arXiv subjects

Ruiqi Chen

Publications and source records attributed to Ruiqi Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage

Biomedical NER is deceptively simple for modern LLMs: plausible biomedical mentions are easy to surface, but corpus-convention correctness depends on annotation conventions, span boundaries, entity granularity, and type schemas. Multi-LLM agreement is a salience signal, not corpus-convention correctness. We introduce a candidate-level panel-output benchmark for panel-surfaced candidate verification, where the unit is an aligned candidate surfaced by an explicitly defined multi-model panel rather than a standalone extractor output. The benchmark aligns eight LLMs' predictions over five public biomedical NER datasets into a candidate master table. BioConCal is an in-domain supervised scorer that instantiates this layer with inference-time gold-free agreement, mention, surface-availability, and document features for a fixed candidate stream. In domain, BioConCal improves AUROC from 0.753 for raw agreement to 0.910. At a validation-selected 0.95 precision target it selects 1,340 candidates at empirical test precision 0.939, compared with 293 for raw agreement. This corresponds to candidate-level recall 0.592 and corpus-level recall 0.523 against a within-panel row-label ceiling of 0.883. The main benefit is not recovering entities missed by every panel member, but reshaping a noisy panel stream into a higher-yield review queue. Under entity-type shift, thresholds require target-domain validation, and exact character localization remains a separate deterministic post-processing step.

cs.CL↗

arXiv2026

Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs

Existing LLM moral benchmarks usually ask which isolated moral act, value, or foundation a model prefers. This is useful but incomplete. Realistic judgments often require a model to combine several moral signals within the same option. We introduce **Moral Trolley Arena**, a two-stage blind ELO benchmark for measuring how LLMs compose moral evidence. The single-scene arena first calibrates individual moral acts from a 229-scenario corpus across five Moral Foundations Theory foundations; the composite arena then combines calibrated acts into two-act moral items over a controlled intensity grid and measures the resulting composite preferences. Across ten frontier models, composite judgments are largely predicted by component act strength, but the relation is consistently compressed rather than simply additive. Models also show non-additive intensity anchoring, bounded foundation-specific residuals after component control, and highly convergent composite preference surfaces across providers. These results suggest that moral audits should measure composition rules for moral evidence, not only rankings over isolated acts.

cs.CL↗

arXiv2026

Scalable iterative Gramian synthesis for control-affine systems

This article presents a scalable implementation of nonlinear Gramian-based control synthesis for control-affine systems, including a minimum energy control construction. These synthesis advances are achieved by addressing key computational bottlenecks inherent to iterative synthesis map formulations, yielding a computational scheme that exhibits rapid convergence and high-precision. The efficacy of this synthesis framework is demonstrated across five canonical nonlinear control systems and 100-dimensional recurrent neural network models, including underactuated systems. Empirical scaling results further indicate that convergence is primarily governed by intrinsic system properties, such as nonlinearity and controllability, rather than by state-space dimensionality. This work provides a practical, scalable computational pathway for translating rigorous nonlinear synthesis theory into high-dimensional control applications.

math.OC↗

arXiv2026

Engagement Is Not Transfer: A Withdrawal Study of a Consumer Social Robot with Autistic Children at Home

This study examines whether engagement with social robots translates into improved human-directed social abilities in autistic children. We conducted an 8-week home-based randomized controlled trial with 40 children aged 5--9 using a commercial social robot (Qrobot). Families were assigned to either continued robot access or robot withdrawal. Quantitative measures and caregiver interviews assessed anxiety, social motivation, emotion inference, and empathy. Results showed that continued robot access significantly reduced anxiety, confirming strong affective benefits and high usability. However, children in the withdrawal group demonstrated greater improvements in social motivation, emotion understanding, and empathic behaviors toward caregivers and peers. Qualitative findings revealed a "handoff versus siloing" pattern: withdrawal promoted reorientation toward human social interaction, while continued access concentrated engagement within the child--robot dyad and limited transfer to real-world contexts. We interpret these results as evidence that high engagement does not guarantee social transfer.

cs.HC↗

arXiv2026

Tracing Generative AI in Digital Art: A Longitudinal Study of Chinese Painters' Attitudes, Practices, and Identity Negotiation

This study presents a five-year longitudinal mixed-methods study of 17 Chinese digital painters, examining how their attitudes and practices evolved in response to generative AI. Our findings reveal a trajectory from resistance and defensiveness, to pragmatic adoption, and ultimately to reflective reconstruction, shaped by strong peer pressures and shifting emotional experiences. Persistent concerns around copyright and creative labor highlight the ongoing negotiation of identity and values. This work contributes by offering rare longitudinal empirical data, advancing a theoretical lens of "identity and value negotiation," and providing design implications for future human-AI collaborative systems.

cs.HC↗

arXiv2026

Interconnect-Aware Logic Resynthesis for Multi-Die FPGAs

Multi-die FPGAs enable device scaling beyond reticle limits but introduce severe interconnect overhead across die boundaries. Inter-die connections, commonly referred to as super-long lines (SLLs), incur high delay and consume scarce interposer interconnect resources, often dominating critical paths and complicating physical design. To address this, this work proposes an interconnect-aware logic resynthesis method that restructures the LUT-level netlist to reduce the number of SLLs. The resynthesis engine uses die partitioning information to apply logic resubstitutions, which simplifies local circuit structures and eliminates SLLs. By reducing the number of SLLs early in the design flow, prior to physical implementation, the proposed method shortens critical paths, alleviates pressure on scarce interposer interconnect resources, and improves overall physical design flexibility. We further build a tool flow for multi-die FPGAs by integrating the proposed resynthesis method with packing and placement. Experimental results on the EPFL benchmarks show that, compared with a state-of-the-art framework, the proposed method reduces the number of SLLs by up to 24.8% for a 2-die FPGA and up to 27.38% for a 3-die FPGA. On MCNC benchmarks, our tool flow achieves an average SLL reduction of 1.65% while preserving placement quality. On Koios benchmarks, where fewer removable SLLs exist, several designs still exhibit considerable inter-die edge reductions. Overall, the results confirm that reducing inter-die connections at the logic level is an effective approach for multi-die FPGAs.

cs.AR↗

arXiv2026

SemFuzz: A Semantics-Aware Fuzzing Framework for Network Protocol Implementations

Network protocols are the foundation of modern communication, yet their implementations often contain semantic vulnerabilities stemming from inadequate understanding of specification semantics. Existing gray-box and black-box testing approaches lack semantic modeling of protocols, making it difficult to precisely express testing intent and cover boundary conditions. Moreover, they typically rely on coarse-grained oracles such as crashes, which are inadequate for identifying deep semantic vulnerabilities. To address these limitations, we present a semantics-aware fuzzing framework, SemFuzz. The framework leverages large language models to extract structured semantic rules from RFC documents and generates test cases that intentionally violate these rules to encode specific testing intents. It then detects deep semantic vulnerabilities by comparing the observed responses with the expected ones. Evaluation on seven widely deployed protocol implementations shows that SemFuzz identified sixteen potential vulnerabilities, ten of which have been confirmed. Among the confirmed vulnerabilities, five were previously unknown and four have been assigned CVEs. These results demonstrate the effectiveness of SemFuzz in detecting semantic vulnerabilities.

cs.CR↗

arXiv2026

52-Hz Whale Song: An Embodied VR Experience for Exploring Misunderstanding and Empathy

Experiences of being misunderstood often stem not from a lack of voice, but from mismatches between how individuals express themselves and how others listen. Such communicative mismatches arise across many social settings, including situations involving linguistic and cultural displacement. While prior HCI research has explored empathy through virtual reality, many approaches rely on narrative explanation, positioning users as observers rather than embodied participants. We present 52-Hz Whale Song, an embodied VR experience that explores miscommunication through metaphor and perspective-shifting. Inspired by the real-world "52-Hz whale," whose calls are not responded to by others, the experience uses this phenomenon as an experiential lens on communicative mismatch rather than representing any specific social group. Players progress through a three-act arc that moves from failed communication to agency and ultimately to mediation. A preliminary mixed-methods study (N = 30) suggests increased perspective-taking and reduced self-reported social distance in immigrant-related situations. This work highlights how embodied metaphor and role-shifting can support empathic engagement and offers transferable design insights for empathy-oriented interactive systems.

cs.HC↗

arXiv2026

Misty Forest VR: Turning Real ADHD Attention Patterns into Shared Momentum for Youth Collaboration

Attention Deficit Hyperactivity Disorder (ADHD) remains highly stigmatized in many cultural contexts, particularly in China, where ADHD-related behaviors are often moralized rather than understood as neurodevelopmental differences. As a result, challenges of self-perception, social misunderstanding, and collaboration between ADHD and non-ADHD individuals remain largely unaddressed. We present Misty Forest, a VR-based collaborative game that explores ADHD through asymmetric co-play. The system translates empirically grounded ADHD behavioral patterns -- such as fluctuating attention and time blindness -- into complementary roles that require mutual coordination between players. Rather than compensating for deficits, the design treats cognitive differences as a source of interdependence. In a controlled study with mixed ADHD--non-ADHD dyads, Misty Forest led to higher task completion, increased self-acceptance among ADHD participants, improved ADHD knowledge, and greater empathy among non-ADHD players. These findings suggest that neurodiversity-centered interactive design can foster understanding, reciprocity, and inclusive collaboration.

cs.HC↗

arXiv2026

CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation

Vision-Language Models (VLMs) have shown remarkable progress in Vision-Language Navigation (VLN), offering new possibilities for navigation decision-making that could benefit both robotic platforms and human users. However, real-world navigation is inherently conditioned by the agent's mobility constraints. For example, a sweeping robot cannot traverse stairs, while a quadruped can. We introduce Capability-Conditioned Navigation (CapNav), a benchmark designed to evaluate how well VLMs can navigate complex indoor spaces given an agent's specific physical and operational capabilities. CapNav defines five representative human and robot agents, each described with physical dimensions, mobility capabilities, and environmental interaction abilities. CapNav provides 45 real-world indoor scenes, 473 navigation tasks, and 2365 QA pairs to test if VLMs can traverse indoor environments based on agent capabilities. We evaluate 13 modern VLMs and find that current VLM's navigation performance drops sharply as mobility constraints tighten, and that even state-of-the-art models struggle with obstacle types that require reasoning on spatial dimensions. We conclude by discussing the implications for capability-aware navigation and the opportunities for advancing embodied spatial reasoning in future VLMs. The benchmark is available at https://github.com/makeabilitylab/CapNav

cs.CV↗

arXiv2026

Before Smelling the Video: A Two-Stage Pipeline for Interpretable Video-to-Scent Plans

Olfactory cues can enhance immersion in interactive media, yet smell remains rare because it is difficult to author and synchronize with dynamic video. Prior olfactory interfaces rely on designer triggers and fixed event-to-odor mappings that do not scale to unconstrained content. This work examines whether semantic planning for smell is intelligible to people before physical scent delivery. We present a video-to-scent planning pipeline that separates visual semantic extraction using a vision-language model from semantic-to-olfactory inference using a large language model. Two survey studies compare system-generated scent plans with over-inclusive and naive baselines. Results show consistent preference for plans that prioritize perceptually salient cues and align scent changes with visible actions, supporting semantic planning as a foundation for future olfactory media systems.

cs.HC↗

arXiv2026

Between Knowledge and Care: Evaluating Generative AI-Based IUI in Type 2 Diabetes Management Through Patient and Physician Perspectives

Generative AI systems are increasingly used by patients seeking everyday health guidance, yet their appropriateness in chronic care contexts remains unclear. Focusing on Type 2 Diabetes Mellitus (T2DM), this paper presents a mixed-methods investigation into how AI-generated health information is interpreted by patients and evaluated by physicians in China. Drawing on formative patient grounding and a dimension-based physician evaluation, we examine AI responses along five quality dimensions: Accuracy, Safety, Clarity, Integrity, and Action Orientation. Our findings reveal that while current systems perform well in factual explanation and general lifestyle guidance, they frequently break down in safety signaling, contextual judgment, and responsibility boundaries, particularly when fluent responses invite overtrust. By treating quality dimensions as an interpretive lens rather than a fixed framework, this work highlights the need for intelligent user interfaces that actively mediate AI outputs in chronic disease management, supporting calibrated trust and responsible boundary-setting in long-term care.

cs.HC↗

arXiv2025

CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation

Maintaining narrative coherence and visual consistency remains a central challenge in open-domain video generation. Existing text-to-video models often treat each shot independently, resulting in identity drift, scene inconsistency, and unstable temporal structure. We propose CoAgent, a collaborative and closed-loop framework for coherent video generation that formulates the process as a plan-synthesize-verify pipeline. Given a user prompt, style reference, and pacing constraints, a Storyboard Planner decomposes the input into structured shot-level plans with explicit entities, spatial relations, and temporal cues. A Global Context Manager maintains entity-level memory to preserve appearance and identity consistency across shots. Each shot is then generated by a Synthesis Module under the guidance of a Visual Consistency Controller, while a Verifier Agent evaluates intermediate results using vision-language reasoning and triggers selective regeneration when inconsistencies are detected. Finally, a pacing-aware editor refines temporal rhythm and transitions to match the desired narrative flow. Extensive experiments demonstrate that CoAgent significantly improves coherence, visual consistency, and narrative quality in long-form video generation.

cs.CV↗

arXiv2025

PTTA: A Pure Text-to-Animation Framework for High-Quality Creation

Traditional animation production involves complex pipelines and significant manual labor cost. While recent video generation models such as Sora, Kling, and CogVideoX achieve impressive results on natural video synthesis, they exhibit notable limitations when applied to animation generation. Recent efforts, such as AniSora, demonstrate promising performance by fine-tuning image-to-video models for animation styles, yet analogous exploration in the text-to-video setting remains limited. In this work, we present PTTA, a pure text-to-animation framework for high-quality animation creation. We first construct a small-scale but high-quality paired dataset of animation videos and textual descriptions. Building upon the pretrained text-to-video model HunyuanVideo, we perform fine-tuning to adapt it to animation-style generation. Extensive visual evaluations across multiple dimensions show that the proposed approach consistently outperforms comparable baselines in animation video synthesis.

cs.CV↗

arXiv2025

Comparing Dynamical Models Through Diffeomorphic Vector Field Alignment

Dynamical systems models such as recurrent neural networks (RNNs) are increasingly popular in theoretical neuroscience for hypothesis-generation and data analysis. Evaluating the dynamics in such models is key to understanding their learned generative mechanisms. However, such evaluation is impeded by two major challenges: First, comparison of learned dynamics across models is difficult because there is no enforced equivalence of their coordinate systems. Second, identification of mechanistically important low-dimensional motifs (e.g., limit sets) is intractable in high-dimensional nonlinear models such as RNNs. Here, we propose a comprehensive framework to address these two issues, termed Diffeomorphic vector field alignment FOR learned Models (DFORM). DFORM learns a nonlinear coordinate transformation between the state spaces of two dynamical systems, which aligns their trajectories in a maximally one-to-one manner. In so doing, DFORM enables an assessment of whether two models exhibit topological equivalence, i.e., similar mechanisms despite differences in coordinate systems. A byproduct of this method is a means to locate dynamical motifs on low-dimensional manifolds embedded within higher-dimensional systems. We verified DFORM's ability to identify linear and nonlinear coordinate transformations using canonical topologically equivalent systems, RNNs, and systems related by nonlinear flows. DFORM was also shown to provide a quantification of similarity between topologically distinct systems. We then demonstrated that DFORM can locate important dynamical motifs including invariant manifolds and saddle limit sets within high-dimensional models. Finally, using a set of RNN models trained on human functional MRI (fMRI) recordings, we illustrated that DFORM can identify limit cycles from high-dimensional data-driven models, which agreed well with prior numerical analysis.

cs.LG↗

arXiv2025

MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models

The ability to perform Chain-of-Thought (CoT) reasoning marks a major milestone for multimodal models (MMs), enabling them to solve complex visual reasoning problems. Yet a critical question remains: is such reasoning genuinely grounded in visual evidence and logically coherent? Existing benchmarks emphasize generation but neglect verification, i.e., the capacity to assess whether a reasoning chain is both visually consistent and logically valid. To fill this gap, we introduce MM-CoT, a diagnostic benchmark specifically designed to probe the visual grounding and logical coherence of CoT reasoning in MMs. Instead of generating free-form explanations, models must select the sole event chain that satisfies two orthogonal constraints: (i) visual consistency, ensuring all steps are anchored in observable evidence, and (ii) logical coherence, ensuring causal and commonsense validity. Adversarial distractors are engineered to violate one of these constraints, exposing distinct reasoning failures. We evaluate leading vision-language models on MM-CoT and find that even the most advanced systems struggle, revealing a sharp discrepancy between generative fluency and true reasoning fidelity. MM-CoT shows low correlation with existing benchmarks, confirming that it measures a unique combination of visual grounding and logical reasoning. This benchmark provides a foundation for developing future models that reason not just plausibly, but faithfully and coherently within the visual world.

cs.CV↗

arXiv2025

Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First

Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of exploration and solution formulation for the given task, one we call agentic speculation. The sheer volume and inefficiencies of agentic speculation can pose challenges for present-day data systems. We argue that data systems need to adapt to more natively support agentic workloads. We take advantage of the characteristics of agentic speculation that we identify, i.e., scale, heterogeneity, redundancy, and steerability - to outline a number of new research opportunities for a new agent-first data systems architecture, ranging from new query interfaces, to new query processing techniques, to new agentic memory stores.

cs.AI↗

arXiv2025

Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA

Deploying large language models (LLMs) on embedded devices remains a significant research challenge due to the high computational and memory demands of LLMs and the limited hardware resources available in such environments. While embedded FPGAs have demonstrated performance and energy efficiency in traditional deep neural networks, their potential for LLM inference remains largely unexplored. Recent efforts to deploy LLMs on FPGAs have primarily relied on large, expensive cloud-grade hardware and have only shown promising results on relatively small LLMs, limiting their real-world applicability. In this work, we present Hummingbird, a novel FPGA accelerator designed specifically for LLM inference on embedded FPGAs. Hummingbird is smaller, targeting embedded FPGAs such as the KV260 and ZCU104 with 67% LUT, 39% DSP, and 42% power savings over existing research. Hummingbird is stronger, targeting LLaMA3-8B and supporting longer contexts, overcoming the typical 4GB memory constraint of embedded FPGAs through offloading strategies. Finally, Hummingbird is faste, achieving 4.8 tokens/s and 8.6 tokens/s for LLaMA3-8B on the KV260 and ZCU104 respectively, with 93-94% model bandwidth utilization, outperforming the prior 4.9 token/s for LLaMA2-7B with 84% bandwidth utilization baseline. We further demonstrate the viability of industrial applications by deploying Hummingbird on a cost-optimized Spartan UltraScale FPGA, paving the way for affordable LLM solutions at the edge.

cs.AR↗