Pith. sign in

Researcher Evidence Record

Haitao Mi

This bounded record lists 74 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.CL, cs.LG, cs.AI work dated 2016 to 2026. The record describes sources and coverage; it makes no judgment about the person.

Compiled coverage vector

Measured lane counts only. Not a trust score or person verdict.

Identity 2 canonical identity row plus typed public identifiers Pith papers 74 attributed paper rows in the Pith corpus, itemized below Imported works 0 imported works beyond the paper ledger Current reviews 21 of 74 papers carrying a current Pith review; presence, not outcome Sourced citations 40 of 74 works with a source-named citation count Coauthors 50 distinct coauthors across shared paper rows
Enumerated paper scope: 5 fields (cs.CL, cs.LG, cs.AI, +2 more) · 2016-2026 sources: authors, author_identifiers · paper_authors · author_works · current_verdicts · cited_works

A sourced case file for attributed work. It is neither a profile score nor a verdict about this researcher.

Attributed works

A bounded ledger from the Pith paper and imported-work queries. Counts and source confidence stay with each work.

  1. 2026 Pith paper

    Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

    cs.LG provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  2. 2026 Pith paper

    Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

    cs.AI provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  3. 2026 Pith paper

    DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

    cs.CL provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  4. 2026 Pith paper

    Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

    cs.CL provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    12
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  5. 2026 Pith paper

    FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

    cs.LG provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    14
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  6. 2026 Pith paper

    Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis

    cs.AI provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  7. 2026 Pith paper

    DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

    cs.CL provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  8. 2026 Pith paper

    Reinforcing Multimodal Reasoning Against Visual Degradation

    cs.CV provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  9. 2026 Pith paper

    Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  10. 2026 Pith paper

    Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  11. 2026 Pith paper

    Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration

    cs.AI provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  12. 2026 Pith paper

    Verified Critical Step Optimization for LLM Agents

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  13. 2026 Pith paper

    Exploring Information Seeking Agent Consolidation

    cs.AI provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  14. 2026 Pith paper

    Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification

    cs.AI provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 3 pith inbound references from cited_work_pith_inbound_counts
  15. 2025 Pith paper

    WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    11
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 4 pith inbound references from cited_work_pith_inbound_counts
  16. 2025 Pith paper

    CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 9 pith inbound references from cited_work_pith_inbound_counts
  17. 2025 Pith paper

    Self-Rewarding Vision-Language Model via Reasoning Decomposition

    cs.CV provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    10
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 29 pith inbound references from cited_work_pith_inbound_counts
  18. 2025 Pith paper

    R-Zero: Self-Evolving Reasoning LLM from Zero Data

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 54 pith inbound references from cited_work_pith_inbound_counts
  19. 2025 Pith paper

    Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

    cs.AI provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Haitao Mi
    Author position
    18
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 8 pith inbound references from cited_work_pith_inbound_counts
  20. 2025 Pith paper

    One Token to Fool LLM-as-a-Judge

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 12 pith inbound references from cited_work_pith_inbound_counts
  21. 2025 Pith paper

    MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 19 pith inbound references from cited_work_pith_inbound_counts
  22. 2025 Pith paper

    Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving

    cs.LO provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  23. 2025 Pith paper

    DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    12
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 4 pith inbound references from cited_work_pith_inbound_counts
  24. 2025 Pith paper

    Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    11
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  25. 2025 Pith paper

    Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 6 pith inbound references from cited_work_pith_inbound_counts
  26. 2025 Pith paper

    MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  27. 2025 Pith paper

    Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  28. 2025 Pith paper

    WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 9 pith inbound references from cited_work_pith_inbound_counts
  29. 2025 Pith paper

    DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    14
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 51 pith inbound references from cited_work_pith_inbound_counts
  30. 2025 Pith paper

    Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 24 pith inbound references from cited_work_pith_inbound_counts
  31. 2025 Pith paper

    Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    10
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  32. 2025 Pith paper

    The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    12
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  33. 2025 Pith paper

    Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 5 pith inbound references from cited_work_pith_inbound_counts
  34. 2025 Pith paper

    Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  35. 2025 Pith paper

    Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    13
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 13 pith inbound references from cited_work_pith_inbound_counts
  36. 2024 Pith paper

    Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    13
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 67 pith inbound references from cited_work_pith_inbound_counts
  37. 2024 Pith paper

    HunyuanProver: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 9 pith inbound references from cited_work_pith_inbound_counts
  38. 2024 Pith paper

    Teaching LLMs to Refine with Tools

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  39. 2024 Pith paper

    Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 7 pith inbound references from cited_work_pith_inbound_counts
  40. 2024 Pith paper

    Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  41. 2024 Pith paper

    DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  42. 2024 Pith paper

    HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  43. 2024 Pith paper

    SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  44. 2024 Pith paper

    Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 5 pith inbound references from cited_work_pith_inbound_counts
  45. 2024 Pith paper

    LiteSearch: Efficacious Tree Search for LLM

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  46. 2024 Pith paper

    Scaling Synthetic Data Creation with 1,000,000,000 Personas

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 50 pith inbound references from cited_work_pith_inbound_counts
  47. 2024 Pith paper

    Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  48. 2024 Pith paper

    Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 6 pith inbound references from cited_work_pith_inbound_counts
  49. 2024 Pith paper

    Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  50. 2024 Pith paper

    Self-Consistency Boosts Calibration for Math Reasoning

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  51. 2024 Pith paper

    A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  52. 2024 Pith paper

    Collaborative decoding of critical tokens for boosting factuality of large language models

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  53. 2024 Pith paper

    Fine-Grained Self-Endorsement Improves Factuality and Reasoning

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  54. 2024 Pith paper

    Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  55. 2024 Pith paper

    Inconsistent dialogue responses and how to recover from them

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  56. 2023 Pith paper

    The Trickle-down Impact of Reward (In-)consistency on RLHF

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  57. 2023 Pith paper

    Stabilizing RLHF through Advantage Model and Selective Rehearsal

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  58. 2023 Pith paper

    Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  59. 2023 Pith paper

    Friend-training: Learning from Models of Different but Related Tasks

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  60. 2022 Pith paper

    Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  61. 2022 Pith paper

    Learning a Grammar Inducer from Massive Uncurated Instructional Videos

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  62. 2022 Pith paper

    Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  63. 2022 Pith paper

    Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  64. 2021 Pith paper

    DP-FP: Differentially Private Forward Propagation for Large Models

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  65. 2021 Pith paper

    A Dialogue-based Information Extraction System for Medical Insurance Assessment

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  66. 2021 Pith paper

    R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  67. 2016 Pith paper

    Multi-Perspective Context Matching for Machine Comprehension

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  68. 2016 Pith paper

    Temporal Attention Model for Neural Machine Translation

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  69. 2016 Pith paper

    Supervised Attentions for Neural Machine Translation

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  70. 2016 Pith paper

    Sense Embedding Learning for Word Sense Induction

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  71. 2016 Pith paper

    Vocabulary Manipulation for Neural Machine Translation

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  72. 2016 Pith paper

    Coverage Embedding Models for Neural Machine Translation

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  73. 2016 Pith paper

    Sentence Similarity Learning by Lexical Decomposition and Composition

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  74. 2016 Pith paper

    Semi-supervised Clustering for Short Text via Deep Representation Learning

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Haitao Mi
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.

Evidence apparatus

The machinery behind this record. Every lane states whether Pith measured it, did not query it, could not reach it, or withheld it.

LaneStateObservedBoundary and source
identity Measured 2 Canonical identity row plus public typed identifiers.
source=authors, author_identifiers
papers Measured 74 of 74 bounded rows Rows attributed to this author UUID in the Pith corpus.
source=paper_authors
works Measured zero 0 of 0 bounded rows Imported works not duplicated by the paper ledger.
source=author_works
reviews Measured 21 of 74 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 40 of 74 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 74 bounded rows Shared-work edges from admitted paper rows.
source=paper_authors
account Unavailable No public count of 1 bounded rows Account metadata is separate from corpus evidence.
source=users.author_id
Public identity sources
  • name variant
    Haitao Mi     backfill
    confidence 0.6

identity history

Enumerated research scope

Fields and dates come only from enumerated, non-disputed Pith paper rows. They do not claim career completeness.

  • cs.CL48 rows
  • cs.LG12 rows
  • cs.AI11 rows
  • cs.CV2 rows
  • cs.LO1 rows
  • 20168 rows
  • 20213 rows
  • 20224 rows
  • 20234 rows
  • 202420 rows
  • 202521 rows
  • 202614 rows
Shared-work index
Record scope

The work queries are bounded. Missing rows may mean measured zero, an unavailable source, a query that did not run, or private data that Pith withheld. The lane table keeps those cases separate.

Paper findings remain attached to papers. They do not become findings about this researcher.