黑料正能量

黑料正能量
AI Measurement Science & Engineering (AIMSEC)

黑料正能量-NIST Cooperative Research Center

黑料正能量-NIST Cooperative Research Center  ›  AI Measurement Science & Engineering (AIMSEC)  ›  Media & Publications

Media

Two Heads Are Better Than One: How to Operationalize AI with People, Processes, and Trust

 

Elevate Podcast Episode 8: Zico Kolter, Head of 黑料正能量 ML and Board at OpenAI

 

Is It Time to Rethink LLM Pre-Training? [Aditi Raghunathan] - 747

黑料正能量 Experts: What If We Could Create a Trusted AI Ecosystem?

Publications

Explore publications from AIMSEC-affiliated faculty below.

2026

Table of AIMSEC faculty publications from 2026
Affiliated Faculty 

Title and Citation

Date
Hong Shen M Li, W Bickersteth, N Tang, P Kapoor, K Win, P Zhong, H ShenWhat People See (and Miss) 黑料正能量 Generative AI Risks: Perceptions of Failures, Risks, and Who Should Address Them
arXiv:2604.22654		 April 2026
Hong Shen A Qian, S Chandhiramowuli, L Dabbish, H ShenHuman Expertise for AI Red-Teaming and Scalable Evaluation
CHI EA ’26, April 13–17, 2026, Barcelona, Spain		 April 2026
Ramayya Krishnan, Rema Padman Y Li, L Zhang, T Jiang, R Krishnan, R PadmanThe Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
arXiv:2603.29025

 March 2026
Yubo Li, Ramayya Krishnan, Rema Padman

Y Li, R Krishnan, R Padman. (2026)
When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models
arXiv:2603.21460

 March 2026
Rema Padman, Ramayya Krishnan

YLT Zhou, X Shen, Y Miao, R Krishnan. (2026)
Confidence as Control: A Survey of Confidence Utilization in Large Language Models

Prior surveys provide strong foundations on confidence estimation, uncertainty quantification, hallucination analysis, and abstention. Our contribution is to connect these strands through a unified control perspective: confidence-related signals are not only quantities to be estimated, but instruments for governing behavior across the full LLM lifecycle.

 March 2026
Ramayya Krishnan, Rema Padman


Y Li, R Krishnan, R Padman. (2026)
Consistency of Large Reasoning Models Under Multi-Turn Attacks. 
arXiv:2602.13093, 2026

 February 2026
Ramayya Krishnan, Rema Padman


J Liu, Y Jiang, R Krishnan, R Padman, Y Zhang, J Bian. (2026)
Closing Reasoning Gaps in Clinical Agents with Differential Reasoning Learning
arXiv:2602.09945.

 February 2026
Eli Ben-Michael

V Lin, LP Morency, E Ben-Michael. (2025)
Omitted Variable Bias in Language Models Under Distribution Shift 
arXiv:2602.16784.

February 2026

2025

Table of AIMSEC faculty publications from 2025
Affiliated Faculty 

Title and Citation

Date
Ramayya Krishnan


Digalakis Jr, V., Krishnan, R., Fernandez, G. M., & Orfanoudaki, A. (2025). ML Compass: Navigating Capability, Cost, and Compliance Trade-offs in AI Model Deployment.
arXiv preprint arXiv:2512.23487.

29 Dec 2025
Hoda Heidari


RM Kim, B Kuehnert, S Lazar, R Singh, H Heidari. (2025)
The AI Power Disparity Index: Toward a Compound Measure of AI Actors’ Power to Shape the AI Ecosystem
Proceedings of the Eighth AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025)

October 2025
Hoda Heidari

 V Keswani, C Cousins, B Nguyen, H Heidari. (2025)
Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback
arXiv.org:2511.10032.

October 2025
Ramayya Krishnan, Rema Padman


R Krishnan, R Padman. (2025)
Time-to-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
arXiv.org:2510.02712.

 October 2025
Ramayya Krishnan


Steven M. Miller
On 24 September 2024, the US National Institute of Standards and Technology (NIST) announced they awarded $6 million to 黑料正能量 to establish the 黑料正能量/NIST AI Measurement Science & Engineering Cooperative Research Center (AIMSEC) https://www.nist.gov/news-events/news/2024/09/nist-awards-6-millioncarnegie-mellon-university-establish-ai-cooperative. 黑料正能量’s Professor Ramayya Krishnan serves as the lead research coordinator for this joint 黑料正能量/NIST research effort /news/stories/archives/2024/september/nistawards-6m-to-carnegie-mellon-university-to-establish-ai-cooperative-research-center.

September 2025
Ramayya Krishnan


Charuvilparambil Titus, Nikhil George and Krishnan, Ramayya and Telang, Rahul, From Posting to Prediction: Building Validated Workforce Analytics
(November 05, 2024). Available at SSRN: https://ssrn.com/abstract=4906323

June 2025

Past Webinars

Webinar recordings will be available here soon. Stay tuned for upcoming sessions and past event archives.

REGISTER FOR UPCOMING WEBINARS 

VIEW PAST EVENTS