Copertina

Circuits, Features, and Heuristics in Molecular Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Varadi, Kristof, Marosi, Mark, Antal, Peter
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Heuristic Transformer: Belief Augmented In-Context Reinforcement Learning
di: Dippel, Oliver, et al.
Pubblicazione: (2025)

Towards a Law of Iterated Expectations for Heuristic Estimators
di: Christiano, Paul, et al.
Pubblicazione: (2024)

Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers
di: Xu, Yongzhong
Pubblicazione: (2026)

It's complicated. The relationship of algorithmic fairness and non-discrimination provisions for high-risk systems in the EU AI Act
di: Meding, Kristof
Pubblicazione: (2025)

Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
di: Cao, Tue M., et al.
Pubblicazione: (2026)

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
di: Dai, Xinnan, et al.
Pubblicazione: (2025)

GDP nowcasting with artificial neural networks: How much does long-term memory matter?
di: Németh, Kristóf, et al.
Pubblicazione: (2023)

Generating density nowcasts for U.S. GDP growth with deep learning: Bayes by Backprop and Monte Carlo dropout
di: Németh, Kristóf, et al.
Pubblicazione: (2024)

Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers
di: Liu, Naiming, et al.
Pubblicazione: (2026)

Finding Interpretable Prompt-Specific Circuits in Language Models
di: Franco, Gabriel, et al.
Pubblicazione: (2026)

Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition
di: Hsu, Aliyah R., et al.
Pubblicazione: (2024)

Transformer Circuit Faithfulness Metrics are not Robust
di: Miller, Joseph, et al.
Pubblicazione: (2024)

Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
di: Furuta, Hiroki, et al.
Pubblicazione: (2024)

Multi-Hierarchical Fine-Grained Feature Mapping Driven by Feature Contribution for Molecular Odor Prediction
di: Xie, Hong Xin, et al.
Pubblicazione: (2025)

Learning Admissible Heuristics for A*: Theory and Practice
di: Futuhi, Ehsan, et al.
Pubblicazione: (2025)

Demystifying the Recency Heuristic in Temporal-Difference Learning
di: Daley, Brett, et al.
Pubblicazione: (2024)

Graph Diffusion Transformers are In-Context Molecular Designers
di: Liu, Gang, et al.
Pubblicazione: (2025)

Equivariant Spherical Transformer for Efficient Molecular Modeling
di: An, Junyi, et al.
Pubblicazione: (2025)

Data-Aware Random Feature Kernel for Transformers
di: Farzam, Amirhossein, et al.
Pubblicazione: (2026)

Feature-level Interaction Explanations in Multimodal Transformers
di: Kim, Yeji, et al.
Pubblicazione: (2026)

Link Prediction for Social Networks using Representation Learning and Heuristic-based Features
di: Khanna, Samarth, et al.
Pubblicazione: (2024)

GTAC: A Generative Transformer for Approximate Circuits
di: Wang, Jingxin, et al.
Pubblicazione: (2025)

Generalizable Heuristic Generation Through LLMs with Meta-Optimization
di: Shi, Yiding, et al.
Pubblicazione: (2025)

Deep Heuristic Learning for Real-Time Urban Pathfinding
di: El-Ela, Mohamed Hussein Abo, et al.
Pubblicazione: (2024)

Enhancing Q-Learning with Large Language Model Heuristics
di: Wu, Xiefeng
Pubblicazione: (2024)

Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation
di: Sommer, Johanna, et al.
Pubblicazione: (2025)

Beware! The AI Act Can Also Apply to Your AI Research Practices
di: Wernick, Alina, et al.
Pubblicazione: (2025)

What constitutes a Deep Fake? The blurry line between legitimate processing and manipulation under the EU AI Act
di: Meding, Kristof, et al.
Pubblicazione: (2024)

Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithms
di: Meding, Kristof, et al.
Pubblicazione: (2023)

Sparse Attention Decomposition Applied to Circuit Tracing
di: Franco, Gabriel, et al.
Pubblicazione: (2024)

QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations
di: Zhao, Zhixiong, et al.
Pubblicazione: (2025)

Disentangled (Un)Controllable Features
di: Kooi, Jacob E., et al.
Pubblicazione: (2022)

RT-Transformer: The Transformer Block as a Spherical State Estimator
di: Racioppo, Peter
Pubblicazione: (2026)

Singular Vectors of Attention Heads Align with Features
di: Franco, Gabriel, et al.
Pubblicazione: (2026)

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
di: Eschenhagen, Runa, et al.
Pubblicazione: (2025)

Automatic Reward Shaping from Multi-Objective Human Heuristics
di: Xie, Yuqing, et al.
Pubblicazione: (2025)

Going Beyond Heuristics by Imposing Policy Improvement as a Constraint
di: Lee, Chi-Chang, et al.
Pubblicazione: (2025)

Learning to Condition: A Neural Heuristic for Scalable MPE Inference
di: Malhotra, Brij, et al.
Pubblicazione: (2025)

Adaptive Variational Continual Learning via Task-Heuristic Modelling
di: Yang, Fan
Pubblicazione: (2024)

SynCircuit: Automated Generation of New Synthetic RTL Circuits Can Enable Big Data in Circuits
di: Liu, Shang, et al.
Pubblicazione: (2025)