Pith. sign in

Researcher Evidence Record

Denis Kuznedelev

This bounded record lists 21 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.LG, cs.CV, cs.CL work dated 2022 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 21 attributed paper rows in the Pith corpus, itemized below Imported works 0 imported works beyond the paper ledger Current reviews 2 of 21 papers carrying a current Pith review; presence, not outcome Sourced citations 11 of 21 works with a source-named citation count Coauthors 50 distinct coauthors across shared paper rows
Enumerated paper scope: 5 fields (cs.LG, cs.CV, cs.CL, +2 more) · 2022-2026 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

    KV Cache Offloading for Context-Intensive Tasks

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    3
    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. 2025 Pith paper

    Asynchronous Reasoning: Training-Free Interactive Thinking LLMs

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Denis Kuznedelev
    Author position
    5
    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
  3. 2025 Pith paper

    Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

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

    Label Privacy in Split Learning for Large Models with Parameter-Efficient Training

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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.
  5. 2024 Pith paper

    Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

    cs.CV provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    2
    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
  6. 2024 Pith paper

    EvoPress: Accurate Dynamic Model Compression via Evolutionary Search

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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
  7. 2024 Pith paper

    Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization

    cs.CV provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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
  8. 2024 Pith paper

    The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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.
  9. 2024 Pith paper

    Does Diffusion Beat GAN in Image Super Resolution?

    eess.IV provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    1
    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
  10. 2024 Pith paper

    PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    4
    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
  11. 2024 Pith paper

    YaART: Yet Another ART Rendering Technology

    cs.CV provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    8
    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. 2024 Pith paper

    Extreme Compression of Large Language Models via Additive Quantization

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 25 pith inbound references from cited_work_pith_inbound_counts
  13. 2023 Pith paper

    Sparse Fine-tuning for Inference Acceleration 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
    Denis Kuznedelev
    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.
  14. 2023 Pith paper

    Accurate Neural Network Pruning Requires Rethinking Sparse Optimization

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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.
  15. 2023 Pith paper

    SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 31 pith inbound references from cited_work_pith_inbound_counts
  16. 2023 Pith paper

    Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression

    cs.CV provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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.
  17. 2023 Pith paper

    Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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.
  18. 2023 Pith paper

    A critical look at the evaluation of GNNs under heterophily: Are we really making progress?

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 14 pith inbound references from cited_work_pith_inbound_counts
  19. 2022 Pith paper

    CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models

    cs.CV provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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. 2022 Pith paper

    Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond

    cs.SI provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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.
  21. 2022 Pith paper

    A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Denis Kuznedelev
    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 21 of 21 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 2 of 21 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 11 of 21 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 21 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
    Denis Kuznedelev     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.LG12 rows
  • cs.CV5 rows
  • cs.CL2 rows
  • cs.SI1 rows
  • eess.IV1 rows
  • 20223 rows
  • 20236 rows
  • 20249 rows
  • 20252 rows
  • 20261 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.