Search posts, papers, and topics
When2Think introduces a post‑training framework that lets a large reasoning model decide per‑instance how much reasoning depth to allocate, using difficulty‑aware reward shaping (IDAC) and verifier rewards. It cuts token usage by ~28% while boosting Pass@3 by 10% on AIME24 and reaches 40% Pass@3 on AIME25, outperforming compression and routing baselines.
The paper isolates the contribution of privileged teacher information in on‑policy self‑distillation (OPSD) using a 5k‑problem math suite. Reference‑free distillation explains most gains, with only modest extra benefit from full solution traces.
This paper introduces Calibrated On-Policy Distillation (Cal-OPD), a method to improve knowledge distillation by filtering out the teacher model's inherent deviations from the learning signal. Cal-OPD estimates and removes the teacher's self-deviation, leading to better student performance on mathematical reasoning tasks.
Register tokens are fixed‑position embeddings that store a compact hidden state across diffusion‑based language model generation chunks, enabling bounded‑state reasoning without retaining all prior text. Post‑training on LLaDA and Dream shows up to +8.5 math and +19.5 code benchmark points versus plain text carry, and RL fine‑tuning further improves long‑horizon tasks.
The paper shows that when specialist LLMs are trained only on QA pairs (no explicit reasoning supervision), their optimization implicitly selects a latent distribution of reasoning trajectories. By treating the distilled student as an agnostic probe—since it inherits only the sampled trajectories—the authors empirically demonstrate a strong correlation (across 27 specialist‑student pairs) between…
Lightning Weave is a post‑training framework that composes specialist capabilities from separate models into one student via on‑policy distillation, improving both accuracy and token efficiency on math and code benchmarks.
The paper builds compositional rule‑induction task families and generates isomorphic variants to probe systematicity in reasoning models. Experiments reveal that models frequently fail on equivalent variants despite solving the original task, indicating a lack of systematic reasoning.
