absorb.md

About guestrin

X / @guestrin
Compiled from 4 entries / v0
No wiki compiled yet. Trigger /api/compile-person/guestrin to generate.
What guestrin Recommends
reinforcement-learning-from-verifiable-rewards-rlvr-on-chainofthought-reasoning
paper
plurel
tool
selfdistillation-policy-optimization
paper
objdisco
tool
Sources (4)

Every entry that fed the multi-agent compile above. Inline citation markers in the wiki text (like [1], [2]) are not yet individually linked to specific sources — this is the full set of sources the compile considered.

  1. SDPO: Overcoming RL Credit-Assignment Bottlenecks via Self-Distillation from Rich Textual Feedbackpaper · 2026-05-13
  2. PluRel: Synthetic Data Scaling Laws Unlock Relational Foundation Model Performancepaper · 2026-05-13
  3. Obj-Disco: Uncovering Hidden LLM Alignment Objectives via Iterative Decompositionpaper · 2026-05-13
  4. Outcome-Based RL Fails to Guarantee Causal or Sufficient Reasoning in LLMspaper · 2026-05-13