Jiaqi W. Ma
7 papers · 2024–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Silver
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(16)
π
Keyword Champion
(4)
Venues
Top co-authors
Research topics
Keywords
data attribution
(4)
influence function
(3)
subset selection
(1)
adversarial attack
(1)
greedy algorithm
(1)
data selection
(1)
vision-language model
(1)
instruction fine-tuning
(1)
membership inference
(1)
training data
(1)
model interpretation
(1)
abstract reasoning
(1)
llm safety
(1)
influence score
(1)
verbatim memorization
(1)
copyright detection
(1)
perception bottleneck
(1)
non-decomposable loss
(1)
leave-one-out retraining
(1)
abstraction and reasoning corpus
(1)
Papers
Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks
ACL 2026
Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks
ACL 2026
Adversarial Attacks on Data Attribution
ICLR 2025
A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
ICML 2025
Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
EMNLP 2025
dattri: A Library for Efficient Data Attribution
NeurIPS 2024
Most Influential Subset Selection: Challenges, Promises, and Beyond
NeurIPS 2024