Field notes
2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
7 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on self-distillation
7 notes
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
SkillForge is a framework that helps large language model-based agents improve their ability to resolve software issues in specific repositories. It does this by proactively acquiring project-specific knowledge from…
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Researchers propose a new method called Observation-Calibrated Self-Distillation (OCSD) to train large language models in reinforcement learning. OCSD addresses a confounding issue in previous methods by comparing two…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
The paper introduces a new method called On-Policy Self-Distillation with Visual Modality Balance (OPD-V) to improve the visual reasoning of multimodal large language models. The authors argue that previous methods…
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
The study investigates self-distillation (SD), a method used in reinforcement learning for efficient teaching by a 'teacher' using privileged information about the answer. The research finds that while SD reproduces…
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
The research investigates self-distillation (SD), a method used in reinforcement learning with verifiable rewards, where a teacher conditioned on privileged information supplies supervision to a student. The study…
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
The authors propose a framework called TurnSight for Tool-Integrated Reasoning (TIR). This framework aims to improve fine-grained credit assignment in long-horizon TIR scenarios by addressing the limitations of…
Enhancing Rubric-based RL via Self-Distillation
The paper proposes a new method called Criterion-Distilled Policy Optimization (CriPO) to address two limitations in Rubric-based Reinforcement Learning (RL). The first limitation, Limited Exploration, occurs when…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
