3

Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time

Reducing verbatim loops during generation by penalizing tokens that continue a previously seen sequence.

XTC: Head-Aware Sampling by Excluding Top Choices

Encouraging varied text by occasionally excluding dominant choices when several plausible next tokens are available.

HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning

Learning graph representations at multiple scales through latent prediction over coarse and fine partitions.

S-JEPA: Soft Clustering Anchors for Self-Supervised Speech Representation Learning

Learning speech representations with soft predictive targets, preserving acoustic ambiguity while avoiding repeated offline reclustering.

On Training in Imagination

Training agents in learned world models: how model errors and rollout budgets shape policy learning.

Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces

Using generative latent spaces to study adversarial transfer and the robustness of vision models.

AI Must Embrace Specialization via Superhuman Adaptable Intelligence

A perspective on specialization, adaptation, and how to define useful goals for AI research.

Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition

We study a mobile AI agent that separates planning, execution, verification, and reflection to improve reliability on AndroidWorld tasks.

UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers

Making pretrained transformer attention sensitive to uncertainty during inference.

Beyond the Loss Curve: Scaling Laws, Active Learning, and the Limits of Learning from Exact Posteriors

Using exact posterior probabilities to separate reducible model error from uncertainty in the data.