arXiv subjects

Qixiang Xu

Publications and source records attributed to Qixiang Xu.

3 recordsLinked to original sources

arXiv2026

Higher-order Spillover Effects Under Partial Interference

Interference, under which a unit's outcome is affected by the treatment of other units through network connections, is often present when units interact on a network. When the network of interactions is measured, researchers are often interested in the spillover effect from first-order neighbors. When this is the case, the prevailing approach often involves the neighborhood interference assumption, which is oftentimes overly restrictive. In this paper, we instead rely on a generalized interference assumption, which allows one's potential outcomes to be influenced by the treatment of units from a wider area of the network, referred to as the "interference set". For instance, this can be a community detected through a community detection algorithm, or the set of units that can be reached through a finite network path. Under this assumption, we define new causal estimands to quantify spillover effects from first-order neighbors and, in general, from units at a specific network distance h. We employ two hypothetical Bernoulli distributions with different probabilities for the h-order neighborhood and for the rest of the units in the interference set. We first derive the bias of an approach that relies on a wrong interference set or incorrect exposure mapping function. We then develop new Horvitz-Thompson and Hajek estimators and corresponding weighted regression estimators under the generalized interference assumption. We conduct a series of simulations to assess the bias of OLS estimators -- which rely on restrictive interference assumptions and an exposure mapping function -- , and the performance of our estimators in different interference scenarios and random graphs. We then apply our estimators to a two-stage randomized trial implemented in Honduras to assess a maternal and child health intervention.

stat.ME↗

arXiv2026

MMAE: A Massive Multitask Audio Editing Benchmark

We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing. Spurred by the shift toward intelligent creation, interactive editing has rapidly expanded from visual domains, pioneered by models like Nano-banana 2 for images and Gemini-Omni for video, into audio. However, the current evaluation infrastructure lags severely, remaining highly fragmented and restricted to specific subdomains or basic operations. Unlike existing benchmarks that are limited in scope, MMAE extends to a broad spectrum of real-world scenarios, encompassing 7 distinct audio modalities, including sound, speech, music, and their mixtures. Furthermore, we establish a comprehensive taxonomy spanning 6 levels of task complexity, from basic modifications to multi-hop reasoning and multi-round editing, 2 levels of granularity, and 8 distinct operation types. Meticulously curated through human-agent collaboration, MMAE comprises 2,000 high-fidelity samples paired with a pioneering rubric-based evaluation framework. By decomposing free-form tasks into 17,741 verifiable criteria, this robust rubric-based paradigm enables a precise, multi-dimensional assessment of both instruction following and context consistency. Our extensive evaluation of leading models reveals that current systems remain far from achieving reliable edits. Strikingly, the Exact Match Rate (EMR) consistently falls below 5% and plummets to an absolute 0% in complex, mixed-modality tasks, exposing critical bottlenecks in precise execution and structural robustness. We hope MMAE will serve as a catalyst for future advances in the intelligent creation community, providing a clear diagnostic roadmap and establishing a standardized, long-lasting evaluation paradigm for next-generation audio editing systems.

cs.SD↗

arXiv2026

Audio-Oscar: A Multi-Agent System for Complex Audio Scene Generation, Orchestration, and Refinement

In recent years, audio generation has made significant progress in tasks such as text-to-speech (TTS), text-to-audio (TTA) and text-to-music (TTM). However, generating long-form and controllable audio from complex audio scene descriptions remains a significant challenge, as such scenes often require coordinated speech, sound effects, music, songs, temporal structure, and post-production. In this work, we introduce \textbf{Audio-Oscar}, a multi-agent framework for generating audio from complex descriptions. Audio-Oscar coordinates a set of specialist agents, each responsible for a different aspect of the audio scene, including character modeling and voice design, speech generation, fine-grained timeline planning, model selection, non-speech generation, and audio post-production. Audio-Oscar further incorporates feedback-driven refinement. In addition, to address the lack of suitable benchmarks for evaluating audio generation from complex audio scene descriptions, we construct \textbf{ASG-Bench}, an Audio Scene Generation Benchmark containing both scene descriptions paired with reference audio and text-only scene descriptions. Each scene is annotated with target audio events and temporal statements to evaluate whether the generated audio faithfully realizes the required scene content and temporal structure. Experimental results show that Audio-Oscar can effectively generate audio that matches complex scene descriptions. Project samples are available at https://audiooscar.github.io/. Our code is available at https://github.com/ziye26/Audio-Oscar.

cs.SD↗