tracked author

Chelsea Finn

Coauthor of SPIRAL and LLM-as-a-Verifier and Stanford CS/EE faculty member. Public homepage lists IRIS lab, Physical Intelligence cofounder role, Berkeley PhD, MIT undergraduate background, and prior Google Brain/DeepMind work.

2 archived notes X: high Homepage GitHub X

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

Jul 13, 2026

LLM as a Verifier: A General Purpose Verification Framework

LLM as a Verifier 把评分 token 的概率期望、重复评估与 criteria decomposition 组合成连续 verifier，并用 Probabilistic Pivot Tournament 在接近线性的比较预算下选择多条 agent 轨迹；它在候选重排、进度代理和 RL dense reward 上显示出广泛用途，同时依赖 logits、成对上下文稳定性、人工 criteria 和较高验证推理预算。

2607.05391-llm-as-a-verifier Verifier Test-Time Scaling Reward Modeling

Jul 03, 2026

SPIRAL: Learning to Search and Aggregate

SPIRAL 从共享策略生成的 8 条 search traces 中随机抽取 4 个互异的四元集合，再为每个集合生成 4 条 aggregation traces；它用集合聚合成功率的 participation averaged advantage 更新搜索轨迹，并用同集合内中心化 reward 更新聚合轨迹，从而把 parallel search 与 model based aggregation 放进同一个最终答案 rewar...

2606.23595-spiral-learning-search-aggregate Test-Time Scaling Credit Assignment RL Algorithm