arXiv subjects

Tianhao Yu

Publications and source records attributed to Tianhao Yu.

10 recordsLinked to original sources

arXiv2026

xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems

Large language models (LLMs) are increasingly used for everyday assistance, yet existing benchmarks only partially reflect the requests users naturally make in practice. Real-world requests are often open-ended, casually specified, and context-dependent, requiring models not only to follow explicit instructions but also to infer unstated needs from user background and situational context. We introduce xDailyBench, a benchmark of 248 carefully curated tasks spanning 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities. The tasks are grounded in requests that users have actually completed or genuinely intended to accomplish with AI, and are evaluated with fine-grained binary rubrics covering both explicit and implicit requirements. We evaluate 11 frontier models under standardized agentic settings. The best models achieve a task-level score of 75.6\%, while all models perform substantially worse on implicit than explicit requirements, with gaps no less than 9 percentage points. These results reveal implicit requirement inference as a persistent bottleneck for reliably satisfying real-world everyday user needs.

cs.AI↗

arXiv2026

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows

Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains. We translate these workflows into complete deliverable-oriented tasks and evaluate them with fine-grained rubrics capturing their complex requirements. Across representative models evaluated under a unified agent harness, even the strongest model successfully completes only approximately 30\% of StartupBench, despite making substantial partial progress on many tasks. Further analysis identifies aspects like complex instruction following and domain-specific expertise as major sources of failure. Our results reveal that many market-validated workflows remain beyond the reliable capabilities of current general-purpose agents, establishing StartupBench as an empirical measure of progress toward E2E completions of real-world user tasks.

cs.AI↗

arXiv2026

Towards Estimating Normal and Shear Interface Pressures in Prosthetic Sockets via Least Squares and Mechanics Modeling

Prosthetic socket fitting remains largely manual and iterative, and objective fit metrics are still limited. Part of the challenge is the lack of long-term real-life pressure data at the residual limb--socket interface. Traditional pressure sensors are prone to drift over time, and capture only normal pressures at sparse locations within the socket, missing a critical component for biomechanical analysis: shear. Although some sensors can report both normal and shear interface stresses, these components are often difficult to decouple because of measurement crosstalk. One potential path forward is to develop models that can augment available measurements. This work introduces a testbed to evaluate model performance under sparse pressure sensing using two complementary validation signals: (i) the global wrench (\ie, total forces and moments expressed in an orthonormal frame) transmitted through the socket, by an artificial residual-limb, and (ii) local interface loads (\ie, decoupled normal and shear pressure components in a right-hand-rule orthogonal frame that lives in each instrumented location) measured by sparse sensing clusters, each composed of four capacitance-sensing channels. Rather than presenting full-field pressure estimates, the focus is on an analysis sequence that quantifies how well candidate mechanical models explain both global and local measurements under controlled conditions. A quasi-static spring--mass contact model is evaluated, and its parameters are identified via a two-stage convex least-squares problem. Validation under static loading shows that estimating constant bias terms reduces steady offsets in the wrench channels and improves agreement with local measurements. A Pareto-front sensitivity analysis further illustrates how the trade-off between global and local objectives changes when bias terms are included.

cs.RO↗

arXiv2025

Model Falsification for Predicting Dynamical Responses of Uncertain Structural Systems

Accurate prediction of dynamical response of structural system depends on the correct modeling of that system. However, modeling becomes increasingly challenging when there are many candidate models available to describe the system behavior. Furthermore, uncertainties can be present even for the parameters of these model classes. The plausibility of each input-output model class of the structures with uncertain components can be determined by a Bayesian approach from measured dynamic responses to one or more input records; predictions of the structural system response to alternate input records can then be made. However, this approach may require many model simulations, even though most of those model classes are quite implausible. An approach is proposed herein to use a bound, computed from the false discovery rate, on the likelihood of measured data to falsify models considering uncertainties in the passive control devices that do not reproduce the measured data to sufficient accuracy. Response prediction is then performed using the unfalsified models in an approximate Bayesian sense by assigning weights, computed from the likelihoods, only to the unfalsified models approach incurring only a fraction of the computational cost of the standard Bayesian approach. The proposed approach for response prediction is illustrated using three structural examples: an earthquake-excited four--degree-of-freedom building model with a hysteretic isolation layer; a 1623--degree-of-freedom three-dimensional building model, with tuned mass dampers attached to its roof, subjected to wind loads; and a full-scale four-story base-isolated building tested on world's largest shake table in Japan's E-Defense lab. The results exhibit accurate response predictions and significant computational savings, thereby illustrating the potential of the proposed method.

stat.AP↗

arXiv2025

On Directed Graphs With Real Laplacian Spectra

It is reported that dynamical systems over digraphs have superior performance in terms of system damping and tolerance to time delays if the underlying graph Laplacian has a purely real spectrum. This paper investigates the topological conditions under which digraphs possess real or complex Laplacian spectra. We derive sufficient conditions for digraphs, which possibly contain self-loops and negative-weighted edges, to have real Laplacian spectra. The established conditions generally imply that a real Laplacian spectrum is linked to the absence of the so-called digon sign-asymmetric interactions and non-strong connectivity in any subgraph of the digraph. Then, two classes of digraphs with complex Laplacian spectra are identified, which imply that the occurrence of directed cycles is a major factor to cause complex Laplacian eigenvalues. Moreover, we extend our analysis to multilayer digraphs, where strategies for preserving real/complex spectra from graph interconnection are proposed. Numerical experiments demonstrate that the obtained results can effectively guide the redesign of digraph topologies for a better performance.

math.OC↗

arXiv2025

Unraveling the Molecular Structure of Lipid Nanoparticles through in-silico Self-Assembly for Rational Delivery Design

Lipid nanoparticles (LNPs) are a leading platform in the delivery of RNA-based therapeutics, playing a pivotal role in the clinical success of mRNA vaccines and other nucleic acid drugs. Their performance in RNA encapsulation and delivery is critically governed by the molecular structure of ionizable lipids and the overall formulation composition. However, mechanistic insight into how these factors govern LNP architecture and function remains limited, primarily owing to the challenges of capturing nanoscale assembly and organization using experimental techniques. Here, we employ coarse-grained molecular dynamics simulations to systematically investigate how ionizable lipid chemistry influences LNP self-assembly, internal organization, and surface properties. We further explore the effects of formulation ratios and pH-dependent deprotonation on both the internal structure and surface morphology of LNPs. Leveraging these insights, we demonstrate how in silico structural characteristics can inform the rational design of novel ionizable lipids and optimization of formulation ratios, supported with experimental validations. Our findings offer a molecular-level understanding of LNP assembly dynamics and architecture, thereby establishing a computational framework linking lipid chemistry and LNP formulation to the structure and performance of LNP, to advance the rational design of novel LNP delivery systems.

cond-mat.soft↗

arXiv2024

Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?

The evaluation of the problem-solving capability under incomplete information scenarios of Large Language Models (LLMs) is increasingly important, encompassing capabilities such as questioning, knowledge search, error detection, and path planning. Current research mainly focus on LLMs' problem-solving capability such as ``Twenty Questions''. However, these kinds of games do not require recognizing misleading cues which are necessary in the incomplete information scenario. Moreover, the existing game such as ``Who is undercover'' are highly subjective, making it challenging for evaluation. Therefore, in this paper, we introduce a novel game named BrainKing based on the ``Who is undercover'' and ``Twenty Questions'' for evaluating LLM capabilities under incomplete information scenarios. It requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers. By setting up easy, medium, and hard difficulty modes, we comprehensively assess the performance of LLMs across various aspects. Our results reveal the capabilities and limitations of LLMs in BrainKing, providing significant insights of LLM problem-solving levels.

cs.CL↗

arXiv2024

LipidBERT: A Lipid Language Model Pre-trained on METiS de novo Lipid Library

In this study, we generate and maintain a database of 10 million virtual lipids through METiS's in-house de novo lipid generation algorithms and lipid virtual screening techniques. These virtual lipids serve as a corpus for pre-training, lipid representation learning, and downstream task knowledge transfer, culminating in state-of-the-art LNP property prediction performance. We propose LipidBERT, a BERT-like model pre-trained with the Masked Language Model (MLM) and various secondary tasks. Additionally, we compare the performance of embeddings generated by LipidBERT and PhatGPT, our GPT-like lipid generation model, on downstream tasks. The proposed bilingual LipidBERT model operates in two languages: the language of ionizable lipid pre-training, using in-house dry-lab lipid structures, and the language of LNP fine-tuning, utilizing in-house LNP wet-lab data. This dual capability positions LipidBERT as a key AI-based filter for future screening tasks, including new versions of METiS de novo lipid libraries and, more importantly, candidates for in vivo testing for orgran-targeting LNPs. To the best of our knowledge, this is the first successful demonstration of the capability of a pre-trained language model on virtual lipids and its effectiveness in downstream tasks using web-lab data. This work showcases the clever utilization of METiS's in-house de novo lipid library as well as the power of dry-wet lab integration.

cs.CL↗

arXiv2021

Mechanisms behind high CO2/CH4 selectivity using ZIF-8 metal organic frameworks with encapsulated ionic liquids: a computational study

CO2/CH4 separation using ionic liquids (ILs) encapsulated metal-organic frameworks (MOFs), especially ZIF-8, has shown promise as a new technique for separating CO2 from CH4. However, the mechanisms behind the high CO2/CH4 selectivity of the method remains indistinct. Here we report the progress of understanding the mechanisms from examining the ZIF-8 aperture configuration variation using DFT and MD simulations. The results indicate that the pristine aperture configuration exhibits the best separation performance, and the addition of ILs prevents the apertures from large swing (i.e. configuration variation). Subsequently, the effect of IL viscosity on the layout variation was investigated. MD simulations also show that the pristine aperture configuration is more stabilized by ILs with large viscosity (0-87Cp). Further increase of IL viscosity above 87Cp did not result in noticeable changes in the aperture stability.

physics.chem-ph↗

arXiv2021

A molecular dynamics simulation study on the frustrated Lewis pairs in ionic liquids

Steric hindered frustrated Lewis pairs (FLPs) have been shown to activate hydrogen molecules, and their reactivity is strongly determined by the geometric parameters of the Lewis acid s and bases. A recent experimental study showed that ionic liquids (ILs) could largely improve the effective configuration of FLPs. However, the detailed mechanistic profile is still unclear. Herein, we performed a molecular dynamics (MD) simulations, aimi ng to reveal the effects of ILs on the structures of FLPs, and to present a rule for selecting more efficient reaction media. For this purpose, mixture systems were adopt consisting of the ILs [Cnmim][NTf2] (n= 6, 10, 14), and the typical FLP (tBu)3P/B(C6F5)3 . Radial distribution function (RDF) results show that toluene competes with (tBu)3P to interact with B(C6F5)3 , resulting in a relatively low effective (tBu)3P/B(C6F5)3 complex. [Cnmim][NTf2] is more intended to form a solvated shell surrounding the (tBu)3P/B(C6F5)3 , which increases the amount of effective FLPs. Spatial distribution function (SDF) results show that toluene formed a continuum solvation shell, which hinders the interactions of (tBu)3P and B(C6F5)3 , while [Cnmim][NTf2] leave a relatively large empty space, which is accessible by (tBu3)P molecules, resulting in a higher probability of Lewis acids and bases interactions. Lastly, we find that the longer alkyl chain length of[Cnmim] cations, the higher probability of effective FLPs.

physics.chem-ph↗