arXiv subjects

Yu-Hsiang Liu

Publications and source records attributed to Yu-Hsiang Liu.

5 recordsLinked to original sources

arXiv2026

EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User Supports

VLMs are increasingly positioned as daily assistants that perceive first-person environments, follow user dialogue, and decide how to help. Existing egocentric benchmarks mainly evaluate visual understanding in isolation, leaving open whether models can arbitrate between visual evidence and user-provided language when the two are helpful, irrelevant, or conflicting. We introduce EgoArgus, a human-annotated dataset for evaluating egocentric assistants on understanding and decision tasks in five dialogue-video daily scenarios. Our results demonstrate that it is still challenging for current VLMs as reliable egocentric assistants, which requires identifying which modality is trustworthy and deciding when intervention is warranted. Deeper analysis also shows that existing modality bias mitigation methods are quite restricted to enhance performance, providing insights to aid practioners into the deployment of current VLMs as daily assistants.

cs.CL↗

arXiv2026

VISTA: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios

Evaluating whether AI agents can proactively assist humans in daily activities, ranging from routine household tasks to urgent safety-critical situations, requires diverse visual data. However, collecting such scenarios in the real world is often difficult, costly, or unsafe, and simulation environments often lack the social commonsense needed to simulate the consequences of different actions. In this work, we present VISTA, a controllable platform that uses a user-provided scenario seed, defined as a short natural-language description of the intended assistance situation, to generate editable plans, egocentric videos, and an auditable review trail. VISTA structures scenario intent around three interaction modes, including reactive, explicit proactive, and implicit proactive, and two consequence families, including safety-critical and everyday inconvenience, with no-assistance cases as controls. Its six-stage pipeline exposes the design brief, timed event script, first-frame plan, motion plan, and video plan, allowing users to revise each artifact in natural language before explicitly authorizing media generation. A human evaluation shows that videos retained by the complete VISTA workflow align more closely with their scenario seeds than outputs from two one-pass baselines. VISTA thereby makes targeted egocentric scenario generation inspectable, revisable, and empirically auditable.

cs.CL↗

arXiv2026

OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference

Benchmarking large language models (LLMs) is critical for understanding their capabilities, limitations, and robustness. In addition to interface artifacts, prior studies have shown that LLM decisions can be influenced by directive signals such as social cues, framing, and instructions. In this work, we introduce option injection, a benchmarking approach that augments the multiple-choice question answering (MCQA) interface with an additional option containing a misleading directive, leveraging standardized choice structure and scalable evaluation. We construct OI-Bench, a benchmark of 3,000 questions spanning knowledge, reasoning, and commonsense tasks, with 16 directive types covering social compliance, bonus framing, threat framing, and instructional interference. This setting combines manipulation of the choice interface with directive-based interference, enabling systematic assessment of model susceptibility. We evaluate 12 LLMs to analyze attack success rates, behavioral responses, and further investigate mitigation strategies ranging from inference-time prompting to post-training alignment. Experimental results reveal substantial vulnerabilities and heterogeneous robustness across models. OI-Bench is expected to support more systematic evaluation of LLM robustness to directive interference within choice-based interfaces.

cs.CL↗

arXiv2020

Donaldson-Thomas theory of quantum Fermat quintic threefolds I

In this paper, we study non-commutative projective schemes whose associated non-commutative graded algebras are finite over their centers. We study their moduli spaces of stable sheaves, and construct a symmetric obstruction theory in the Calabi-Yau-3 case. This allows us to define Donaldson-Thomas type invariants. We also discuss the simplest examples, called quantum Fermat quintic threefolds.

math.AG↗

arXiv2020

Donaldson-Thomas theory of quantum Fermat quintic threefolds II

This paper is a continuation of author's previous work arXiv:1911.07949, where we defined Donaldson-Thomas invariants of quantum Fermat threefolds. In this paper, we study the generic quantum Fermat threefold. We give explicit local models for Hilbert schemes of points as quivers with potential, and compute degree zero Donaldson-Thomas invariants. The result is expressed in terms of certain colored plane partitions.

math.AG↗