arXiv subjects

Jiarui Han

Publications and source records attributed to Jiarui Han.

8 recordsLinked to original sources

arXiv2026

VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance

Visually impaired individuals (VIIs) encounter significant daily challenges due to limited access to visual information. Although Multimodal Large Language Models (MLLMs) have achieved impressive results on general vision and language tasks, their practical utility in real-world blind assistance still remains largely underexplored. To fill this gap, we introduce VIABench, a comprehensive video benchmark specifically designed to evaluate MLLMs in Visually Impaired Assistance scenarios using first-person videos recorded or shared by VIIs themselves. VIABench defines three core tasks, each targeting a distinct requirement in visual assistance. Proactive Reminder: Assesses the model's ability to interpret ongoing video content while proactively anticipating and verbally describing upcoming navigation-critical events; Visual Question Answering (VQA): Evaluates the model's capacity to answer user-posed questions about the environment or objects within the video; Vision-Guided Interaction: Tests context-aware reasoning to accomplish intentional interactions between user and environment. To ensure a robust and fair evaluation, we propose a rigorous benchmarking pipeline that supports both online (real-time) and offline settings. Our experiments demonstrate that current MLLMs still struggle to deliver comprehensive support for VIIs, especially in the Proactive Reminder task, which demands accurate anticipation and real-time responsiveness. We hope VIABench will drive future research toward developing customized MLLMs for real-world assistance, ultimately improving navigation and interaction experiences for visually impaired individuals. Code and data will be released at https://github.com/MCG-NJU/VIABench.

cs.CV↗

arXiv2026

Boundary Suppression Asymmetry in Post-trained Assistants: Over-expansion as a Controllability Cost

Post-trained language-model assistants are often optimized to avoid under-answering, encouraging complete, helpful, cautious, and proactive responses. We ask whether this optimization creates asymmetric controllability costs: when users explicitly request narrower answers, which assistant behaviors remain suppressible, and which continue to shape the response? We study this problem as boundary-suppression asymmetry. Prompt-side probes across multiple high-level response dimensions suggest a selective cost, concentrated around `too-much assistant' directions such as over-completion, extra help, and anti-underanswering. Using controlled assistant-policy variants derived from a shared base model, we find that anti-underanswering policies are harder to pull back than the baseline under matched boundary-control evaluations, while minimal-boundary variants generally avoid this anti-side upward shift in the direct boundary-control comparisons. Mechanism-oriented probes point beyond longer default outputs, pure EOS failure, uncertainty compensation, and local continuation bias, while robustness checks preserve the main anti-over-baseline ordering under shared-system and larger-scale settings. The evidence supports a mixed planning/stopping account, where content-budget overshoot and continuation persistence jointly make boundary correction harder. Overall, post-training may create direction-specific controllability costs: some helpful assistant tendencies remain easy to invoke, yet harder to locally suppress.

cs.CL↗

arXiv2026

Auditing Stance Asymmetry in Generative Explanations

Bias evaluation for language models has made substantial progress on bounded comparisons, such as overt derogation, stereotype association, or label-sensitive differences under controlled substitutions. Open-ended explanations raise a different problem: they guide interpretation by assigning responsibility, legitimacy, context, and grievance. A model can avoid hostile language while making one side structurally understandable and another personally at fault, overreacting, or less worth taking seriously. We call this stance-bearing asymmetry in generative explanations. We propose Symmetry Decomposition Evaluation (SDE), which tests paired situations with concrete group labels, structural-role rewrites, and explicit support or counter-evidence. In a controlled 32-family prototype suite, this decomposition shows that surface differences are not all alike: some weaken under structural or evidence control, while others remain as stable differences in how the model assigns blame, context, or legitimacy. Targeted case review and judge comparison suggest a broader difficulty for evaluating open-ended framing asymmetries: judge readings shift across operationalizations, and scalar scores can flatten distinctions that readers use to interpret explanatory stance. SDE therefore reframes generative bias evaluation as an audit of explanatory stance -- what stance each side receives, how it changes under decomposition, and where automatic scoring becomes unstable.

cs.CL↗

arXiv2026

Retention Consequence in Lifecycle Memory Control

Persistent memory can fail after successful admission: a premise is written, then becomes a silent assumption, and later maintenance treats it as ordinary residue to be compressed, demoted, or evicted. We study this post-admission failure as a lifecycle-control problem. Existing memory systems already perform admission, update, compression, retrieval, and eviction. Our claim is not that such systems lack maintenance, but that retention consequence is often operationalized only indirectly through validity, similarity, recency, frequency, importance, or summarization signals rather than exposed as a separate lifecycle state. We therefore treat confidence as carried-forward validity/support evidence, and introduce strength as an explicit lifecycle state for retention consequence. We operationalize this distinction in StageMem, a small staged controller whose transient, working, and durable stores expose promotion, compression, and eviction pressure points. Across controlled premise-realization, compression, pressure, and implicit-heuristic diagnostics, the experiments separate writing too little, retaining the wrong high-cue content, forgetting costly premises, and preserving everything by saturation. Explicit retention consequence, used through lifecycle settlement, provides a control surface between omission and hoarding. For the targeted post-admission failure mode, the results support a lifecycle view of persistent memory: reliability depends not only on what enters memory, but on whether admission validity and retention consequence remain available during maintenance.

cs.CL↗

arXiv2026

A quasi-monolithic localized high-order ALE finite element method for multi-scale fluid-structure interaction problems

This paper presents a quasi-monolithic localized high-order arbitrary Lagrangian-Eulerian (qMLH-ALE) finite element method for multi-scale fluid-structure interaction (FSI) in microfluidic systems. The fluid momentum, the incompressible Neo-Hookean constitutive law, and the left Cauchy-Green tensor $\mathcal{B}$ are assembled into a single implicit system, while the harmonic mesh extension is updated explicitly in a staggered manner. Isoparametric $\mathcal{P}_2$ elements provide third-order geometric approximation of curved fluid-solid interfaces, and a second-order implicit-explicit partitioned Runge-Kutta scheme delivers second-order temporal accuracy without the dissipation of backward Euler. A localized updating strategy confines the moving mesh and the deformation history to a body-fitted sub-domain coupled with a precomputed steady background flow, bridging the scale disparity between local FSI dynamics and the macroscopic microchannel geometry. The Turek-Hron FSI3 benchmark, performed at unit fluid-solid density ratio, reproduces the reference beam-tip amplitude and frequency within $3\%$, confirming stability under the strong added-mass coupling that destabilizes conventional partitioned schemes. Three-dimensional particle-focusing simulations in spiral microchannels further illustrate the framework on long-range multi-scale problems.

math.NA↗

arXiv2026

High-order DLM-ALE discretizations with robust operator preconditioning for fluid-rigid-body interaction

Motivated by the design of deterministic lateral displacement (DLD) microfluidic devices, we develop a high-order numerical framework for fluid-rigid-body interaction on fitted moving meshes. Rigid-body motion is enforced by a distributed Lagrange multiplier (DLM) formulation, while the moving fluid domain is treated by an arbitrary Lagrangian-Eulerian (ALE) mapping. In space, we use isoparametric Taylor-Hood elements to achieve high-order accuracy and to represent curved boundaries and the fluid-particle interface. In time, we employ a high-order partitioned Runge-Kutta strategy in which the mesh motion is advanced explicitly and the coupled physical fields are advanced implicitly, yielding high-order accuracy for the particle trajectory. The fully coupled system is linearized into a generalized Stokes problem subject to distributed constraints of incompressibility and rigid-body motion. We establish well-posedness of this generalized Stokes formulation at both the continuous and discrete levels, providing the stability foundation for operator preconditioning that is robust with respect to key physical and discretization parameters. Numerical experiments on representative benchmarks, including a DLD case, demonstrate high-order convergence for the fluid solution and rigid-body dynamics, as well as robust iterative convergence of the proposed preconditioners.

math.NA↗

arXiv2025

Retrieval Augmented Comic Image Generation

We present RaCig, a novel system for generating comic-style image sequences with consistent characters and expressive gestures. RaCig addresses two key challenges: (1) maintaining character identity and costume consistency across frames, and (2) producing diverse and vivid character gestures. Our approach integrates a retrieval-based character assignment module, which aligns characters in textual prompts with reference images, and a regional character injection mechanism that embeds character features into specified image regions. Experimental results demonstrate that RaCig effectively generates engaging comic narratives with coherent characters and dynamic interactions. The source code will be publicly available to support further research in this area.

cs.CV↗

arXiv2024

A Unified-Field Monolithic Fictitious Domain-Finite Element Method for Fluid-Structure-Contact Interactions and Applications to Deterministic Lateral Displacement Problems

Based upon two overlapped, body-unfitted meshes, a type of unified-field monolithic fictitious domain-finite element method (UFMFD-FEM) is developed in this paper for moving interface problems of dynamic fluid-structure interactions (FSI) accompanying with high-contrast physical coefficients across the interface and contacting collisions between the structure and fluidic channel wall when the structure is immersed in the fluid. In particular, the proposed novel numerical method consists of a monolithic, stabilized mixed finite element method within the frame of fictitious domain/immersed boundary method (IBM) for generic fluid-structure-contact interaction (FSCI) problems in the Eulerian-updated Lagrangian description, while involving the no-slip type of interface conditions on the fluid-structure interface, and the repulsive contact force on the structural surface when the immersed structure contacts the fluidic channel wall. The developed UFMFD-FEM for FSI or FSCI problems can deal with the structural motion with large rotational and translational displacements and/or large deformation in an accurate and efficient fashion, which are first validated by two benchmark FSI problems and one FSCI model problem, then by experimental results of a realistic FSCI scenario -- the microfluidic deterministic lateral displacement (DLD) problem that is applied to isolate circulating tumor cells (CTCs) from blood cells in the blood fluid through a cascaded filter DLD microchip in practice, where a particulate fluid with the pillar obstacles effect in the fluidic channel, i.e., the effects of fluid-structure interaction and structure collision, play significant roles to sort particles (cells) of different sizes with tilted pillar arrays.

math.NA↗