosis of LLM Failures cs.CL · 2026 · author #11
  20. RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty cs.CL · 2026 · author #9
  21. Alignment Risks from Capability-Seeking RL Training cs.LG · 2026 · author #11
  22. Evaluating Large Language Models in Scientific Discovery cs.AI · 2025 · author #41
  23. MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training cs.CL · 2025 · author #6
  24. On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective cs.CY · 2025 · author #66
  25. Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge cs.CL · 2024 · author #12
  26. Large Language Model based Multi-Agents: A Survey of Progress and Challenges cs.CL · 2024 · author #8
  27. TrustLLM: Trustworthiness in Large Language Models cs.CL · 2024 · author #61
  28. Weakly-paired Cross-Modal Hashing cs.LG · 2019 · author #5
  29. ActiveHNE: Active Heterogeneous Network Embedding cs.LG · 2019 · author #6
  30. Multi-View Multiple Clustering cs.LG · 2019 · author #5
  31. Robust Federated Training via Collaborative Machine Teaching using Trusted Instances cs.LG · 2019 · author #2
  32. Utilizing Dynamic Properties of Sharing Bits and Registers to Estimate User Cardinalities over Time cs.DS · 2018 · author #3
  33. Submodular Optimization Over Streams with Inhomogeneous Decays cs.DS · 2018 · author #5
  34. Tracking Influential Nodes in Time-Decaying Dynamic Interaction Networks cs.SI · 2018 · author #5
  35. Graph Embedding with Rich Information through Heterogeneous Network cs.AI · 2017 · author #2
  36. Coarse Grained Exponential Variational Autoencoders cs.LG · 2017 · author #2
  37. Analysis and Modeling of Social Influence in High Performance Computing Workloads cs.DC · 2016 · author #3
  38. A Fast Sampling Method of Exploring Graphlet Degrees of Large Directed and Undirected Graphs cs.SI · 2016 · author #2
  39. Scaling Analysis of Affinity Propagation cs.AI · 2009 · author #3

Mentions

  • 2602.12966 #11 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2602.12424 #9 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2606.09293 #7 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2606.07678 #9 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2602.12124 #11 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2605.28914 #5 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2605.26329 #16 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2602.20042 #7 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2605.11518 #4 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2502.14296 #66 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 2401.05561 #61 · arxiv_oai · confidence 0.70 Xiangliang Zhang
  • 0910.1800 #3 · backfill · confidence 0.70 Xiangliang Zhang
  • 2410.02736 #12 · arxiv_oai · confidence 0.70 Xiangliang Zhang

Frequent Coauthors