Search papers, labs, and topics across Lattice.
Affiliation:
5
0
6
0
LLM agents can learn from past mistakes by retroactively revising their internal "harness" state, significantly improving continual learning performance.
Task-oriented multi-agent systems can achieve unprecedented performance by leveraging specialized roles and subtasks, revealing the power of structured collaboration in AI.
Sparse user histories can be transformed into rich personalization insights by leveraging collaborative signals from behaviorally similar peers.
Learning insertion order in sequence generation can drastically improve modeling quality and generalization, challenging the dominance of fixed-canvas methods.
By mapping permutations to a continuous space of "soft ranks," this new diffusion approach makes learning permutation distributions far more tractable, especially for long sequences.
