The catalog, page 15
Records 3,501 to 3,750 of 10,618. Explained and Verified records first, then newest. Every row carries the label that says how far the checking went.
-
Information acquisition under resource limitations in a noisy environment.
Listed -
Information Technology Roles and Their Most-Used Programming Languages.
Listed -
Instruction-Following Agents with Jointly Pre-Trained Vision-Language Models.
Listed -
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning.
Listed - Listed
-
ISAACS: Iterative Soft Adversarial Actor-Critic for Safety.
Listed -
Israel’s Autonomous Urban Quadcopter Brings ‘Search & Attack In One’.
Listed -
It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation.
Listed -
JEDAI: A System for Skill-Aligned Explainable Robot Planning.
Listed -
Joint Communication and Motion Planning for Cobots.
Listed -
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents.
Listed -
Learning Bimanual Scooping Policies for Food Acquisition.
Listed -
Learning Deterministic Finite Automata Decompositions from Examples and Demonstrations.
Listed -
Learning from Humans for Adaptive Interaction.
Listed -
Learning from Imperfect Demonstrations via Adversarial Confidence Transfer.
Listed -
Learning Latent Actions to Control Assistive Robots.
Listed -
Learning multimodal rewards from rankings.
Listed -
Learning Multimodal Rewards from Rankings.
Listed -
Learning Preferences for Interactive Autonomy.
Listed -
Learning Representations that Enable Generalization in Assistive Tasks.
Listed - Listed
-
Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation.
Listed -
Learning Visuo-Haptic Skewering Strategies for Robot-Assisted Feeding.
Listed - Listed
- Listed
-
Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction.
Listed -
Linguistic communication as (inverse) reward design.
Listed -
Masked Autoencoding for Scalable and Generalizable Decision Making.
Listed -
Masked World Models for Visual Control.
Listed -
Mechanisms of Belief Persistence in the Face of Societal Disagreement.
Listed -
Mens Rea in Moral Judgment and Criminal Law.
Listed -
Metareasoning for Safe Decision Making in Autonomous Systems.
Listed -
Microdrones: the AI assassins set to become weapons of mass destruction.
Listed -
Mining Frequently Traveled Routes During COVID-19.
Listed -
Mirror learning: A unifying framework of policy optimisation.
Listed -
Motivated to learn: An account of explanatory satisfaction.
Listed -
Multi-agent reinforcement learning is a sequence modeling problem.
Listed -
Multi-Objective Policy Gradients with Topological Constraints.
Listed -
No‑regret Learning in Dynamic Stackelberg Games.
Listed - Listed
-
On testing for discrimination using causal models.
Listed -
On the computational consequences of cost function design in nonlinear optimal control.
Listed -
On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning.
Listed -
Optimal Behavior Prior: Improving Human-AI Collaboration Through Generalizable Human Models..
Listed -
Optimal conservative offline RL with general function approximation via augmented Lagrangian.
Listed - Listed
-
Pairwise Weights for Temporal Credit Assignment.
Listed -
PantheonRL: A MARL Library for Dynamic Training Interactions.
Listed -
Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams.
Listed -
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation.
Listed -
PhD thesis: SQL Comprehension and Synthesis.
Listed -
PLATO: Predicting Latent Affordances Through Object-Centric Play.
Listed -
Playful Interactions for Representation Learning.
Listed -
Politicians must prepare for AI or face the consequences.
Listed -
Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design.
Listed -
Probabilistic and Causal Inference: The Works of Judea Pearl.
Listed -
Real-World Robot Learning with Masked Visual Pre-training.
Listed -
Reasoning about causal models with infinitely many variables.
Listed - Listed
-
Reducing Exploitability with Population Based Training.
Listed -
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks.
Listed -
Reinforcement Learning with Action-Free Pre-Training from Videos.
Listed - Listed
-
Reliable Prediction and Decision-Making in Sequential Environments.
Listed - Listed
-
Retrospective on the 2021 MineRL BASALT Competition on Learning from Human Feedback.
Listed -
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning.
Listed - Listed
-
Robotic Weapons Are Coming: What Should We Do About It.
Listed -
RvS: What is Essential for Offline RL via Supervised Learning?.
Listed -
Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Models.
Listed -
Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments.
Listed -
SHARP: Shielding-aware robust planning for safe and efficient human-robot interaction.
Listed -
Sim-to-Lab-to-Real: Safe RL with Shielding and Generalization Guarantees.
Listed -
Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin-picking.
Listed -
Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data.
Listed - Listed
-
Simplicity as a Cue to Probability: multiple roles for Simplicity in Evaluating Explanations.
Listed - Listed
-
Social media is polluting society. Moderation alone won’t fix the problem.
Listed -
Sociotechnical Specification for the Broader Impacts of Autonomous Vehicles.
Listed -
Solving Structured Hierarchical Games Using Differential Backward Induction.
Listed -
Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions.
Listed -
Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents.
Listed -
Steerable Partial Differential Operators for Equivariant Neural Networks.
Listed -
Stress, Intertemporal Choice, and Mitigation Behavior During the COVID-19 Pandemic.
Listed -
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ Tasks..
Listed - Listed
-
Teaching Robots to Span the Space of Functional Expressive Motion. .
Listed -
The best of Radio Davos over the last year.
Listed -
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models.
Listed -
The Foundations of Artificial Intelligence.
Listed -
The promises and perils of AI.
Listed -
Time spent thinking in online chess reflects the value of computation.
Listed -
Time-Efficient Reward Learning via Visually Assisted Cluster Ranking.
Listed -
Toward transparent ai: A survey on interpreting the inner structures of deep neural networks.
Listed -
Towards more Generalizable One-shot Visual Imitation Learning.
Listed -
Towards Psychologically-Grounded Dynamic Preference Models.
Listed -
trading with superintelligence: a wonky proto-alignment scheme
Listed -
Training and Inference on Any-Order Autoregressive Models the Right Way.
Listed -
Tuning the Hyperparameters of Anytime Planning: A Metareasoning Approach with Deep RL.
Listed -
Uncertain Decisions Facilitate Better Preference Learning.
Listed -
Uncertainty Estimation for Language Reward Models.
Listed -
Understanding Value Decomposition Algorithms in Deep Cooperative Multi-Agent Reinforcement Learning.
Listed -
Uni[MASK]: Unified Inference in Sequential Decision Problems. .
Listed -
Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines..
Listed -
Varieties of ignorance: Mystery and the unknown in science and religion.
Listed -
Weakly Supervised Correspondence Learning.
Listed - Listed
-
When and how children use explanations to guide generalizations.
Listed -
White-Box Adversarial Policies in Deep Reinforcement Learning.
Listed -
Why we need to regulate non-state use of arms.
Listed -
WordSig: QR streams enabling platform-independent self-identification that’s impossible to deepfake.
Listed -
X-Risk Analysis for AI Research.
Listed -
Zero-Shot Text-Guided Object Generation with Dream Fields,.
Listed -
An extended rocket alignment analogy
Listed - Listed
-
Evolution is a bad analogy for AGI: inner alignment
Listed - Listed
-
Gradient descent doesn't select for inner search
Listed - Listed
-
I missed the crux of the alignment problem the whole time
Listed -
Recognition of All Categories of Entities by AI
Listed - Listed
-
Shapes of Mind and Pluralism in Alignment
Listed - Listed
-
The animals and humans analogy for AI risk
Listed -
The Dumbest Possible Gets There First
Listed -
the Insulated Goal-Program idea
Listed -
why my timelines are short: all roads lead to doom
Listed - Listed
-
Artificial intelligence wireheading
Listed -
DeepMind alignment team opinions on AGI ruin arguments
Listed -
Distillation of The Offense-Defense Balance of Scientific Knowledge
Listed - Listed
-
Oversight Misses 100% of Thoughts The AI Does Not Think
Listed - Listed
-
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Listed - Listed
-
Timelines explanation post part 1 of ?
Listed -
A pseudo mathematical formulation of direct work choice between two x-risks
Listed -
Encultured AI Pre-planning, Part 2: Providing a Service
Listed -
Encultured AI, Part 2: Providing a Service
Listed - Listed
-
Language models seem to be much better than humans at next-token prediction
Listed - Listed
-
Seriously, what goes wrong with "reward the agent when it makes you smile"?
Listed - Listed
-
The alignment problem from a deep learning perspective
Listed -
what does it mean to value our survival?
Listed - Listed
-
active reward learning from multiple teachers.
Listed -
Active Reward Learning from Multiple Teachers.
Listed -
An Empirical Investigation of Representation Learning for Imitation.
Listed -
Artificial intelligence development races in heterogeneous settings.
Listed - Listed
-
Can Humans Do Less-Than-One-Shot Learning?.
Listed -
Clustering and the efficient use of cognitive resources..
Listed - Listed
- Listed
-
Complex cognitive algorithms preserved by selective social learning in experimental populations.
Listed -
Deep models of superficial face judgments.
Listed -
Delegation to artificial agents fosters prosocial behaviors in the collective risk dilemma.
Listed -
Differential Assessment of Black-Box AI Agents.
Listed -
Distinguishing rule- and exemplar-based generalization in learning systems.
Listed -
Dynamic Multi-Robot Task Allocation under Uncertainty and Temporal Constraints.
Listed -
From partners to populations: A hierarchical Bayesian account of coordination and convention.
Listed -
Globally inaccurate stereotypes can result from locally adaptive exploration.
Listed -
How Do We Align an AGI Without Getting Socially Engineered? (Hint: Box It)
Listed -
How Do We Align an AGI Without Getting Socially Engineered? (Hint: Box It)
Listed -
How much alignment data will we need in the long run?
Listed -
How To Go From Interpretability To Alignment: Just Retarget The Search
Listed -
If it’s important, then I’m curious: Increasing perceived usefulness stimulates curiosity.
Listed -
Inferring strategies from observations in long iterated Prisoner’s dilemma experiments.
Listed -
Is the rise of killer machines closer than we think?.
Listed - Listed
-
Memory transmission in small groups and large networks: An empirical study.
Listed -
Multiscale Heterogeneous Optimal Lockdown Control for COVID-19 Using Geographic Information.
Listed -
Natural Selection Favors AIs over Humans.
Listed -
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection.
Listed -
Optimal policies for free recall.
Listed - Listed
-
People construct simplified mental representations to plan..
Listed -
Possible directions in AI ideal governance research
Listed -
Predicting Human Similarity Judgments Using Large Language Models..
Listed -
Probing BERT’s priors with serial reproduction chains.
Listed -
Rational heuristics for one-shot games.
Listed -
Rational use of cognitive resources in human planning. Nature Human Behaviour,.
Listed - Listed
- Listed
- Listed
-
Shared Autonomy for Robotic Manipulation with Language Corrections.
Listed -
The alignment problem from a deep learning perspective
Listed -
The experimental evolution of human culture: flexibility, fidelity and environmental instability.
Listed -
The History, Epistemology and Strategy of Technological Restraint, and lessons for AI (short essay)
Listed -
the Insulated Goal-Program idea
Listed -
The pursuit of happiness: A reinforcement learning perspective on habituation and comparisons.
Listed -
There are two factions working to prevent AI dangers. Here’s why they’re deeply divided.
Listed -
Trade Regulation Rule on Commercial Surveillance and Data Security Rulemaking.
Listed - Listed
- Listed
- Listed
-
Using GPT-3 to augment human intelligence
Listed -
Using Natural Language to Guide Meta-Learning Agents towards Human-like Inductive Biases.
Listed -
Voluntary safety commitments provide an escape from over-regulation in AI development.
Listed -
Announcing: Mechanism Design for AI Safety - Reading Group
Listed - Listed
-
Bahamian Adventures: An Epic Tale of Entrepreneurship, AI Strategy Research and Potatoes
Listed -
Content generation. Where do we draw the line?
Listed -
Effective Persuasion For AI Alignment Risk
Listed -
How would two superintelligent AIs interact, if they are unaligned with each other?
Listed -
How/When Should One Introduce AI Risk Arguments to People Unfamiliar With the Idea?
Listed -
ruling out intuitions about materially acausal things
Listed -
Spicy takes about AI policy (Clark, 2022)
Listed -
Which of these arguments for x-risk do you think we should test?
Listed -
"Normal accidents" and AI systems
Listed -
Classifying sources of AI x-risk
Listed -
Disagreements about Alignment: Why, and how, we should try to solve them
Listed -
Encultured AI Pre-planning, Part 1: Enabling New Benchmarks
Listed -
Encultured AI, Part 1 Appendix: Relevant Research Examples
Listed -
Encultured AI, Part 1: Enabling New Benchmarks
Listed -
Future Matters #4: AI timelines, AGI risk, and existential risk from climate change
Listed - Listed
-
How technical safety standards could promote TAI safety
Listed -
Interpretability/Tool-ness/Alignment/Corrigibility are not Composable
Listed -
Steganography in Chain of Thought Reasoning
Listed -
Will Superhuman AI be created?
Listed -
How I Came To Longtermism On My Own & An Outsider Perspective On EA Longtermism
Listed -
How would Logical Decision Theories address the Psychopath Button?
Listed -
Jack Clark on the realities of AI policy
Listed -
List of sources arguing against existential risk from AI
Listed -
Longtermists Should Work on AI - There is No "AI Neutral" Scenario
Listed -
Why does no one care about AI?
Listed - Listed
-
AI risks: the most convincing argument
Listed -
Announcing the Introduction to ML Safety course
Listed -
Announcing the Introduction to ML Safety Course
Listed - Listed
-
Incentives to create AI systems known to pose extinction risks
Listed -
List of sources arguing for existential risk from AI
Listed -
probability under potential hardware failure
Listed -
quantum immortality and local deaths under X-risk
Listed -
Why I Am Skeptical of AI Regulation as an X-Risk Mitigation Strategy
Listed -
$20K In Bounties for AI Safety Public Materials
Listed -
$20K in Bounties for AI Safety Public Materials
Listed -
Bridging Expected Utility Maximization and Optimization
Listed -
Counterfactuals are Confusing because of an Ontological Shift
Listed -
Rant on Problem Factorization for Alignment
Listed -
Where are the red lines for AI?
Listed - Listed