Aniket Rege — accepted AI-conference papers

2026

Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents

Mahesh Ramesh, Kaousheik Jayakumar, Aswinkumar Ramkumar, Pavan Thodima, Aniket Rege, Emmanouil-Vasileios Vlatakis-Gkaragkounis

ICML 2026poster

Cooperative reasoning under incomplete information remains complex for both humans and multi-agent AI, requiring agents to transcend individual logic in favor of recursive Theory-of-Mind (ToM) and strategic coordination. To investigate these challenges, we conduct a large-scale evaluation of 17 stat…

Cited by 0 Source ↗Scholar ↗

2025

CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems

Aniket Rege, Zinnia Nie, Mahesh Ramesh, Unmesh Raskar, Zhuoran Yu, Aditya Kusupati +2

ICCV 2025poster

Popular text-to-image (T2I) systems are trained on web-scraped data, which is heavily Amero and Euro-centric, underrepresenting the cultures of the Global South. To analyze these biases, we introduce CuRe, a novel and scalable benchmarking and scoring suite for cultural representativeness that lever…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment

Daiwei Chen, Yi Chen, Aniket Rege, Zhi Wang, Ramya Korlakai Vinayak

ICLR 2025poster

Foundation models trained on internet-scale data benefit from extensive alignment to human preferences before deployment. However, existing methods typically assume a homogeneous preference shared by all individuals, overlooking the diversity inherent in human values. In this work, we propose a gene…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

AdANNS: A Framework for Adaptive Semantic Search

Aniket Rege, Aditya Kusupati, Sharan Ranjit S, Alan Fan, Qingqing Cao, Sham M. Kakade +2

NeurIPS 2023poster

Web-scale search systems learn an encoder to embed a given query which is then hooked into an approximate nearest neighbor search (ANNS) pipeline to retrieve similar data points. To accurately capture tail queries and data points, learned representations typically are _rigid, high-dimensional_ vecto…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

Matryoshka Representation Learning

Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan +5

NeurIPS 2022accept

Learned representations are a central component in modern ML systems, serving a multitude of downstream tasks. When training such representations, it is often the case that computational and statistical constraints for each downstream task are unknown. In this context rigid, fixed capacity represent…

Cited by 146 Source ↗PDF ↗code ↗Scholar ↗