pith. sign in

Xiangyu Peng

Identifiers

  • name variant Xiangyu Peng 0.60 · backfill

Papers (25)

  1. Don\'t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination cs.CL · 2026 · author #7
  2. The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation cs.LG · 2026 · author #2
  3. MTA-Agent: An Open Recipe for Multimodal Deep Search Agents cs.CV · 2026 · author #1
  4. Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k cs.GR · 2025 · author #2
  5. Open-Sora: Democratizing Efficient Video Production for All cs.CV · 2024 · author #2
  6. Dataset Quantization cs.CV · 2023 · author #4
  7. Thespian: Multi-Character Text Role-Playing Game Agents cs.AI · 2023 · author #2
  8. Ambient Adventures: Teaching ChatGPT on Developing Complex Stories cs.CL · 2023 · author #4
  9. Dialogue Shaping: Empowering Agents through NPC Interaction cs.CL · 2023 · author #2
  10. InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning cs.CV · 2023 · author #5
  11. Story Shaping: Teaching Agents Human-like Behavior with Stories cs.AI · 2023 · author #1
  12. Neuro-Symbolic World Models for Adapting to Open World Novelty cs.AI · 2023 · author #4
  13. Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning cs.CL · 2022 · author #1
  14. Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors cs.LG · 2022 · author #2
  15. FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders cs.CV · 2022 · author #3
  16. Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels cs.CV · 2022 · author #2
  17. NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty cs.AI · 2022 · author #6
  18. CAFE: Learning to Condense Dataset by Aligning Features cs.CV · 2022 · author #3
  19. XFBoost: Improving Text Generation with Controllable Decoders cs.CL · 2022 · author #1
  20. Crafting Better Contrastive Views for Siamese Representation Learning cs.CV · 2022 · author #1
  21. Inherently Explainable Reinforcement Learning in Natural Language cs.HC · 2021 · author #1
  22. Guiding Neural Story Generation with Reader Models cs.CL · 2021 · author #1
  23. Detecting and Adapting to Novelty in Games cs.AI · 2021 · author #1
  24. Automatic Story Generation: Challenges and Attempts cs.CL · 2021 · author #3
  25. Reducing Non-Normative Text Generation from Language Models cs.CL · 2020 · author #1

Mentions

  • 2303.04947 #5 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2308.10524 #4 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2308.01872 #2 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2308.01734 #4 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2307.15833 #2 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2210.12587 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2301.10107 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2301.06294 #4 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2112.08907 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2205.00186 #2 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2205.14467 #2 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2205.11090 #3 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2112.08596 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2202.03278 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2203.01531 #3 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2203.12117 #6 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2202.08124 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2106.02204 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2102.12634 #3 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2001.08764 #1 · arxiv_oai · confidence 0.70 Xiangyu Peng
  • 2503.09642 #2 · arxiv_oai · confidence 0.70 Xiangyu Peng

Frequent Coauthors