Papers with Code paper Oct 6

Sherpa: Teaching LLMs to Teach Adaptively

Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approaches to t...

Papers with Code paper Oct 6

PhysEvo: Astra Can Act, Let It

Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive self-impro...

Papers with Code paper Oct 6

On-Policy Distillation with Negative-Policy Rollouts

On-policy distillation (OPD) has been widely studied as a post-training method in which a student model obtains token-level supervision from a stronger teacher on its own rollouts....

Papers with Code paper Oct 6

WorldSonus: Bringing Sound to Worlds

Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bringing sound to world models po...

Papers with Code paper Oct 6

Recurrent Looped Transformer

State tracking requires an update at every input, but the depth a Transformer applies to each token is fixed regardless of sequence length. We introduce the Recurrent Looped Transf...

Papers with Code paper Oct 6

On KL-Regularized Policy Optimization

Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the...