http://yiziruifang.com/tags/bayesian-inference/Bayesian InferenceHugo Blox Builder (https://hugoblox.com)en-usSat, 31 Jan 2026 00:00:00 +0000http://yiziruifang.com/media/icon_hu7729264130191091259.pnghttp://yiziruifang.com/tags/bayesian-inference/http://yiziruifang.com/project/siftom/Sat, 31 Jan 2026 00:00:00 +0000http://yiziruifang.com/project/siftom/<h2 id="hiring-manager-view">Hiring-manager view</h2> <p>This project, formerly listed as SIFToM, connects language, perception, and decision-making in embodied AI. It is a useful signal for applied scientist roles that require modeling user intent, reasoning under uncertainty, and evaluating behavior in simulated and real-world settings.</p> <h2 id="scientific-problem">Scientific problem</h2> <p>Robots need to infer intended goals from spoken instructions even when the acoustic signal is noisy or ambiguous. The challenge is to model both what the speaker said and what a human listener likely perceived.</p> <h2 id="method">Method</h2> <ul> <li>Contributed to a theory-of-mind formulation for pragmatic spoken instruction following.</li> <li>Used vision-language modeling and model-based mental inference to infer robot goals from speech-related evidence and task context.</li> <li>Evaluated the approach on simulated and real-world embodied task data.</li> </ul> <h2 id="evaluation-signal">Evaluation signal</h2> <p>The central evaluation question is whether the model improves goal inference and instruction-following robustness when speech, perception, and intent are uncertain.</p>