arXiv subjects

Jiaqi Shen

Publications and source records attributed to Jiaqi Shen.

4 recordsLinked to original sources

arXiv2026

Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind

Theory of Mind (ToM), the ability to infer others' beliefs, goals, and intentions, is a cornerstone of social intelligence. Multimodal ToM requires inferring an agent's mental state from evidence that is available to that agent, rather than from the complete episode observed by the solver. Existing LLM-based and Bayesian model-based approaches reconstruct global event traces, yet they do not explicitly distinguish objective events from agent-admissible evidence during hypothesis evaluation. Consequently, agent-inaccessible events or semantically misaligned actions and utterances may influence the inferred belief, goal, or social intention, leading to perspective leakage and source or route confusion. We formulate this limitation as an evidence-admissibility problem: evidence should contribute to a mental-state hypothesis only when it is accessible to the relevant agent, preserves its information source, and is diagnostic of the queried mental-state variable. To operationalize this principle, we propose PIP-ToM, an evidence-admissibility interface that constructs agent-specific evidence stores, aligns them with structured mental-state claims, and calibrates model-based hypothesis scores while preserving the underlying Bayesian inference process. PIP-ToM with GPT-4o outperforms existing ToM methods across MuMA-ToM, MMToM-QA, and Hi-ToM, achieving average accuracies of 92.56%, 95.00%, and 95.00%, respectively.

cs.AI↗

arXiv2026

TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering

AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds for future-round discovery toward agentic protein engineering. TadA-Bench preserves the campaign chronology and defines a fixed-data replay task: given earlier experimental rounds, models rank variants that appear only in later rounds. It provides aligned DNA, RNA, and protein views, and uses Seq2Graph, a graph-based label-unification pipeline, to reconcile noisy enrichment measurements into consistent cross-round activity labels. Random-split controls show strong interpolation, but future-round ranking and finite-budget candidate selection are much weaker. Controlled analyses suggest that evolutionary coverage is more informative than local data density, positioning TadA-Bench as a reproducible wet-lab replay substrate for future-round discovery toward agentic protein engineering; the data and code are released on Hugging Face and GitHub.

q-bio.QM↗

arXiv2021

Series expansions and direct inversion for the Heston model

Efficient sampling for the conditional time integrated variance process in the Heston stochastic volatility model is key to the simulation of the stock price based on its exact distribution. We construct a new series expansion for this integral in terms of double infinite weighted sums of particular independent random variables through a change of measure and the decomposition of squared Bessel bridges. When approximated by series truncations, this representation has exponentially decaying truncation errors. We propose feasible strategies to largely reduce the implementation of the new series to simulations of simple random variables that are independent of any model parameters. We further develop direct inversion algorithms to generate samples for such random variables based on Chebyshev polynomial approximations for their inverse distribution functions. These approximations can be used under any market conditions. Thus, we establish a strong, efficient and almost exact sampling scheme for the Heston model.

q-fin.PR↗

arXiv2019

Measurement of Apparent Magnitude and Effective Temperature with Amateur Telescopes

In the present study, we developed algorithms that are capable of measuring apparent magnitudes and the effective temperature of stars using raw images shot with amateur telescopes. The regularized Radial Basis Function (RBF) network, one of the machine learning algorithms, was employed to measure the effective temperature, and the simple function fitting method was adopted to measure the apparent magnitude. The achieved results are satisfying. After the white balance and noise cancellation process was simply calibrated, it was demonstrated that the measurements of the effective temperature had mean fraction errors at around 9%, and the measurements of the magnitudes had absolute error at nearly 0.1.

astro-ph.IM↗