pith. sign in

Dayiheng Liu

Identifiers

  • name variant Dayiheng Liu 0.60 · backfill

Papers (34)

  1. The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates cs.CL · 2026 · author #7
  2. CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents cs.AI · 2026 · author #11
  3. ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning cs.CL · 2026 · author #8
  4. Unified Data Selection for LLM Reasoning cs.CL · 2026 · author #9
  5. DISA: Offline Importance Sampling for Distribution-Matching LLM-RL cs.LG · 2026 · author #11
  6. Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows cs.AI · 2026 · author #8
  7. SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs cs.CL · 2026 · author #6
  8. SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation cs.CL · 2026 · author #7
  9. On Predicting the Post-training Potential of Pre-trained LLMs cs.CL · 2026 · author #8
  10. Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models cs.CL · 2026 · author #17
  11. Qwen-Image-2.0 Technical Report cs.CV · 2026 · author #37
  12. SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training cs.LG · 2026 · author #10
  13. CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing cs.CL · 2026 · author #13
  14. JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR cs.AI · 2026 · author #6
  15. OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation cs.CL · 2026 · author #9
  16. ClinConsensus: A Physician-Calibrated Benchmark for Evaluating Clinical Rubric Coverage in Chinese Medical LLMs cs.CL · 2026 · author #14
  17. Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking cs.CL · 2026 · author #10
  18. Qwen3-VL Technical Report cs.CV · 2025 · author #28
  19. Qwen3Guard Technical Report cs.CL · 2025 · author #8
  20. Qwen3-Omni Technical Report cs.CL · 2025 · author #29
  21. Qwen-Image Technical Report cs.CV · 2025 · author #18
  22. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models cs.CL · 2025 · author #9
  23. MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation cs.CL · 2025 · author #9
  24. Qwen3 Technical Report cs.CL · 2025 · author #12
  25. Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free cs.CL · 2025 · author #11
  26. SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines cs.CL · 2025 · author #79
  27. Qwen2.5-1M Technical Report cs.CL · 2025 · author #4
  28. The Lessons of Developing Process Reward Models in Mathematical Reasoning cs.CL · 2025 · author #7
  29. Qwen2.5 Technical Report cs.CL · 2024 · author #8
  30. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution cs.CV · 2024 · author #16
  31. Qwen2.5-Coder Technical Report cs.CL · 2024 · author #5
  32. Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement cs.CL · 2024 · author #7
  33. Qwen2 Technical Report cs.CL · 2024 · author #9
  34. Qwen Technical Report cs.CL · 2023 · author #16

Mentions

  • 2605.28020 #7 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2603.02097 #14 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2605.25624 #11 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2605.23454 #8 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2605.22389 #9 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2505.17123 #9 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2605.14322 #8 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2605.08738 #10 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2605.17295 #11 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2501.07301 #7 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2502.14739 #79 · arxiv_oai · confidence 0.70 Dayiheng Liu
  • 2505.09388 #12 · backfill · confidence 0.70 Dayiheng Liu
  • 2412.15115 #8 · backfill · confidence 0.70 Dayiheng Liu
  • 2605.11887 #17 · backfill · confidence 0.70 Dayiheng Liu
  • 2407.10671 #9 · backfill · confidence 0.70 Dayiheng Liu
  • 2604.10866 #9 · backfill · confidence 0.70 Dayiheng Liu
  • 2511.21631 #28 · backfill · confidence 0.70 Dayiheng Liu

Frequent Coauthors