Yaniv Nikankin
5 papers · 2023–2025 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
👥
Mega-Team · Squad
Venues
Top co-authors
Research topics
Keywords
mechanistic interpretability
(3)
video generation
(1)
video prediction
(1)
multi-class classification
(1)
integer programming
(1)
diffusion model
(1)
convolutional neural network
(1)
weight decay
(1)
circuit analysis
(1)
sparse autoencoder
(1)
model optimization
(1)
circuit discovery
(1)
motion dynamics
(1)
causal analysis
(1)
data reconstruction
(1)
arithmetic reasoning
(1)
single image
(1)
large language model
(1)
neural network
(1)
attribution score
(1)
Papers
Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
ICLR 2025
BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection
EMNLP 2025
MIB: A Mechanistic Interpretability Benchmark
ICML 2025
Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses
NeurIPS 2023
SinFusion: Training Diffusion Models on a Single Image or Video
ICML 2023