:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Kangaslahti, Sara, Rosenfeld, Elan, Saphra, Naomi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	https://arxiv.org/abs/2506.15872
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Fast Forwarding Low-Rank Training
di: Rahamim, Adir, et al.
Pubblicazione: (2024)

One-Shot Strategic Classification Under Unknown Costs
di: Rosenfeld, Elan, et al.
Pubblicazione: (2023)

Continuous Language Model Interpolation for Dynamic and Controllable Text Generation
di: Kangaslahti, Sara, et al.
Pubblicazione: (2024)

Latent State Models of Training Dynamics
di: Hu, Michael Y., et al.
Pubblicazione: (2023)

Mechanistic?
di: Saphra, Naomi, et al.
Pubblicazione: (2024)

Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
di: Qin, Tian, et al.
Pubblicazione: (2024)

Deep sequence models tend to memorize geometrically; it is unclear why
di: Noroozizadeh, Shahriar, et al.
Pubblicazione: (2025)

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
di: van der Wal, Oskar, et al.
Pubblicazione: (2025)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
di: Sherborne, Tom, et al.
Pubblicazione: (2023)

Identifying Representations for Intervention Extrapolation
di: Saengkyongam, Sorawit, et al.
Pubblicazione: (2023)

Transcendence: Generative Models Can Outperform The Experts That Train Them
di: Zhang, Edwin, et al.
Pubblicazione: (2024)

Inverse Depth Scaling From Most Layers Being Similar
di: Liu, Yizhou, et al.
Pubblicazione: (2026)

World Properties without World Models: Recovering Spatial and Temporal Structure from Co-occurrence Statistics in Static Word Embeddings
di: Barenholtz, Elan
Pubblicazione: (2026)

Random Scaling of Emergent Capabilities
di: Zhao, Rosie, et al.
Pubblicazione: (2025)

Boomerang Distillation Enables Zero-Shot Model Size Interpolation
di: Kangaslahti, Sara, et al.
Pubblicazione: (2025)

Do Activation Verbalization Methods Convey Privileged Information?
di: Li, Millicent, et al.
Pubblicazione: (2025)

Can Interpretation Predict Behavior on Unseen Data?
di: Li, Victoria R., et al.
Pubblicazione: (2025)

Analyzing Political Text at Scale with Online Tensor LDA
di: Kangaslahti, Sara, et al.
Pubblicazione: (2025)

Using Shapley interactions to understand how models use structure
di: Singhvi, Divyansh, et al.
Pubblicazione: (2024)

Attribute Diversity Determines the Systematicity Gap in VQA
di: Berlot-Attwell, Ian, et al.
Pubblicazione: (2023)

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

Learning under noisy supervision is governed by a feedback-truth gap
di: Schonfeld, Elan, et al.
Pubblicazione: (2026)

K-Edit: Language Model Editing with Contextual Knowledge Awareness
di: Markowitz, Elan, et al.
Pubblicazione: (2025)

Strategic Classification with Non-Linear Classifiers
di: Trachtenberg, Benyamin, et al.
Pubblicazione: (2025)

Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias
di: Itzhak, Itay, et al.
Pubblicazione: (2023)

FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models
di: Liu, Jiachang, et al.
Pubblicazione: (2024)

Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
di: Yu, Zhongzhi, et al.
Pubblicazione: (2024)

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
di: Kong, Lingkai, et al.
Pubblicazione: (2026)

Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
di: Beerens, Lucas, et al.
Pubblicazione: (2025)

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them
di: Chen, Guanyu, et al.
Pubblicazione: (2025)

A Market for Accuracy: Classification under Competition
di: Einav, Ohad, et al.
Pubblicazione: (2025)

Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmap
di: Rosenfeld, Nir, et al.
Pubblicazione: (2025)

Multiway Multislice PHATE: Visualizing Hidden Dynamics of RNNs through Training
di: Xie, Jiancheng, et al.
Pubblicazione: (2024)

Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges
di: Jaquier, Noémie, et al.
Pubblicazione: (2023)

Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
di: Wu, Jianghao, et al.
Pubblicazione: (2026)

Pre-trained Large Language Models Learn Hidden Markov Models In-context
di: Dai, Yijia, et al.
Pubblicazione: (2025)

Layer by Layer: Uncovering Hidden Representations in Language Models
di: Skean, Oscar, et al.
Pubblicazione: (2025)

Prototype Training with Dual Pseudo-Inverse and Optimized Hidden Activations
di: Tucci, Mauro
Pubblicazione: (2025)

Evolutionary Prediction Games
di: Saig, Eden, et al.
Pubblicazione: (2025)

Learning Classifiers That Induce Markets
di: Sommer, Yonatan, et al.
Pubblicazione: (2025)