190 citations · 238 across the 26 of their papers we have counts for
28 papers
Learning to Clarify Underspecified Intents Under Limited Interaction
Pranav M R, Manuel Cherep, Pattie Maes +1
AI assistants receive requests that leave out information needed for a good outcome, for example about users' preferences or goals. They must then either speculate or ask for more…
Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities
Chenming Shang, Yujin Tang, Jun Jie Ou Yang +3
The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work finds only weak pointwise s…
PRISM-BN: A Controlled Corpus and Benchmark for Text-to-Parameterized Bayesian Network Extraction
Amartya Bhattacharya, Nikhil Singh, Neeti Pokhriyal +1
Probabilistic Graphical Models (PGMs), especially Bayesian Networks (BNs), expose directed structure and probabilistic parameters, making them natural symbolic targets for neurosym…
Improving Information Extraction with Learned Queries
Omar Sharif, Soroush Vosoughi, Nikhil Singh
When information extraction fails, a natural instinct is to improve the model doing it: for example, by scaling it up or refining its reasoning. In this paper, we show that another…
How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account
Ruize Xu, Xiao Yu, Yujin Tang +2
How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-model training (next-state predi…
Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls
Manuel Cherep, Pattie Maes, Nikhil Singh
A model's behavior on a task is jointly determined by the input it receives and the prior it brings in, i.e. the distribution over stimuli it implicitly expects. Interpretability r…
OpenForgeRL: Train Harness-native Agents in Any Environment
Xiao Yu, Baolin Peng, Ruize Xu +7
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While power…
Position: Behavioral Systems Require Behavioral Tests
Manuel Cherep, Nikhil Singh, Pattie Maes
Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation meth…
RIME: Enabling Large-Scale Agentic Music Post-Production
Noah Schaffer, Nikhil Singh
Almost every piece of recorded music you have ever heard was modified before it reached you; commercial releases rarely spring fully formed from a musician's mind. Despite the prom…
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
Yujin Tang, Chenming Shang, Ruize Xu +1
Agent benchmarks for measuring memory largely study textual cases, in which information is deliberately extracted from the environment, written down, and then later retrieved. In o…
Reinforcement World Model Learning for LLM-based Agents
Xiao Yu, Baolin Peng, Ruize Xu +6
Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and ada…
Visual Persuasion: What Influences Decisions of Vision-Language Models?
Manuel Cherep, Pranav M R, Pattie Maes +1
The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisio…
A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
Manuel Cherep, Chengtian Ma, Abigail Xu +3
Environments built for people are increasingly operated by a new class of economic actors: LLM-powered software agents making decisions on our behalf. These decisions range from ou…
LLM Agents Are Hypersensitive to Nudges
Manuel Cherep, Pattie Maes, Nikhil Singh
LLMs are being set loose in complex, real-world environments involving sequential decision-making and tool use. Often, this involves making choices on behalf of human users. Howeve…
Discovering and Steering Interpretable Concepts in Large Generative Music Models
Nikhil Singh, Manuel Cherep, Pattie Maes
The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such con…
Bridging the Data Provenance Gap Across Text, Speech and Video
Shayne Longpre, Nikhil Singh, Manuel Cherep +40
Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established data…
Consent in Crisis: The Rapid Decline of the AI Data Commons
Shayne Longpre, Robert Mahari, Ariel Lee +46
General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we…
Purrfect Pitch: Exploring Musical Interval Learning through Multisensory Interfaces
Sam Chin, Cathy Mengying Fang, Nikhil Singh +3
We introduce Purrfect Pitch, a system consisting of a wearable haptic device and a custom-designed learning interface for musical ear training. We focus on the ability to identify…
Contrastive Learning from Synthetic Audio Doppelgängers
Manuel Cherep, Nikhil Singh
Learning robust audio representations currently demands extensive datasets of real-world sound recordings. By applying artificial transformations to these recordings, models can le…
Creative Text-to-Audio Generation via Synthesizer Programming
Manuel Cherep, Nikhil Singh, Jessica Shand
Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily tweaked, as they are based on large late…
Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning
Nikhil Singh, Chih-Wei Wu, Iroro Orife +1
Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual…
Human Detection of Political Speech Deepfakes across Transcripts, Audio, and Video
Matthew Groh, Aruna Sankaranarayanan, Nikhil Singh +3
Recent advances in technology for hyper-realistic visual and audio effects provoke the concern that deepfake videos of political speeches will soon be indistinguishable from authen…
A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
Iddo Drori, Sarah Zhang, Reece Shuttleworth +15
We demonstrate that a neural network pre-trained on text and fine-tuned on code solves mathematics course problems, explains solutions, and generates new questions at a human level…
Solving Probability and Statistics Problems by Program Synthesis
Leonard Tang, Elizabeth Ke, Nikhil Singh +2
We solve university level probability and statistics questions by program synthesis using OpenAI's Codex, a Transformer trained on text and fine-tuned on code. We transform course…