arXiv subjects

Hong Jia

Publications and source records attributed to Hong Jia.

At least 19 recordsLinked to original sources

arXiv2026

Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models

Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio representations into a large language model (LLM) backbone to enable multimodal reasoning. Recent test-time reinforcement learning (TTRL) methods further improve LLM reasoning capability by leveraging unlabelled test data after pre-training. However, the importance of the perceptual capability of LALMs remains underexplored, particularly how much acoustic evidence is integrated and relied upon during reasoning, and how this contributes to final task performance. This gap limits the development of effective post-training methods like TTRL for audio reasoning. In this work, we first analyse how audio information is integrated and utilised during reasoning process. We quantify layer-wise perceptual reliance and show that stronger acoustic reliance is associated with higher accuracy and a larger performance gain attributable to the audio input. Building on this, we propose Perception-Grounded TTRL (PG-TTRL), which aligns label-free test-time optimisation with perceptually grounded reasoning, encouraging the model to structure its reasoning more strongly on the audio input. Experiments across LALMs and benchmarks show that PG-TTRL consistently improves reasoning performance over both the base models and standard TTRL, showing the value of perceptual-grounding optimisation for test-time audio reasoning.

cs.SD↗

arXiv2026

When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents

Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also introduces security and privacy risks because malicious instructions from external sources may be written into persistent memory and persist across sessions. To study this risk, we propose PMPA, a Persistent Memory Poisoning Attack against harness-based agents. PMPA embeds malicious instructions into benign external sources and induces the victim agent to write them into persistent memory without directly accessing to the agent framework. Once stored, the poisoned memory can be retrieved in later sessions, triggering additional malicious actions and causing privacy leakage. We evaluate PMPA on OpenClaw and Claude Code across different backbone LLMs, input modalities, and trigger scenarios. Across all settings, PMPA achieves average Injection Success Rate (ISR) and Cross-session Attack Success Rate (C-ASR) of 73.7%/ 55.5% on OpenClaw and 66.9%/ 81.7% on Claude Code, while preserving benign task performance on both systems. We further evaluate a targeted prompt-level defense and find that it can reduce memory injection in many settings, but provides limited protection once the persistent memory has been poisoned.

cs.CR↗

arXiv2026

ManGo: Manga Active Narrative Grounding Optimization

Manga visual question answering requires models to answer questions over panel-based visual narratives, where relevant evidence is distributed across ordered panels, embedded text, recurring characters, and implicit event transitions. This structure makes passive page encoding insufficient, as the model must identify which panels to inspect, what clues to retain, and when the accumulated evidence is sufficient for answering. We propose ManGo (Manga Active Narrative Grounding Optimization), an unsupervised framework for active manga visual question answering. ManGo introduces Active Narrative Sketching (ANS), which iteratively selects panels, extracts concise grounded clues, and decides when to stop, forming a compact question-directed evidence sketch before answer generation. To optimize this behavior without human-annotated answers or rationale paths, ManGo samples multiple ANS rollouts and applies group-relative training with two rewards: answer preference from listwise self-ranking and path consistency from stable ordered panel trajectories. The combined reward is optimized with group-relative policy training, encouraging the model to improve both final answers and the panel-level evidence paths that support them. Experiments on standard manga understanding benchmarks show that ManGo achieves state-of-the-art performance across different settings.

cs.CL↗

arXiv2026

Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment

Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to reproduce, compare, and extend. Existing evaluations are often tied to custom infrastructure, released as incomplete research code, and conducted primarily in simulation, which limits portability and practical relevance. We present Flower Hub, a platform for publishing, discovering, and executing decentralized and federated applications. We show how it enables reproducible benchmarking by packaging benchmarks as executable, versioned applications with standardized metadata, pinned dependencies, and explicit evaluation workflows. We instantiate this approach with a multi-domain benchmark suite spanning cross-silo and cross-device settings, and including tasks in medical imaging, financial tabular learning, legal instruction tuning, phishing URL detection, and audio tagging. We further demonstrate that the same benchmarking application can run across both simulation and deployment runtimes without changing the application code, enabling unified evaluation across varying learning environments. Beyond model quality, our benchmark design supports system-aware reporting, including runtime and communication metrics. This work advances benchmarking in FL settings from ad hoc code artifacts towards portable, executable, and reusable benchmark applications.

cs.LG↗

arXiv2026

MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection

Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a realistic attack scenario in which speech and background audio are independently manipulated over otherwise authentic video. Yet existing research either focuses on visual manipulation, addresses speech detection in isolation, or conflates speech and non-speech audio as a single undifferentiated audio stream, overlooking the distinct forensic challenges posed by background audio. This conflation is consequential: the two acoustic components arise from fundamentally different generative mechanisms, exhibit distinct artifact profiles, and pose different challenges to detection systems. We introduce MADBench, the first benchmark that treats speech and environmental audio as distinct acoustic components, enabling component-aware evaluation of audio deepfake detection across independently manipulated forgery sources. We benchmark representative state-of-the-art detectors and multimodal large language models under a unified protocol. Our experiments reveal that environmental audio manipulation is more detectable than synthetic speech across general-purpose encoders, while existing pretrained detectors fail on both acoustic components, and manipulated environmental audio asymmetrically degrades speech deepfake detection, findings entirely invisible under the single-label paradigm of prior benchmarks. MADBench establishes a rigorous foundation for future research into robust, component-aware audio deepfake detection.

cs.SD↗

arXiv2026

LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding

Vision-Language-Action (VLA) models transform representations from pretrained vision-language models (VLMs) into robot actions, yet the interface that routes intermediate VLM features into action decoders remains underexplored. Existing designs either expose only a narrow part of the representation hierarchy or rigidly match each decoder block to one VLM layer, restricting access to complementary task evidence across depths. We introduce LIRA, a local cross-layer action-conditioning mechanism that formulates VLM-to-action conditioning as depth-aware information routing. LIRA operates on task-token features and LIRA Query features derived from intermediate VLM states, then assigns each Parallel Fusion Block a depth-aligned local window centered on its corresponding VLM layer. Parallel Fusion Blocks aggregate neighboring LIRA Query features and integrate them with task-token features and proprioceptive inputs before action prediction. This routing interface leaves the backbone architecture, action decoder, and supervised training recipe unchanged. Across LIBERO, LIBERO-Plus, CALVIN ABC$\rightarrow$D, and real-world manipulation, LIRA improves the principal aggregate metrics over the VLA-Adapter baseline under the same 0.5B-parameter configuration. In zero-shot transfer to LIBERO-Plus, LIRA increases average success from 59.1% to 78.0%, an 18.9-point gain indicating improved robustness under controlled distribution shifts.

cs.RO↗

arXiv2026

HealthSLM-Bench: Benchmarking Small Language Models for Mobile and Wearable Healthcare Monitoring

Mobile and wearable healthcare monitoring play a vital role in facilitating timely interventions, managing chronic health conditions, and ultimately improving individuals' quality of life. Previous studies on large language models (LLMs) have highlighted their impressive generalization abilities and effectiveness in healthcare prediction tasks. However, most LLM-based healthcare solutions are cloud-based, which raises significant privacy concerns and results in increased memory usage and latency. To address these challenges, there is growing interest in compact models, Small Language Models (SLMs), which are lightweight and designed to run locally and efficiently on mobile and wearable devices. Nevertheless, how well these models perform in healthcare prediction remains largely unexplored. We systematically evaluated SLMs on health prediction tasks using zero-shot, few-shot, and instruction fine-tuning approaches, and deployed the best performing fine-tuned SLMs on mobile devices to evaluate their real-world efficiency and predictive performance in practical healthcare scenarios. Our results show that SLMs can achieve performance comparable to LLMs while offering substantial gains in efficiency and privacy. However, challenges remain, particularly in handling class imbalance and few-shot scenarios. These findings highlight SLMs, though imperfect in their current form, as a promising solution for next-generation, privacy-preserving healthcare monitoring.

cs.AI↗

arXiv2026

Straight-Path Flow Matching for Incomplete Multi-View Clustering

Incomplete Multi-View Clustering addresses the problem of clustering multi-modal data when certain views are missing. Recent end-to-end generative approaches leverage diffusion models to recover missing views via stochastic noise-to-data trajectories. While expressive, such mechanisms are not explicitly designed for clustering, as they initialize from cluster-agnostic noise and rely on stochastic denoising dynamics. In this work, we revisit probability path design in end-to-end generative IMVC. We introduce a flow-matching framework with a linear interpolation path between paired view representations, that replaces diffusion with probability flows between observed and missing views. We provide a formal analysis showing that deterministic ODE flows are inherently better aligned with clustering objectives than diffusion-based stochastic trajectories, especially in terms of transport mechanisms that respect class-conditional data distributions and maintain cluster consistency in finite-step regimes. Building upon this insight, we develop an end-to-end IMVC architecture that integrates straight-path flow-matching view completion with cluster-level and entropy-based alignment to enforce cross-view clustering consistency. Extensive experiments on standard IMVC benchmarks demonstrate that the proposed framework establishes new state-of-the-art performance.

cs.CV↗

arXiv2026

Pocket-Dentist: On-Device Dental Image Understanding via Efficient Multimodal Large Language Models

Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cost. This limits their widespread deployment for dental screening outside specialist centres, where timely inference, limited hardware, and local handling of patient images are vital for practical, privacy-preserving clinical prescreening. Here we present Pocket-Dentist, an efficiency-aware benchmark for dental multimodal question answering that brings together three datasets spanning approximately 1,159 patients from BRAR and MetaDent, five task types and seven metrics. Across 14 typical VLMs, our results reveal an interesting observation: compact VLMs, such as 2B-parameter models, become competitive with much larger VLMs on most metrics after lightweight adaptation while requiring substantially lower computational costs in dental image understanding. Deployed locally on an iPhone 17 Pro, our finetuned compact VLM Pocket-Dentist-2B processed each sample in 4.31 s, reducing latency by 4.9x and memory use by 2.3x compared with a 7B baseline. Our project page is available at https://2026-icml.github.io/pocket-dentist-icml.

cs.CV↗

arXiv2026

Efficient Multimodal Clinical Question Answering for Pulmonary Embolism Risk Assessment

Pulmonary embolism (PE) is a high risk cardiopulmonary condition whose management requires both timely diagnosis and reliable assessment of future clinical risk. Because PE care routinely combines computed tomography pulmonary angiography (CTPA), radiology interpretation, and longitudinal electronic health record (EHR) evidence, it provides a clinically meaningful setting for evaluating compact multimodal language models. In this work, we build a benchmark using efficient multimodal large language models (MLLMs) on INSPECT, a multimodal PE dataset containing 23,248 CTPA studies from 19,402 patients. We formulate eight diagnostic and prognostic tasks as structured clinical question answering problems and evaluate on typical efficient MLLMs under CTPA-Only, EHR-Only, and CTPA+EHR settings with zero-shot and few-shot prompting. Results show that Gemma4 E4B and Gemma4 E2B perform more strongly when EHR evidence is available, especially under CTPA+EHR input. Task level analysis further shows that PE diagnosis achieves higher performance than prognostic tasks, particularly readmission prediction. These observations suggest that compact multimodal models have the great potential in early stage PE risk detection and explanation.

cs.AI↗

arXiv2026

Localizing and Editing Knowledge in Large Audio-Language Models

Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual information. Yet they are trained on static corpora and may encode incorrect facts. Existing model editing methods localize and update facts in text-only LLMs, but do not account for continuous speech representations, or where knowledge is stored across acoustic or language modules, or their cross-modal module. We construct the first audio benchmark for knowledge localization and editing in LALMs and propose a speech-driven locate-then-edit framework. First, we use speech-aware causal tracing to localize layers and modules that support factual retrieval and then apply editing at identified sites. Experiments show that factual knowledge is jointly encoded in audio and text modules, and that audio editing yields more effective updates than text editing or fine-tuning, enabling fine-grained knowledge control in speech AI systems.

cs.LG↗

arXiv2026

VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data

Wearable devices enable continuous monitoring of physiological signals such as ECG and PPG, but existing mHealth systems are largely limited to task-specific prediction pipelines or reactive question answering over static summaries. They lack the ability to support temporal reasoning, persistent physiological context, and proactive monitoring over long-term signal streams. We propose VitalAgent, a tool-augmented agentic framework for ECG/PPG-based mHealth that supports both reactive question answering and proactive monitoring. VitalAgent is built on a longitudinal physiological memory and a tool-augmented reasoning interface that enables dynamic computation over raw signals. We further introduce VitalBench, a longitudinal physiological monitoring benchmark dataset comprising 1,862 QA pairs for reactive question answering and 90.2 hours of continuous ECG/PPG recordings for proactive monitoring, covering cardiac, physical activity, and stress-related tasks. Experiments demonstrate that VitalAgent achieves over 25% improvement over prompt-based and ReAct baselines in reactive evaluation and supports proactive alert monitoring over long-term physiological signals, highlighting the importance of dynamic tool use and long-term physiological monitoring.

cs.AI↗

arXiv2026

CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering

Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In contrast, most expressive text-to-speech systems enforce a single utterance-level emotion, collapsing affective diversity and suppressing mixed or text-emotion-misaligned expression. While activation steering via latent direction vectors offers a promising solution, it remains unclear whether emotion representations are linearly steerable in TTS, where steering should be applied within hybrid TTS architectures, and how such complex emotion behaviors should be evaluated. This paper presents the first systematic analysis of activation steering for emotional control in hybrid TTS models, introducing a quantitative, controllable steering framework, and multi-rater evaluation protocols that enable composable mixed-emotion synthesis and reliable text-emotion mismatch synthesis. Our results demonstrate, for the first time, that emotional prosody and expressive variability are primarily synthesized by the TTS language module instead of the flow-matching module, and also provide a lightweight steering approach for generating natural, human-like emotional speech.

cs.SD↗

arXiv2026

RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark

Humans process rich auditory environments through tightly integrated cognitive capabilities such as audio perception, audio reasoning, and memory. Despite recent progress in large audio-language models (LALMs) across speech understanding and multimodal audio reasoning, current evaluation paradigms remain largely task- or modality-centric, focusing on end performance while overlooking underlying auditory cognitive behaviours. This reveals a fundamental gap between how auditory cognition is understood in humans and how it is evaluated in LALMs, particularly in the lack of frameworks that operationalise cognitive principles beyond task-level metrics to systematically capture model behaviour. In this work, we introduce RAIL, a human-centric evaluation paradigm grounded in the Cattell-Horn-Carroll (CHC) cognitive framework. RAIL formalises auditory cognition into five core capabilities and develop them into structured evaluation tasks that probe how models process, retain, and integrate auditory information. We further construct a cognitively grounded benchmark with principled data curation and human-aligned evaluation protocols. Evaluating 26 state-of-the-art LALMs, we find that current models exhibit highly uneven performance across cognitive abilities. RAIL establishes a new evaluation paradigm that moves beyond task-centric benchmarking toward cognitively grounded assessment of auditory intelligence.

cs.SD↗

arXiv2026

Titans-as-a-Layer: Test-Time Memory for Conversational Speech Emotion Recognition

Speech emotion recognition (SER) is commonly formulated as utterance-level classification, although conversational emotion depends on a speaker's usual vocal range and the emotional context established by previous utterances. Speech-language models provide strong pretrained acoustic and semantic representations, and can adapts them to SER labels via finetune, but this mechanism still missing per-dialogue state. We study whether test-time neural memory can supply this missing context while leaving the large audio language models (LALMs) backbone intact. Building on Titans, we introduce a plug-and-play Memory-as-a-Layer (MAL) adapter that writes dialogue history into a small neural memory and reads it back as an audio-token-aligned residual update, avoiding changes to the host model's token positions. Across different audio LLMs and emotion recognition datasets evaluations, our design improves SER performs across different evaluation metrics, supporting test-time memory as a residual contextual mechanism for conversational SER.

cs.LG↗

arXiv2026

XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge

Deep learning for human sensing on edge systems presents significant potential for smart applications. However, its training and development are hindered by the limited availability of sensor data and resource constraints of edge systems. While transferring pre-trained models to different sensing applications is promising, existing methods often require extensive sensor data and computational resources, resulting in high costs and limited transferability. In this paper, we propose XTransfer, a first-of-its-kind method enabling modality-agnostic, few-shot model transfer with resource-efficient design. XTransfer flexibly uses pre-trained models and transfers knowledge across different modalities by (i) model repairing that safely mitigates modality shift by adapting pre-trained layers with only few sensor data, and (ii) layer recombining that efficiently searches and recombines layers of interest from source models in a layer-wise manner to restructure models. We benchmark various baselines across diverse human sensing datasets spanning different modalities. The results show that XTransfer achieves state-of-the-art performance while significantly reducing the costs of sensor data collection, model training, and edge deployment.

cs.CV↗

arXiv2026

Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory

Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech) understanding remains poorly understood, and the underlying mechanisms of representation and retrieval are still unclear. This work introduces EnvMem, a controlled multi-turn benchmark designed to study this gap and identify the root causes of failures at the representation (i.e., latent embeddings) and retrieval levels (i.e., attention allocation). We further conduct post-hoc interventions to probe representational structure and attention dynamics. Our results reveal representational trajectory drift as the key failure mode, while showing that attention allocation plays a limited role in explaining the observed degradation. Overall, we provide a systematic framework for analyzing and improving non-linguistic memory in long-context LALMs, shedding light on future data and training design for robust acoustic memory modeling.

eess.AS↗

arXiv2026

Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots

With the rapid advancement of large language models (LLMs), mobile agents have emerged as promising tools for phone automation, simulating human interactions on screens to accomplish complex tasks. However, these agents often suffer from low accuracy, misinterpretation of user instructions, and failure on challenging tasks, with limited prior work examining why and where they fail. To address this, we introduce DailyDroid, a benchmark of 75 tasks in five scenarios across 25 Android apps, spanning three difficulty levels to mimic everyday smartphone use. We evaluate it using text-only and multimodal (text + screenshot) inputs on GPT-4o and o4-mini across 300 trials, revealing comparable performance with multimodal inputs yielding marginally higher success rates. Through in-depth failure analysis, we compile a handbook of common failures. Our findings reveal critical issues in UI accessibility, input modalities, and LLM/app design, offering implications for future mobile agents, applications, and UI development.

cs.HC↗