arXiv subjects

Alexander Wang

Publications and source records attributed to Alexander Wang.

18 recordsLinked to original sources

arXiv2026

MultiVerse: A Creator-Centered Approach to Steering Context-Adaptive Lyrics

Generative AI may enable new forms of context-aware creative expression by dynamically tailoring media content to its consumption context. For instance, AI systems could adapt song lyrics to the listener and their current activity. However, existing media adaptation systems primarily optimize for audience experience, often neglecting artists' intent, style, and preference. We address this challenge by introducing a novel creator-centered approach to adaptive media authoring and present MultiVerse, a system that instantiates this approach for steering adaptive lyrics. Our approach allows creators to explicitly author controls based on their intent, lyric structure, and audience context, and uses rule-based validations to ensure controls are followed. We conducted a study with 10 songwriters, comparing MultiVerse with a prompting-based workflow for composing adaptive lyrics. The comparison revealed that creators preferred to author how lyrics adapt by explicitly specifying relevant context and adaptation constraints, while recognizing trade-offs in flexibility and iteration speed. Interviews further revealed that creators viewed adaptive media as enabling new forms of audience connection, introducing a distinct creative process, favoring new compositional strategies, and reshaping notions of authorship.

cs.HC↗

arXiv2026

Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness

End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM "pure" mode. The pure suite (238 cases across 23 slices; 225 run in 2.39 s, ~10 ms/case) runs in CI on every change against a locked per-slice baseline. We validate by controlled regression injection, degrading one layer at a time across seven non-safety layers. The effect we did not design in is masking: the aggregate pass-rate barely moves (-1.7 to -5.9 pp for six local regressions), while the matching slice craters (-25 to -91 pp). A layer's slice reacting to its own fault is partly by construction; the measured results are (i) the aggregate masking and (ii) that damage stays off the other slices: the injected layer's slice is the single worst-hit in 5 of 7 cases and top-3 in 7 of 7 (mean rank 1.29 of 19). Localization replicates on a second, structurally different tenant (Starbucks SG): all seven matching slices crater, so it is not a single-catalog artifact. We position it as a concrete, deterministic instantiation of the component-level evaluation EDDOps prescribes but leaves unimplemented, with CheckList as ancestor and as the deterministic mirror image of whole-workflow stochastic mutation testing. Our contributions: (a) a fully decomposed, sub-second, no-LLM per-layer harness for a production agent, (b) a coverage-honesty test-adequacy criterion that refuses to score an unexercised layer, and (c) the regression-injection demonstration that per-slice baseline-locked gates localize regressions an aggregate metric masks.

cs.CL↗

arXiv2026

Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agents

LLM-as-judge is the default instrument for evaluating conversational agents, yet its reliability is almost always reported as agreement with human ratings, not recall of real defects. We study a deployed multi-turn food-and-beverage ordering agent and measure how many genuine quality problems its built-in LLM judge catches, using exhaustive human transcript review as ground truth. Across three batches the judge surfaces well under a quarter of human-confirmed systematic problems -- 2 of 9 patterns (22%) in one batch, and its operational gate flagged zero of 100 rounds in a batch where humans confirmed 23 distinct defects and 7 new cross-cutting patterns. Our blind-spot taxonomy shows the failure is structured, not random: the judge catches turn-local issues (a fabricated statistic, a wrong language) but misses cross-turn state issues (confirm-gate lockout, cart hallucination, escalation lockout, stale referents). The mechanism: the scoring rubric exposes only three coarse axes (intent, brand-voice, personalization) and has no category for the behavioural dimensions -- state-tracking, guardrails, recovery -- where most defects cluster. The failure is routing, not perception: 113 of 114 rounds whose raw judge note describes a confirm-gate or cart-state defect are scored "brand voice", and none reach an operational failure -- the gate is wired to hangs and hard assertions, not the rubric -- so the 0% is a routing-and-wiring failure, not blindness. The consequence for prevalence estimation is sharp: when the apparent defect rate is zero the Rogan-Gladen correction degenerates -- no signal can recover the true rate -- while where the gate reports a nonzero rate the same estimator implies a 3-6x undercount under our measured sensitivity. For production multi-turn agents, automated judging is a regression floor, not a substitute for human review.

cs.CL↗

arXiv2026

Online learning of smooth functions on $\mathbb{R}$

We study adversarial online learning of real-valued functions on $\mathbb{R}$. In each round the learner is queried at $x_t\in\mathbb{R}$, predicts $\hat y_t$, and then observes the true value $f(x_t)$; performance is measured by cumulative $p$-loss $\sum_{t\ge 1}|\hat y_t-f(x_t)|^p$. For the class \[ \mathcal{G}_q=\Bigl\{f:\mathbb{R}\to\mathbb{R}\ \text{absolutely continuous}:\ \int_{\mathbb{R}}|f'(x)|^q\,dx\le 1\Bigr\}, \] we show that the standard model becomes ill-posed on $\mathbb{R}$: for every $p\ge 1$ and $q>1$, an adversary can force infinite loss. Motivated by this obstruction, we analyze three modified learning scenarios that limit the influence of queries that are far from previously observed inputs. In Scenario 1 the adversary must choose each new query within distance $1$ of some past query. In Scenario 2 the adversary may query anywhere, but the learner is penalized only on rounds whose query lies within distance $1$ of a past query. In Scenario 3 the loss in round $t$ is multiplied by a weight $g(\min_{j<t}|x_t-x_j|)$. We obtain sharp characterizations for Scenarios 1-2 in several regimes. For Scenario 3 we identify a clean threshold phenomenon: if $g$ decays too slowly, then the adversary can force infinite weighted loss. In contrast, for rapidly decaying weights such as $g(z)=e^{-cz}$ we obtain finite and sharp guarantees in the quadratic case $p=q=2$. Finally, we study a natural multivariable slice generalization $\mathcal{G}_{q,d}$ of $\mathcal{G}_q$ on $\mathbb{R}^d$ and show a sharp dichotomy: while the one-dimensional case admits finite opt-values in certain regimes, for every $d\ge 2$ the slice class $\mathcal{G}_{q,d}$ is too permissive, and even under Scenarios 1-3 an adversary can force infinite loss.

cs.LG↗

arXiv2026

GameDevBench: Evaluating Agentic Capabilities Through Game Development

Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. In game development, agents must navigate large, dense codebases while manipulating intrinsically multimodal assets such as shaders, sprites, and animations within a visual game scene. We present GameDevBench, the first benchmark for evaluating agents on game development tasks. GameDevBench consists of 333 tasks derived from web and video tutorials. Tasks require significant multimodal understanding and are complex: the average solution requires over three times the lines of code and file changes compared to prior software development benchmarks. Agents struggle with game development, with the best agent and method solving only 53.8% of tasks. We find a strong correlation between perceived task difficulty and multimodal complexity, with average success rate dropping from 51.4% on gameplay-oriented tasks to 33.0% on 2D graphics tasks. To improve multimodal capability, we introduce two simple image- and video-based feedback mechanisms for agents. Despite their simplicity, these methods consistently improve performance, increasing GPT-5.4's performance from 41.1% to 52.0% when given visual feedback.

cs.AI↗

arXiv2026

A Design Space for Live Music Agents

Live music provides a uniquely rich setting for studying creativity and interaction due to its spontaneous nature. The pursuit of live music agents--intelligent systems supporting real-time music performance and interaction--has captivated researchers across HCI, AI, and computer music for decades, and recent advancements in AI suggest unprecedented opportunities to evolve their design. However, the interdisciplinary nature of music has led to fragmented development across research communities, hindering effective communication and collaborative progress. In this work, we bring together perspectives from these diverse fields to map the current landscape of live music agents. Based on our analysis of 184 systems across both academic literature and video, we develop a comprehensive design space that categorizes dimensions spanning usage contexts, interactions, technologies, and ecosystems. By highlighting trends and gaps in live music agents, our design space offers researchers, designers, and musicians a structured lens to understand existing systems and shape future directions in real-time human-AI music co-creation. We release our annotated systems as a living artifact at https://live-music-agents.github.io.

cs.HC↗

arXiv2026

Auditorily Embodied Conversational Agents: Effects of Spatialization and Situated Audio Cues on Presence and Social Perception

Embodiment can enhance conversational agents, such as increasing their perceived presence. This is typically achieved through visual representations of a virtual body; however, visual modalities are not always available, such as when users interact with agents using headphones or display-less glasses. In this work, we explore auditory embodiment. By introducing auditory cues of bodily presence - through spatially localized voice and situated Foley audio from environmental interactions - we investigate how audio alone can convey embodiment and influence perceptions of a conversational agent. We conducted a 2 (spatialization: monaural vs. spatialized) x 2 (Foley: none vs. Foley) within-subjects study, where participants (n=24) engaged in conversations with agents. Our results show that spatialization and Foley increase co-presence, but reduce users' perceptions of the agent's attention and other social attributes.

cs.HC↗

arXiv2025

Superelliptic degree sets over Henselian fields

Let $K$ be a discretely valued Henselian field. Creutz and Viray show that the degree set of a curve $C$ over a $p$-adic field can miss infinitely many multiples of the index of $C$, a phenomenon that cannot occur over finitely generated fields. For curves $C/K$ with a cyclic cover of $\mathbb{P}^1$ of prime degree, under mild assumptions, we completely characterize how and when this behavior can occur, and give a method for computing degree sets of curves of this type.

math.NT↗

arXiv2025

RISE: Adaptive music playback for Realtime Intensity Synchronization with Exercise

We propose a system to adapt a user's music to their exercise by aligning high-energy music segments with intense intervals of the workout. Listening to music during exercise can boost motivation and performance. However, the structure of the music may be different from the user's natural phases of rest and work, causing users to rest longer than needed while waiting for a motivational section, or lose motivation mid-work if the section ends too soon. To address this, our system, called RISE, automatically estimates the intense segments in music and uses component-based music rearrangement techniques to dynamically extend and shorten different segments of the user's song to fit the ongoing exercise routine. Our system takes as input the rest and work durations to guide adaptation. Currently, this is determined either via a pre-defined plan or manual input during the workout. We evaluated RISE with 12 participants and compared our system to a non-adaptive music baseline while exercising in our lab. Participants found our rearrangements keeps intensity estimation accurate, and many recalled moments when intensity alignment helped them push through their workout.

cs.SD↗

arXiv2025

On the Hasse Principle for conic bundles over even degree extensions

Let $k$ be a number field and let $\pi \colon X \rightarrow\mathbb{P}_k^1$ be a smooth conic bundle. We show that if $X/k$ has four geometric singular fibers and either $X(\mathbb{A}_k)\neq \emptyset$ or $X/k$ has non-trivial Brauer group, then $X$ satisfies the Hasse principle over any even degree extension $L/k$. Furthermore for arbitrary $X$ we show that, conditional on Schinzel's hypothesis, $X$ satisfies the Hasse principle over all but finitely many quadratic extensions of $k$. We prove these results by showing the Brauer-Manin obstruction vanishes and then apply fibration method results of Colliot-Th\'el\`ene, following Colliot-Th\'el\`ene and Sansuc.

math.NT↗

arXiv2025

SAM-EM: Real-Time Segmentation for Automated Liquid Phase Transmission Electron Microscopy

The absence of robust segmentation frameworks for noisy liquid phase transmission electron microscopy (LPTEM) videos prevents reliable extraction of particle trajectories, creating a major barrier to quantitative analysis and to connecting observed dynamics with materials characterization and design. To address this challenge, we present Segment Anything Model for Electron Microscopy (SAM-EM), a domain-adapted foundation model that unifies segmentation, tracking, and statistical analysis for LPTEM data. Built on Segment Anything Model 2 (SAM~2), SAM-EM is derived through full-model fine-tuning on 46,600 curated LPTEM synthetic video frames, substantially improving mask quality and temporal identity stability compared to zero-shot SAM~2 and existing baselines. Beyond segmentation, SAM-EM integrates particle tracking with statistical tools, including mean-squared displacement and particle displacement distribution analysis, providing an end-to-end framework for extracting and interpreting nanoscale dynamics. Crucially, full fine-tuning allows SAM-EM to remain robust under low signal-to-noise conditions, such as those caused by increased liquid sample thickness in LPTEM experiments. By establishing a reliable analysis pipeline, SAM-EM transforms LPTEM into a quantitative single-particle tracking platform and accelerates its integration into data-driven materials discovery and design. Project page: \href{https://github.com/JamaliLab/SAM-EM}{github.com/JamaliLab/SAM-EM}.

cs.CV↗

arXiv2024

On maximal common divisors in Puiseux monoids

Let $M$ be a commutative monoid. An element $d \in M$ is called a maximal common divisor of a nonempty subset $S$ of $M$ if $d$ is a common divisor of $S$ in $M$ and the only common divisors in $M$ of the set $\big\{ \frac{s}d : s \in S \big\}$ are the units of $M$. In this paper, we investigate the existence of maximal common divisors in rank-$1$ torsion-free commutative monoids, also known as Puiseux monoids. We also establish some connections between the existence of maximal common divisors and both atomicity and the ascending chain condition on principal ideals for the monoids we investigate here.

math.AC↗

arXiv2024

Auptimize: Optimal Placement of Spatial Audio Cues for Extended Reality

Spatial audio in Extended Reality (XR) provides users with better awareness of where virtual elements are placed, and efficiently guides them to events such as notifications, system alerts from different windows, or approaching avatars. Humans, however, are inaccurate in localizing sound cues, especially with multiple sources due to limitations in human auditory perception such as angular discrimination error and front-back confusion. This decreases the efficiency of XR interfaces because users misidentify from which XR element a sound is coming. To address this, we propose Auptimize, a novel computational approach for placing XR sound sources, which mitigates such localization errors by utilizing the ventriloquist effect. Auptimize disentangles the sound source locations from the visual elements and relocates the sound sources to optimal positions for unambiguous identification of sound cues, avoiding errors due to inter-source proximity and front-back confusion. Our evaluation shows that Auptimize decreases spatial audio-based source identification errors compared to playing sound cues at the paired visual-sound locations. We demonstrate the applicability of Auptimize for diverse spatial audio-based interactive XR scenarios.

cs.HC↗

arXiv2024

STAT: Shrinking Transformers After Training

We present STAT: a simple algorithm to prune transformer models without any fine-tuning. STAT eliminates both attention heads and neurons from the network, while preserving accuracy by calculating a correction to the weights of the next layer. Each layer block in the network is compressed using a series of principled matrix factorizations that preserve the network structure. Our entire algorithm takes minutes to compress BERT, and less than three hours to compress models with 7B parameters using a single GPU. Using only several hundred data examples, STAT preserves the output of the network and improves upon existing gradient-free pruning methods. It is even competitive with methods that include significant fine-tuning. We demonstrate our method on both encoder and decoder architectures, including BERT, DistilBERT, and Llama-2 using benchmarks such as GLUE, Squad, WikiText2.

cs.LG↗

arXiv2022

"COVID-19 was a FIFA conspiracy #curropt": An Investigation into the Viral Spread of COVID-19 Misinformation

The outbreak of the infectious and fatal disease COVID-19 has revealed that pandemics assail public health in two waves: first, from the contagion itself and second, from plagues of suspicion and stigma. Now, we have in our hands and on our phones an outbreak of moral controversy. Modern dependency on social medias has not only facilitated access to the locations of vaccine clinics and testing sites but also-and more frequently-to the convoluted explanations of how "COVID-19 was a FIFA conspiracy"[1]. The MIT Media Lab finds that false news "diffuses significantly farther, faster, deeper, and more broadly than truth, in all categories of information, and by an order of magnitude"[2]. The question is, how does the spread of misinformation interact with a physical epidemic disease? In this paper, we estimate the extent to which misinformation has influenced the course of the COVID-19 pandemic using natural language processing models and provide a strategy to combat social media posts that are likely to cause widespread harm.

cs.CY↗

arXiv2020

SketchEmbedNet: Learning Novel Concepts by Imitating Drawings

Sketch drawings capture the salient information of visual concepts. Previous work has shown that neural networks are capable of producing sketches of natural objects drawn from a small number of classes. While earlier approaches focus on generation quality or retrieval, we explore properties of image representations learned by training a model to produce sketches of images. We show that this generative, class-agnostic model produces informative embeddings of images from novel examples, classes, and even novel datasets in a few-shot setting. Additionally, we find that these learned representations exhibit interesting structure and compositionality.

cs.CV↗

arXiv2019

Centrally symmetric and balanced triangulations of $\mathbb{S}^2\times \mathbb{S}^{d-3}$ with few vertices

A small triangulation of the sphere product can be found in lower dimensions by computer search and is known in few other cases: Klee and Novik constructed a centrally symmetric triangulation of $\mathbb{S}^i\times \mathbb{S}^{d-i-1}$ with $2d+2$ vertices for all $d\geq 3$ and $1\leq i\leq d-2$; they also proposed a balanced triangulation of $\mathbb{S}^1\times \mathbb{S}^{d-2}$ with $3d$ or $3d+2$ vertices. In this paper, we provide another centrally symmetric $(2d+2)$-vertex triangulation of $\mathbb{S}^2\times \mathbb{S}^{d-3}$. We also construct the first balanced triangulation of $\mathbb{S}^2\times \mathbb{S}^{d-3}$ with $4d$ vertices, using a sphere decomposition inspired by handle theory.

math.CO↗

arXiv2019

Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance

Attribute prior avoidance entails subconscious or willful non-modeling of (meta)attributes that datasets are oft born with, such as the 40 semantic facial attributes associated with the CelebA and CelebA-HQ datasets. The consequences of this infirmity, we discover, are especially stark in state-of-the-art deep generative models learned on these datasets that just model the pixel-space measurements, resulting in an inter-attribute bias-laden latent space. This viscerally manifests itself when we perform face manipulation experiments based on latent vector interpolations. In this paper, we address this and propose a post-hoc solution that utilizes an Ising attribute prior learned in the attribute space and showcase its efficacy via qualitative experiments.

cs.CV↗