arXiv subjects

Wenshuo Zhang

Publications and source records attributed to Wenshuo Zhang.

6 recordsLinked to original sources

arXiv2026

Sonic Stage: Auto-Generating Interactive Spatial Soundscapes to Facilitate Dialogue Video Comprehension for Blind Viewers

Audio description (AD) makes film and television accessible to blind and low-vision (BLV) audiences by narrating characters' actions. However, in scenes with lots of dialogue, AD often omits important actions because it is constrained not to overlap with speech. It is not yet known how to convey characters' actions during dialogue. We present Sonic Stage, a system that transforms dialogue videos into interactive spatial soundscapes, enabling BLV audiences to intuitively understand characters' actions and movements through immersive auditory cues. Sonic Stage conveys essential visual information during dialogue through three auditory techniques: (1) spatialized dialogue to represent spatial layout, (2) diegetic sound to convey character actions, and (3) interactive descriptions to provide context-specific visual details. Evaluation with 12 BLV viewers showed that Sonic Stage significantly improved video comprehension, spatial presence, and narrative engagement. We highlight opportunities for enhancing video accessibility across diverse genres through immersive, interactive audio representations.

cs.HC↗

arXiv2026

Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants

AI-assisted coding increasingly translates informal user intent into executable software, yet coding requests often contain ambiguities that recur in user-specific ways across tasks and sessions. Existing disambiguation methods typically address each ambiguous request in isolation within the current coding session, often through eliciting additional clarification. However, whether resolved session history from the same user can serve as memory for resolving recurring personalized ambiguity in a newly opened session remains underexplored. We formulate personalized ambiguity adaptation as a new task: given a user's previously resolved coding sessions and a new ambiguous request, an assistant should identify the recurring ambiguity pattern, produce the intended executable solution, and minimize clarification. To benchmark this task, we introduce CAPA, which characterizes personalized coding ambiguity through six mechanisms and injects these mechanisms into unambiguous executable tasks using a controlled three-stage generation pipeline. CAPA contains 600 coding sessions across 60 balanced user--ambiguity cells, including 300 held-out evaluation sessions. We evaluate 12 recent LLMs under no-history and same-user-history conditions using executable success, first-turn success, and turns-to-completion. Our analyses examine task difficulty, user identity, and memory-based history use, and we further propose same-user history gating as a lightweight inference-time method. CAPA provides a foundation for developing long-term coding assistants that better align generated code with user intent while reducing repeated clarification.

cs.AI↗

arXiv2025

NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification

Conversational LLMs have been widely adopted by domain users with limited programming experience to solve domain problems. However, these users often face misalignment between their intent and generated code, resulting in frustration and rounds of clarification. This work first investigates the cause of this misalignment, which dues to bidirectional ambiguity: both user intents and coding tasks are inherently nonlinear, yet must be expressed and interpreted through linear prompts and code sequences. To address this, we propose direct intent-task matching, a new human-LLM interaction paradigm that externalizes and enables direct manipulation of the LLM understanding, i.e., the coding tasks and their relationships inferred by the LLM prior to code generation. As a proof-of-concept, this paradigm is then implemented in NeuroSync, which employs a knowledge distillation pipeline to extract LLM understanding, user intents, and their mappings, and enhances the alignment by allowing users to intuitively inspect and edit them via visualizations. We evaluate the algorithmic components of NeuroSync via technical experiments, and assess its overall usability and effectiveness via a user study (N=12). The results show that it enhances intent-task alignment, lowers cognitive effort, and improves coding efficiency.

cs.HC↗

arXiv2025

Branch Explorer: Leveraging Branching Narratives to Support Interactive 360° Video Viewing for Blind and Low Vision Users

360° videos enable users to freely choose their viewing paths, but blind and low vision (BLV) users are often excluded from this interactive experience. To bridge this gap, we present Branch Explorer, a system that transforms 360° videos into branching narratives -- stories that dynamically unfold based on viewer choices -- to support interactive viewing for BLV audiences. Our formative study identified three key considerations for accessible branching narratives: providing diverse branch options, ensuring coherent story progression, and enabling immersive navigation among branches. To address these needs, Branch Explorer employs a multi-modal machine learning pipeline to generate diverse narrative paths, allowing users to flexibly make choices at detected branching points and seamlessly engage with each storyline through immersive audio guidance. Evaluation with 12 BLV viewers showed that Branch Explorer significantly enhanced user agency and engagement in 360° video viewing. Users also developed personalized strategies for exploring 360° content. We further highlight implications for supporting accessible exploration of videos and virtual environments.

cs.HC↗

arXiv2021

The method to increase the thrust of high Mach number Scramjets

The problem of engine unstart of scramjets has not been resolved. In this paper, the mechanism of engine unstart is discussed from the point of view of shock/shock interaction and deflagration-to-detonation transition. The shock/shock interaction leads to the nonlinear, transient and discontinuous process of the supersonic combustion flow field. This process is similar to the deflagration-to-detonation transition process. If the velocity of pre-combustion shock wave is faster than the velocity in the isolator, it will propagate upstream and cause the engine unstart. The C-J detonation velocity is defined as the stable operation boundary of scramjets, which is the maximum shock wave produced by combustion theoretically. The scramjets will work stable if the velocity in the isolator is faster than the corresponding C-J detonation velocity. The combustion characteristics and propulsive performance of scramjets is theoretically analyzed by using C-J detonation theory. For high Mach number scramjets, the velocity in the isolator is much faster than the C-J detonation velocity. Therefore, extra fuel and oxygen can be injected into the combustor to increase the thrust as long as the shock wave velocity driven by the combustion products is slower than the air velocity in the isolator. The theoretical results agree well with the existing experimental results, which can be used as a baseline for the development of scramjets.

physics.flu-dyn↗

arXiv2020

The propagating mechanism of Chapman-Jouguet deflagration

The deflagration-to-detonation transition (DDT) process is of great importance to both combustion theory and industry safety. In this study, the propagating mechanism of Chapman-Jouguet (C-J) deflagration is studied. Firstly, three models are put forth to decouple the C-J detonation front. These three models are (a) to introduce an expansion parameter into the one-dimensional energy equation, (b) to increase the activation energy of the chemical reaction model and (c) to decouple the shock wave from the flame front by artificial method. The C-J deflagration is obtained after the C-J detonation is decoupled by one-dimensional numerical simulations with different models, chemical reaction kinetics and numerical schemes. Secondly, the propagating mechanism of C-J deflagration is discussed. For the C-J deflagration with a propagating velocity of about 1/2 C-J detonation, the static temperature behind the leading shock wave is too low to ignite the combustion. But, the total temperature of the flow induced by the leading shock wave is high enough to ignite the mixture. The induced flow is slowed down by the rarefaction waves form the wall and its static temperature increases. The flame and the leading shock wave propagate with almost the same velocity and the double-discontinuity structure of the flow field keeps stable. The propagating velocity equals to the sound speed of the combustion products, which is about 1/2 C-J detonation velocity.

physics.flu-dyn↗