I-Con: A Unifying Framework for Representation Learning
Paper • 2504.16929 • Published • 30
Theory and Representation learning
-
-
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
Paper • 2508.05305 • Published • 47 -
The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms
Paper • 2511.04217 • Published • 17 -
Large Language Models as Markov Chains
Paper • 2410.02724 • Published • 33 -
Alignment Makes Language Models Normative, Not Descriptive
Paper • 2603.17218 • Published • 46 -
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Paper • 2603.14482 • Published • 27 -
Learn2Fold: Structured Origami Generation with World Model Planning
Paper • 2603.29585 • Published • 16