Copertina

Swing-by Dynamics in Concept Learning and Compositional Generalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Yongyi, Park, Core Francisco, Lubana, Ekdeep Singh, Okawa, Maya, Hu, Wei, Tanaka, Hidenori
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
di: Park, Core Francisco, et al.
Pubblicazione: (2024)

Competition Dynamics Shape Algorithmic Phases of In-Context Learning
di: Park, Core Francisco, et al.
Pubblicazione: (2024)

ICLR: In-Context Learning of Representations
di: Park, Core Francisco, et al.
Pubblicazione: (2024)

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
di: Okawa, Maya, et al.
Pubblicazione: (2023)

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
di: Nishi, Kento, et al.
Pubblicazione: (2024)

In-Context Learning Strategies Emerge Rationally
di: Wurgaft, Daniel, et al.
Pubblicazione: (2025)

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
di: Ramesh, Rahul, et al.
Pubblicazione: (2023)

Emergence of Hierarchical Emotion Organization in Large Language Models
di: Zhao, Bo, et al.
Pubblicazione: (2025)

Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
di: Khona, Mikail, et al.
Pubblicazione: (2024)

Abrupt Learning in Transformers: A Case Study on Matrix Completion
di: Gopalani, Pulkit, et al.
Pubblicazione: (2024)

A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
di: Lubana, Ekdeep Singh, et al.
Pubblicazione: (2024)

In-Context Learning Dynamics with Random Binary Sequences
di: Bigelow, Eric J., et al.
Pubblicazione: (2023)

Provable Low-Frequency Bias of In-Context Learning of Representations
di: Yang, Yongyi, et al.
Pubblicazione: (2025)

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
di: Bigelow, Eric, et al.
Pubblicazione: (2025)

$\textit{New News}$: System-2 Fine-tuning for Robust Integration of New Knowledge
di: Park, Core Francisco, et al.
Pubblicazione: (2025)

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
di: Jaipersaud, Brandon, et al.
Pubblicazione: (2025)

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
di: Hindupur, Sai Sumedh R., et al.
Pubblicazione: (2025)

Analyzing (In)Abilities of SAEs via Formal Languages
di: Menon, Abhinav, et al.
Pubblicazione: (2024)

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
di: Jain, Samyak, et al.
Pubblicazione: (2023)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
di: Mueller, Aaron, et al.
Pubblicazione: (2025)

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
di: Costa, Valérie, et al.
Pubblicazione: (2025)

Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit
di: Costa, Valérie, et al.
Pubblicazione: (2025)

Convergent World Representations and Divergent Tasks
di: Park, Core Francisco
Pubblicazione: (2026)

The Impact of Off-Policy Training Data on Probe Generalisation
di: Kirch, Nathalie, et al.
Pubblicazione: (2025)

An Equivariance Toolbox for Learning Dynamics
di: Yang, Yongyi, et al.
Pubblicazione: (2025)

Do Sparse Autoencoders Capture Concept Manifolds?
di: Bhalla, Usha, et al.
Pubblicazione: (2026)

Detecting High-Stakes Interactions with Activation Probes
di: McKenzie, Alex, et al.
Pubblicazione: (2025)

Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
di: Prasad, Aaditya Vikram, et al.
Pubblicazione: (2026)

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
di: Huang, Jing, et al.
Pubblicazione: (2026)

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
di: Bigelow, Eric, et al.
Pubblicazione: (2026)

Decomposing Elements of Problem Solving: What "Math" Does RL Teach?
di: Qin, Tian, et al.
Pubblicazione: (2025)

Meta-Learning for Neural Network-based Temporal Point Processes
di: Takimoto, Yoshiaki, et al.
Pubblicazione: (2024)

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
di: Jain, Samyak, et al.
Pubblicazione: (2024)

Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains
di: Tanaka, Yusuke, et al.
Pubblicazione: (2022)

New Evidence of the Two-Phase Learning Dynamics of Neural Networks
di: Zhou, Zhanpeng, et al.
Pubblicazione: (2025)

RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm
di: Yang, Yongyi, et al.
Pubblicazione: (2025)

HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks
di: Yang, Yongyi, et al.
Pubblicazione: (2024)

On the Cone Effect in the Learning Dynamics
di: Zhou, Zhanpeng, et al.
Pubblicazione: (2025)

Continuous-Time Analysis of Adaptive Optimization and Normalization
di: Gould, Rhys, et al.
Pubblicazione: (2024)

Cross-patient Seizure Onset Zone Classification by Patient-Dependent Weight
di: Zhao, Xuyang, et al.
Pubblicazione: (2025)