7 papers
Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics
Yufeng Wang, Parivesh Priye, Lu Wei +1
A world model learns to forecast how a physical system evolves from recorded trajectories, yet the systems it imitates obey physical laws that are neither fully supplied nor reliab…
-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource
Yufeng Wang, Parivesh Priye, Meeshawn Marathe +1
Reinforcement learning is increasingly used to align image generators with reward signals, and Flow-GRPO recently extended this paradigm to flow-matching models by treating the den…
Available Guardrails: Certifying Selective Prediction across ML Systems
Parivesh Priye, Yufeng Wang, Haibin Ling +1
A selective predictor acts as a safety gate: it returns an output only when the prediction appears sufficiently trustworthy. Deployments increasingly require this reliability to be…
Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models
Yufeng Wang, Parivesh Priye, Lu Wei +1
A learned simulator can reproduce its training conditions accurately yet fail in two distinct ways once those conditions change. Over long rollouts, small errors accumulate until t…
GRPO-QPS: Target-Preserving Reinforcement Learning for Quantum Posterior Sampling
Yufeng Wang, Parivesh Priye, Lu Wei +1
Bayesian quantum tomography requires efficient inference while preserving a posterior fixed by the prior and Born likelihood. Learned transport provides fast amortized samples, but…
VoiceLongMemEval: Do Assistants Remember How You Sounded?
Ramit Pahwa, Parivesh Priye, Apoorva Beedu
With the growing scale of multi-agent architectures and large language models, deployed AI assistants are increasingly tasked with reasoning over long, continuous, multi-session co…
Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use
Ramit Pahwa, Apoorva Beedu, Parivesh Priye +4
Voice assistants increasingly rely on Speech Language Models (SpeechLMs) to interpret spoken queries and execute complex tasks, yet existing benchmarks lack domain breadth, acousti…