Weekly Updates
Current and historical weekly readouts for the communication-efficient RLVR work.
2026-07-24Two-circuit pipeline-parallel RL at longer horizons
The exact-k PRF fast circuit completes the full long run without collapse at a strong fixed compression budget. Real W&B trajectories explain why fresh random masks survive while a reused PowerSGD Q subspace can turn ordinary RL policy movement into a directional failure.
2026-07-20Communication-efficient RLVR: the phase-one conclusion
The compressed method learns to full strength in and out of domain and matches an uncompressed run at saturation. On these datasets the collapse risk is manageable, and phase one closes with one open problem: a train and inference mismatch that compression enlarges, reads out as a rising KL, and has to be answered before this technique meets realistic asynchronous RL.
2026-07-13The two-circuit method beyond GSM8K: harder math and correct base models
On harder math the projection lever is worthless but the two-circuit correction holds; on a correct math-distilled base with 16k reasoning, both variants hold the dense line. Training only one middle block matches full-parameter RL in-domain.
2026-07-06Weight projection for two-circuit-network RLVR stability at longer K
Coherence-gated projection: GSM8K benefits, Math collapses to do-nothing at operational staleness.