pith. sign in

Xiaosen Zheng

Identifiers

  • name variant Xiaosen Zheng 0.60 · backfill

Papers (7)

  1. SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning cs.LG · 2025 · author #5
  2. Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates cs.CL · 2024 · author #1
  3. RegMix: Data Mixture as Regression for Language Model Pre-training cs.CL · 2024 · author #2
  4. Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses cs.CL · 2024 · author #1
  5. Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast cs.CL · 2024 · author #2
  6. Intriguing Properties of Data Attribution on Diffusion Models cs.LG · 2023 · author #1
  7. An Empirical Study of Memorization in NLP cs.CL · 2022 · author #1

Mentions

  • 2509.02479 #5 · arxiv_oai · confidence 0.70 Xiaosen Zheng
  • 2410.07137 #1 · arxiv_oai · confidence 0.70 Xiaosen Zheng
  • 2407.01492 #2 · arxiv_oai · confidence 0.70 Xiaosen Zheng
  • 2406.01288 #1 · arxiv_oai · confidence 0.70 Xiaosen Zheng
  • 2402.08567 #2 · arxiv_oai · confidence 0.70 Xiaosen Zheng
  • 2311.00500 #1 · arxiv_oai · confidence 0.70 Xiaosen Zheng
  • 2203.12171 #1 · arxiv_oai · confidence 0.70 Xiaosen Zheng

Frequent Coauthors