https://liv-daliberti.github.io/research/behavior-consistent-rl/ 2026-10-28T21:04:54+00:00 https://liv-daliberti.github.io/assets/research/behavior/paper-01-rollouts.png https://liv-daliberti.github.io/assets/research/behavior/paper-03-results.png https://liv-daliberti.github.io/assets/research/behavior/paper-05-temperature.png https://liv-daliberti.github.io/research/illusion-of-insight/ 2026-10-28T21:04:54+00:00 https://liv-daliberti.github.io/assets/research/insight/paper-01-aha.png https://liv-daliberti.github.io/assets/research/insight/paper-03-domains.png https://liv-daliberti.github.io/assets/research/insight/paper-04-prevalence.png https://liv-daliberti.github.io/research/rlvr-mode-collapse/ 2026-10-28T21:04:54+00:00 https://liv-daliberti.github.io/assets/research/rlvr/paper-01-training.png https://liv-daliberti.github.io/assets/research/rlvr/paper-02-modebench.png https://liv-daliberti.github.io/assets/research/rlvr/paper-07-replay.png https://liv-daliberti.github.io/assets/research/rlvr/01-graph-six-colorings.png https://liv-daliberti.github.io/assets/research/rlvr/02-same-accuracy.png https://liv-daliberti.github.io/assets/research/rlvr/03-measured-concentration.png https://liv-daliberti.github.io/assets/research/rlvr/04-feedback.png https://liv-daliberti.github.io/assets/research/rlvr/05-sampling.png