Copertina

Where is the Truth? The Risk of Getting Confounded in a Continual World

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Busch, Florian Peter, Kamath, Roshni, Mitchell, Rupert, Stammer, Wolfgang, Kersting, Kristian, Mundt, Martin
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

BOWL: A Deceptively Simple Open World Learner
di: Kamath, Roshni . R., et al.
Pubblicazione: (2024)

Masked Autoencoders are Efficient Continual Federated Learners
di: Paul, Subarnaduti, et al.
Pubblicazione: (2023)

Self-Expanding Neural Networks
di: Mitchell, Rupert, et al.
Pubblicazione: (2023)

Scaling Probabilistic Circuits via Data Partitioning
di: Seng, Jonas, et al.
Pubblicazione: (2025)

Deep Classifier Mimicry without Data Access
di: Braun, Steven, et al.
Pubblicazione: (2023)

Object Centric Concept Bottlenecks
di: Steinmann, David, et al.
Pubblicazione: (2025)

Learning to Intervene on Concept Bottlenecks
di: Steinmann, David, et al.
Pubblicazione: (2023)

Boosting Object Representation Learning via Motion and Object Continuity
di: Delfosse, Quentin, et al.
Pubblicazione: (2022)

Neural Concept Binder
di: Stammer, Wolfgang, et al.
Pubblicazione: (2024)

Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
di: Mitchell, Rupert, et al.
Pubblicazione: (2025)

A Typology for Exploring the Mitigation of Shortcut Behavior
di: Friedrich, Felix, et al.
Pubblicazione: (2022)

Adaptive Rational Activations to Boost Deep Reinforcement Learning
di: Delfosse, Quentin, et al.
Pubblicazione: (2021)

Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
di: Delfosse, Quentin, et al.
Pubblicazione: (2024)

Better Decisions through the Right Causal World Model
di: Dillies, Elisabeth, et al.
Pubblicazione: (2025)

The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation
di: Mundt, Martin, et al.
Pubblicazione: (2025)

Tagged for Direction: Pinning Down Causal Edge Directions with Precision
di: Busch, Florian Peter, et al.
Pubblicazione: (2025)

Learning by Self-Explaining
di: Stammer, Wolfgang, et al.
Pubblicazione: (2023)

Continual Learning Should Move Beyond Incremental Classification
di: Mitchell, Rupert, et al.
Pubblicazione: (2025)

SLR: Automated Synthesis for Scalable Logical Reasoning
di: Helff, Lukas, et al.
Pubblicazione: (2025)

Tractable Representation Learning with Probabilistic Circuits
di: Braun, Steven, et al.
Pubblicazione: (2025)

Pix2Code: Learning to Compose Neural Visual Concepts as Programs
di: Wüst, Antonia, et al.
Pubblicazione: (2024)

V-LoL: A Diagnostic Dataset for Visual Logical Learning
di: Helff, Lukas, et al.
Pubblicazione: (2023)

Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks
di: Woydt, Tim, et al.
Pubblicazione: (2025)

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
di: Turan, Berkant, et al.
Pubblicazione: (2025)

Systems with Switching Causal Relations: A Meta-Causal Perspective
di: Willig, Moritz, et al.
Pubblicazione: (2024)

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
di: Steinmann, David, et al.
Pubblicazione: (2024)

Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
di: Wüst, Antonia, et al.
Pubblicazione: (2024)

ActivationReasoning: Logical Reasoning in Latent Activation Spaces
di: Helff, Lukas, et al.
Pubblicazione: (2025)

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
di: Helff, Lukas, et al.
Pubblicazione: (2026)

Making deep neural networks right for the right scientific reasons by interacting with their explanations
di: Schramowski, Patrick, et al.
Pubblicazione: (2020)

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
di: Delfosse, Quentin, et al.
Pubblicazione: (2024)

Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
di: Jaziri, Achref, et al.
Pubblicazione: (2025)

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
di: Struppek, Lukas, et al.
Pubblicazione: (2023)

GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
di: Shindo, Hikaru, et al.
Pubblicazione: (2026)

Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions
di: Cömer, Can, et al.
Pubblicazione: (2025)

Hyperparameter Optimization via Interacting with Probabilistic Circuits
di: Seng, Jonas, et al.
Pubblicazione: (2025)

Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess
di: Helfenstein, Felix, et al.
Pubblicazione: (2024)

Right on Time: Revising Time Series Models by Constraining their Explanations
di: Kraus, Maurice, et al.
Pubblicazione: (2024)

Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
di: Prabhakar, Nikhilesh, et al.
Pubblicazione: (2026)

Reinforcement Learning with Continuous Actions Under Unmeasured Confounding
di: Li, Yuhan, et al.
Pubblicazione: (2025)