Learning to Clarify Underspecified Intents Under Limited Interaction
Pranav M R, equal contribution, Manuel Cherep, equal contribution, Pattie Maes, Nikhil Singh
arXiv preprint arXiv:2610.04719
Publications
2026
17 publications so far
Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls
Manuel Cherep, Pattie Maes, Nikhil Singh
arXiv preprint arXiv:2608.27727
Dual-Contrastive Sparse Autoencoders Reveal Features of Musical Interpretation
Jan Chen, equal contribution, Manuel Cherep, equal contribution, Pattie Maes, Nikhil Singh
NeurIPS 2026
Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities
Chenming Shang, Yujin Tang, Jun Jie Ou Yang, Ruize Xu, Adam Breuer, equal contribution, Nikhil Singh, equal contribution
NeurIPS 2026
Reinforcement World Model Learning for LLM-based Agents
Xiao Yu, Baolin Peng, Ruize Xu, Yelong Shen, Pengcheng He, Suman Nath, Nikhil Singh, Jiangfeng Gao, Zhou Yu
NeurIPS 2026
How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account
Ruize Xu, Xiao Yu, Yujin Tang, Chenming Shang, Nikhil Singh
EMNLP 2026 Findings
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
Yujin Tang, Chenming Shang, Ruize Xu, Nikhil Singh
EMNLP 2026
Improving Information Extraction with Learned Queries
Omar Sharif, Soroush Vosoughi, Nikhil Singh
EMNLP 2026 Findings
RIME: Enabling Large-Scale Agentic Music Post-Production
Noah Schaffer, Nikhil Singh
ICML 2026 Workshop on Machine Learning for Audio
OpenForgeRL: Train Harness-native Agents in Any Environment
Xiao Yu, Baolin Peng, Ruize Xu, Hao Zou, Qianhui Wu, Hao Cheng, Wenlin Yao, Nikhil Singh, Zhou Yu, Jianfeng Gao
arXiv preprint arXiv:2607.21557
AI Agents are Sensitive to Nudges
Manuel Cherep, Pattie Maes, Nikhil Singh
Proceedings of the National Academy of Sciences
Visual Persuasion: What Influences Decisions of Vision-Language Models?
Manuel Cherep, equal contribution, Pranav M R, equal contribution, Pattie Maes, Nikhil Singh
International Conference on Machine Learning
Behavioral Systems Require Behavioral Tests
Manuel Cherep, equal contribution, Nikhil Singh, equal contribution, Pattie Maes
International Conference on Machine Learning (Position Track)
If Only My CGM Could Speak: A Privacy-Preserving Agent for Question Answering over Continuous Glucose Data
Yanjun Cui, Ali Emami, Temiloluwa Prioleau, equal contribution, Nikhil Singh, equal contribution
ACL Findings
Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design
Omar Sharif, Eftekhar Hossain, Nikhil Singh, Patrick Ng
AACL-IJCNLP 2026 Findings
A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
Manuel Cherep, Chengtian Ma, Abigail Xu, Maya Shaked, Pattie Maes, Nikhil Singh
International Conference on Learning Representations
Discovering and Steering Interpretable Concepts in Large Generative Music Models
Nikhil Singh, equal contribution, Manuel Cherep, equal contribution, Pattie Maes
International Conference on Learning Representations
2025
2 publications
Contrastive Learning from Synthetic Audio Doppelgangers
Manuel Cherep, equal contribution, Nikhil Singh, equal contribution
International Conference on Learning Representations
Bridging the Data Provenance Gap Across Text, Speech and Video
Shayne Longpre, Nikhil Singh, Manuel Cherep, Kushagra Tiwary, Joanna Materzynska, William Brannon, Robert Mahari, Manan Dey, Mohammed Hamdy, Nayan Saxena, Ahmad Anis, Emad Alghamdi, Vu Minh Chien, Naana Obeng-Marnu, Da Yin, Kun Qian, Yizhi Li, Minnie Liang, An Dinh, Shrestha Mohanty, Deividas Mataciunas, Tobin South, Jianguo Zhang, Ariel N Lee, Campbell S Lund, Christopher Klamm, Damien Sileo, Diganta Misra, Enrico Shippole, Kevin Klyman, Lester JV Miranda, Niklas Muennighoff, Seonghyeon Ye, Seungone Kim, Vipul Gupta, Vivek Sharma, Xuhui Zhou, Caiming Xiong, Luis Villa, Stella Biderman, Alex Pentland, Sara Hooker, Jad Kabbara
International Conference on Learning Representations