Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/4ICML 2026Oral· Social Aspects / Robustness

Position: Stop Automating Peer Review Without Rigorous Evaluation

Joachim Baumann · Jiaxin Pei · Sanmi Koyejo · Dirk Hovy

评测与基准社会与人本OpenReview

作者位次 #7/7ICML 2026Poster· Social Aspects / Fairness

Position: Beyond Sensitive Attributes, ML Fairness Should Quantify Structural Injustice via Social Determinants

Zeyu Tang · Alex John London · Atoosa Kasirzadeh · Sarah de Ramirez · Peter Spirtes · Kun Zhang · Sanmi Koyejo

社会与人本OpenReview

作者位次 #32/37ICML 2026Poster· General Machine Learning / Evaluation

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Mubashara Akhtar · Anka Reuel · Prajna Soni · Sanchit Ahuja · Pawan Sasanka Ammanamanchi · Ruchit Rawal · Vilém Zouhar · Srishti Yadav · Chenxi Whitehouse · Dayeon Ki · Jennifer Mickel · Leshem Choshen · Marek Šuppa · Jan Batzner · Jenny Chim · Jeba Sania · Yanan Long · Hossein A. Rahmani · Christina Knight · Yiyang Nan · Jyoutir Raj · Yu Fan · Shubham Singh · Subramanyam Sahoo · Eliya Habba · Usman Gohar · Siddhesh Pawar · Robert Scholz · Arjun Subramonian · Jingwei Ni · Mykel Kochenderfer · Sanmi Koyejo · Mrinmaya Sachan · Stella Biderman · Zeerak Talat · Avijit Ghosh · Irene Solaiman

评测与基准OpenReview

作者位次 #7/7ICML 2026Poster· Deep Learning / Large Language Models

Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy Verifier

Yegor Denisov-Blanch · Joshua Kazdan · Jessica Chudnovsky · Rylan Schaeffer · Sheng Guan · Soji Adeshina · Sanmi Koyejo

推理OpenReview

作者位次 #4/4ICML 2026Poster· General Machine Learning / Evaluation

Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation

Sang Truong · Yuheng Tu · Rylan Schaeffer · Sanmi Koyejo

评测与基准理论与学习动力学效率与系统OpenReview

作者位次 #7/7ICML 2026Poster· Social Aspects / Security

Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking

Nikil Selvam · Jay Baxter · Sophie Hilgard · Brad Miller · Keith Coleman · Ellen Vitercik · Sanmi Koyejo

安全检索与知识社会与人本OpenReview

作者位次 #6/12ICML 2026Oral

Position: There are futures that benchmark-driven AI cannot see

Sobhan Lotfi · Ava Iranmanesh · Lachin Naghashyar · Ali Shirali · Fateme Haredasht · Sanmi Koyejo · Phil Torr · Yong Suk Lee · Fazl Barez · Joel Lehman · Peter Norvig · Arvind Narayanan

评测与基准OpenReview

作者位次 #2/3ICML 2026Poster· Social Aspects / Alignment

Discovering Implicit Large Language Model Alignment Objectives

Edward Chen · Sanmi Koyejo · Carlos Guestrin

对齐与偏好社会与人本OpenReview

作者位次 #4/4ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Position: Multiple Definitions & Unrealistic Assumptions of Model Collapse Distract from Real World Threats

Rylan Schaeffer · Joshua Kazdan · Alvan Arulandu · Sanmi Koyejo

OpenReview

作者位次 #7/7ICML 2026Poster· Deep Learning / Large Language Models

The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning

(Andrew) Zhanke Zhou · Xiangyu Lu · Chentao Cao · Brando Miranda · Tongliang Liu · Bo Han · Sanmi Koyejo

推理强化学习与后训练OpenReview

作者位次 #34/35ICML 2026Poster

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations

Anka Reuel · Avijit Ghosh · Jenny Chim · Andrew Tran · Yanan Long · Jennifer Mickel · Usman Gohar · Srishti Yadav · Pawan Sasanka Ammanamanchi · Mowafak Allaham · Hossein A. Rahmani · Mubashara Akhtar · Felix Friedrich · Robert Scholz · Michael Riegler · Jan Batzner · Eliya Habba · Arushi Saxena · Anastassia Kornilova · Kevin Wei · Prajna Soni · Yohan Mathew · Kevin Klyman · Jeba Sania · Subramanyam Sahoo · Olivia B Bruvik · Pouya Sadeghi · Sujata Goswami · Angelina Wang · Yacine Jernite · Zeerak Talat · Stella Biderman · Mykel Kochenderfer · Sanmi Koyejo · Irene Solaiman

评测与基准社会与人本OpenReview

作者位次 #9/9ICML 2026Poster· General Machine Learning / Evaluation

AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems

Michael Hardy · Anka Reuel · Lijin Zhang · Jodi Casabianca · Sang Truong · Yash Dave · Hansol Lee · Ben Domingue · Sanmi Koyejo

评测与基准OpenReview

Sanmi Koyejo

获取完整研究档案

联系方式

2026 顶会论文

Position: Stop Automating Peer Review Without Rigorous Evaluation

Position: Beyond Sensitive Attributes, ML Fairness Should Quantify Structural Injustice via Social Determinants

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy Verifier

Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation

Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking

Position: There are futures that benchmark-driven AI cannot see

Discovering Implicit Large Language Model Alignment Objectives

Position: Multiple Definitions & Unrealistic Assumptions of Model Collapse Distract from Real World Threats

The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations

AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems

常见合作者