Pith. sign in

Researcher Evidence Record

Ziquan Liu

This bounded record lists 30 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.CV, cs.LG, cs.CL work dated 2020 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.

Enumerated paper scope: 6 fields (cs.CV, cs.LG, cs.CL, +3 more) · 2020-2026 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

    Each Judge Its Own Yardstick: Discovering Per-VLM Taxonomies for Physical Video Evaluation

    cs.CV provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    2
    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
  2. 2026 Pith paper

    LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution

    cs.CV provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    2
    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

    MidSteer: Optimal Affine Framework for Steering Generative Models

    cs.LG provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    3
    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

    Confidence Should Be Calibrated More Than One Turn Deep

    cs.CL provisional current review present

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Ziquan Liu
    Author position
    5
    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

    LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

    cs.CV provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    2
    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
  6. 2026 Pith paper

    GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking

    cs.CV provisional current review present

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Ziquan Liu
    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
  7. 2025 Pith paper

    GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models

    cs.CL provisional current review present

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Ziquan Liu
    Author position
    2
    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. 2025 Pith paper

    Reinforcement Learning for Target Zone Blood Glucose Control

    cs.LG provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    4
    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. 2025 Pith paper

    ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction

    cs.CV provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    2
    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.
  10. 2025 Pith paper

    Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking

    cs.CV provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    4
    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.
  11. 2025 Pith paper

    Query-based Knowledge Transfer for Heterogeneous Learning Environments

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  12. 2025 Pith paper

    V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning

    cs.CV provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 22 pith inbound references from cited_work_pith_inbound_counts
  13. 2025 Pith paper

    CASteer: Cross-Attention Steering for Controllable Concept Erasure

    cs.GR provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    4
    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
  14. 2025 Pith paper

    Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework

    cs.AI provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    8
    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
  15. 2025 Pith paper

    AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data

    cs.CV provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    2
    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
  16. 2025 Pith paper

    Sebra: Debiasing Through Self-Guided Bias Ranking

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  17. 2025 Pith paper

    RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning

    cs.CV provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    5
    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
  18. 2024 Pith paper

    Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization

    cs.CL provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  19. 2024 Pith paper

    The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  20. 2024 Pith paper

    Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    2
    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
  21. 2024 Pith paper

    PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  22. 2023 Pith paper

    Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions

    cs.CY provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    Author position
    2
    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. 2023 Pith paper

    DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks

    cs.CV provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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
  24. 2023 Pith paper

    TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  25. 2022 Pith paper

    Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  26. 2022 Pith paper

    An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation

    cs.CV provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  27. 2021 Pith paper

    Improved Fine-Tuning by Better Leveraging Pre-Training Data

    cs.CV provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  28. 2021 Pith paper

    Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  29. 2021 Pith paper

    Variational Nested Dropout

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.
  30. 2020 Pith paper

    Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ziquan Liu
    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.

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 30 of 30 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 10 of 30 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 11 of 30 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 30 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
    Ziquan Liu
    backfill
    confidence 0.6
Enumerated research scope

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

  • cs.CV12 rows
  • cs.LG12 rows
  • cs.CL3 rows
  • cs.AI1 rows
  • cs.CY1 rows
  • cs.GR1 rows
  • 20201 rows
  • 20213 rows
  • 20222 rows
  • 20233 rows
  • 20244 rows
  • 202511 rows
  • 20266 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.