arXiv subjects

Yansong Liu

Publications and source records attributed to Yansong Liu.

12 recordsLinked to original sources

arXiv2026

Enhancing Speech Large Language Models through Reinforced Behavior Alignment

Speech large language models (SpeechLMs) can process spoken requests, yet still lag behind text-prompted large language models (LLMs) on instruction following and reasoning. We argue that this gap is not only an ASR or representation problem: the same semantic instruction can induce different response policies when spoken with different speakers, accents, noise conditions, prosody, or disfluencies. We propose Verifiable Invariant Reinforced Behavior Alignment (VIRBA), a reinforcement-learning framework for aligning SpeechLM behavior across acoustic realizations of the same semantic intent. VIRBA builds multi-view spoken instruction groups, scores sampled responses with semantic preference, rule-verifiable correctness, cross-acoustic invariance, and adaptive reasoning rewards, and optimizes the model with Cross-Acoustic Group Relative Policy Optimization (CA-GRPO). The resulting objective moves SpeechLM alignment beyond teacher imitation toward robust reasoning policies that remain stable across realistic spoken realizations. Experiments with recent SpeechLM baselines, disfluency robustness, spoken QA, audio reasoning, and speech-to-text translation show the largest gains on reasoning-heavy and acoustically perturbed spoken prompts.

cs.CL↗

arXiv2026

MiMaAlign: Hierarchical Micro-Macro Alignment for Physically Plausible Video Generation

Text-to-video (T2V) diffusion models have made remarkable progress in generating high-fidelity visuals, yet their outputs still often exhibit physically implausible phenomena, including discontinuous dynamics and implausible event interactions. Existing representation alignment methods mainly transfer generic video features or short-range motion cues, treating physical plausibility as a single-level representation problem. To address this issue, we propose MiMaAlign, a hierarchical micro-macro alignment framework that transfers complementary dynamics-oriented and event-oriented knowledge into different abstraction depths of a pretrained video diffusion model. Specifically, micro-level continuous dynamics alignment imposes constraints by aligning diffusion features with a continuous-time motion representation learned by a Neural Ordinary Differential Equation (Neural ODE), while macro-level event-commonsense alignment provides representations of object interactions and event semantics through an instruction-prompted vision-language model (VLM). With training-only auxiliary objectives, we align the complementary supervision from the two teachers with shallower and deeper generator features, respectively, enabling the generator to internalize the corresponding physical priors. Empirical evaluations show that, on CogVideoX-2B, MiMaAlign achieves a relative improvement of up to 21.0% in the Physical Commonsense (PC) score on the VideoPhy benchmark over the baseline, and also delivers substantial gains on the highly challenging VideoPhy2 benchmark, while maintaining general video quality on VBench and being supported by blind user comparisons.

cs.CV↗

arXiv2026

Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning

Few-Shot Class-Incremental Learning (FSCIL) addresses the challenge of learning new classes from very limited samples while retaining knowledge of previously learned ones. Although parameter-efficient fine-tuning methods with pre-trained models show promise for class-incremental learning, strict gradient-based constraints can be unreliable under severe data scarcity, while multi-expert approaches can impose substantial inference-time costs. We propose TALON (Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer), an inference-efficient FSCIL framework. TALON dynamically allocates an independent LoRA-Teacher to each incremental task for task-specific representation learning, then distills multiple frozen teachers into a unified LoRA-Student through Ensemble Knowledge Transfer, eliminating runtime module selection or generation. A semantic-guided distillation strategy weights teacher contributions by feature-space similarity to mitigate catastrophic forgetting and overfitting. Across three class-order runs, TALON achieves comparable or better mean average accuracy across four FSCIL benchmarks, obtaining 86.68 +/- 1.22% on CUB200, 90.39 +/- 0.27% on CIFAR100, 78.38 +/- 0.94% on ImageNet-R, and 96.34 +/- 0.33% on miniImageNet. TALON uses up to 33x fewer deployment parameters and reduces average inference time per task to 26.7 s, a 41.70% reduction relative to ASP.

cs.LG↗

arXiv2026

Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning

Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulative interference and suboptimal alignment between inference samples and specialized modules. We propose Dynamic LoRA-Experts and Prototype-Ensemble Matching (DLEPEM), a two-stage rehearsal-free framework. DLEPEM allocates a task-specific LoRA-Expert for each incremental task to reduce cross-task interference, then combines frozen pre-trained-model prototypes with task-adaptive LoRA-Expert prototypes for reliable task-level discrimination. Experiments on standard CIL and Few-Shot CIL benchmarks demonstrate strong performance under the evaluated protocols.

cs.LG↗

arXiv2026

Prediction bias in biological ageing markers

Biological ageing markers have attracted growing interest, with models estimating age from organ imaging or blood biomarkers. An estimated age above chronological age or the age-specific population expectation is assumed to reflect accelerated ageing and poorer health. Previous research has supported this assumption through positive associations between disease and age gaps or acceleration. However, in this study, we identified a widespread health-dependent prediction bias in ageing markers that affects their key interpretation and application. Specifically, we investigated five ageing markers derived from retinal images, brain MRI, chest radiographs, abdominal CT, and blood tests, and evaluated them using association analyses. We observed the well-recognised phenomenon of regression to the mean (RTM) in the four organ-image based markers, whereby estimated ages were shifted towards the mean age of the training cohort. More importantly, we revealed that the strength of RTM varied with health status, with stronger RTM in unhealthy than in healthy individuals. This differential RTM introduced a health-dependent prediction bias that persisted after calibration and systematically altered associations across age subgroups, suggesting that whole cohort associations may not reflect those observed within individual age subgroups. Additionally, we showed that the tested ageing markers, including PhenoAge derived from blood biomarkers, had limited ability to distinguish health status at the individual level. These findings call for careful interpretation of biological ageing markers and their use in clinical studies, and highlight the need for further development and validation before these ageing markers can reliably inform individual health assessments.

q-bio.QM↗

arXiv2026

HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation

Extrapolative temporal knowledge graph reasoning (TKGR) predicts future facts from historical snapshots. Most existing methods train once on an early prefix of the timeline and then use a frozen model for all future timestamps. We argue that this fixed-prefix protocol is misaligned with extrapolation. It learns from a static prefix, whereas the target stream is non-stationary: new entities and facts emerge, temporal dependencies shift across regimes, and recurring historical signals must be refreshed online. As a result, models trained only on early snapshots become outdated and degrade over long horizons. We address this mismatch by formulating extrapolative TKGR as continual learning over streaming snapshots. Under this view, effective extrapolation must jointly handle current dynamics, stable knowledge, and recurring historical evidence. Based on these requirements, we propose History-enhanced Two-Step Continual Learning (HiTS-CL), a backbone-agnostic continual learning framework for extrapolative TKGR. HiTS-CL tracks current dynamics via continual fine-tuning, preserves stable knowledge via multi-teacher adaptive distillation, and retains recurring historical evidence via a selective memory of recent and frequent facts. We integrate HiTS-CL into five representative TKGR backbones and evaluate it on four benchmark datasets. HiTS-CL consistently improves extrapolation accuracy, reduces long-horizon degradation, and outperforms strong continual-learning baselines, including a recent method for temporal knowledge graphs. Source code and data are available at https://github.com/liuyansong98/HiTS-CL.

cs.LG↗

arXiv2026

AI-driven Optimisation of Quality of Recovery (QoR) in Remote Patient Monitoring

Remote patient monitoring depends on patient-reported data to capture the subjective dimension of recovery that devices cannot measure. The Quality of Recovery (QoR-15) survey is the gold-standard instrument for this purpose. It was designed and validated for occasional in-hospital assessment, yet remote monitoring now administers it to patients daily. In our own post-surgical deployment, only 55% of patients submitted the survey more than 14 days of 30 monitoring days. We developed QoR-compact, a five-item daily input for the RPM prediction pathway. Setting a deployment-driven target of one-third of the daily items, we exhaustively evaluated all 3,003 five-question subsets of the QoR-15 and tested whether the best of them matches the full instrument in predicting near-term postoperative recovery severity. QoR-compact achieves a mean AUC-ROC of 0.968 (95% CI 0.915-0.988), statistically comparable to the 0.964 baseline obtained with one-third of the items. Patient-level backtesting indicates that it tracks readmission events as faithfully as the full form. Its five items span the physical and psychological axes of recovery: Q3 (feeling rested), Q9 (feeling comfortable and in control), Q10 (general well-being), Q12 (severe pain), and Q14 (feeling worried or anxious). The QoR-15 remains the gold-standard measure of recovery; QoR-compact complements it as a shorter daily input designed for prediction. This parity provides the basis for a prospective study of whether a lighter daily input is, in turn, completed more consistently. External validation on larger cohorts is required before clinical use.

cs.AI↗

arXiv2026

Strategy-Aware Optimization Modeling with Reasoning LLMs

Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect formulations and inefficient solver behavior. We propose SAGE, a strategy-aware framework that makes Modeling Strategy explicit in both data construction and post-training. SAGE builds a solver-verified multi-strategy dataset and trains a student model with supervised fine-tuning followed by Segment-Weighted GRPO using a composite reward over format compliance, correctness, and solver efficiency. Across eight benchmarks spanning synthetic and real-world settings, SAGE improves average pass@1 from 72.7 to 80.3 over the strongest open-source baseline. With multiple generations, SAGE discovers more distinct correct formulations and improves component-level diversity at pass@16 by 19-29%. At the largest scale, SAGE produces more compact constraint systems with 14.2% fewer constraints than the baseline, consistent with solver-efficient modeling. Overall, these results show that making Modeling Strategy explicit improves automated optimization modeling. Code is available at https://github.com/rachhhhing/SAGE.

cs.AI↗

arXiv2026

Multi-Modal AI for Remote Patient Monitoring in Cancer Care

For patients undergoing systemic cancer therapy, the time between clinic visits is full of uncertainties and risks of unmonitored side effects. To bridge this gap in care, we developed and prospectively trialed a multi-modal AI framework for remote patient monitoring (RPM). This system integrates multi-modal data from the HALO-X platform, such as demographics, wearable sensors, daily surveys, and clinical events. Our observational trial is one of the largest of its kind and has collected over 2.1 million data points (6,080 patient-days) of monitoring from 84 patients. We developed and adapted a multi-modal AI model to handle the asynchronous and incomplete nature of real-world RPM data, forecasting a continuous risk of future adverse events. The model achieved an accuracy of 83.9% (AUROC=0.70). Notably, the model identified previous treatments, wellness check-ins, and daily maximum heart rate as key predictive features. A case study demonstrated the model's ability to provide early warnings by outputting escalating risk profiles prior to the event. This work establishes the feasibility of multi-modal AI RPM for cancer care and offers a path toward more proactive patient support.(Accepted at Europe NeurIPS 2025 Multimodal Representation Learning for Healthcare Workshop. Best Paper Poster Award.)

cs.LG↗

arXiv2025

RISE-T2V: Rephrasing and Injecting Semantics with LLM for Expansive Text-to-Video Generation

Most text-to-video(T2V) diffusion models depend on pre-trained text encoders for semantic alignment, yet they often fail to maintain video quality when provided with concise prompts rather than well-designed ones. The primary issue lies in their limited textual semantics understanding. Moreover, these text encoders cannot rephrase prompts online to better align with user intentions, which limits both the scalability and usability of the models, To address these challenges, we introduce RISE-T2V, which uniquely integrates the processes of prompt rephrasing and semantic feature extraction into a single and seamless step instead of two separate steps. RISE-T2V is universal and can be applied to various pre-trained LLMs and video diffusion models(VDMs), significantly enhancing their capabilities for T2V tasks. We propose an innovative module called the Rephrasing Adapter, enabling diffusion models to utilize text hidden states during the next token prediction of the LLM as a condition for video generation. By employing a Rephrasing Adapter, the video generation model can implicitly rephrase basic prompts into more comprehensive representations that better match the user's intent. Furthermore, we leverage the powerful capabilities of LLMs to enable video generation models to accomplish a broader range of T2V tasks. Extensive experiments demonstrate that RISE-T2V is a versatile framework applicable to different video diffusion model architectures, significantly enhancing the ability of T2V models to generate high-quality videos that align with user intent. Visual results are available on the webpage at https://rise-t2v.github.io.

cs.CV↗

arXiv2025

Joint Knowledge and Power Management for Secure Semantic Communication Networks

Recently, semantic communication (SemCom) has shown its great superiorities in resource savings and information exchanges. However, while its unique background knowledge guarantees accurate semantic reasoning and recovery, semantic information security-related concerns are introduced at the same time. Since the potential eavesdroppers may have the same background knowledge to accurately decrypt the private semantic information transmitted between legal SemCom users, this makes the knowledge management in SemCom networks rather challenging in joint consideration with the power control. To this end, this paper focuses on jointly addressing three core issues of power allocation, knowledge base caching (KBC), and device-to-device (D2D) user pairing (DUP) in secure SemCom networks. We first develop a novel performance metric, namely semantic secrecy throughput (SST), to quantify the information security level that can be achieved at each pair of D2D SemCom users. Next, an SST maximization problem is formulated subject to secure SemCom-related delay and reliability constraints. Afterward, we propose a security-aware resource management solution using the Lagrange primal-dual method and a two-stage method. Simulation results demonstrate our proposed solution nearly doubles the SST performance and realizes less than half of the queuing delay performance compared to different benchmarks.

eess.SP↗

arXiv2024

MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability

This work aims to address the multi-view perspective RGB generation from text prompts given Bird-Eye-View(BEV) semantics. Unlike prior methods that neglect layout consistency, lack the ability to handle detailed text prompts, or are incapable of generalizing to unseen view points, MVPbev simultaneously generates cross-view consistent images of different perspective views with a two-stage design, allowing object-level control and novel view generation at test-time. Specifically, MVPbev firstly projects given BEV semantics to perspective view with camera parameters, empowering the model to generalize to unseen view points. Then we introduce a multi-view attention module where special initialization and de-noising processes are introduced to explicitly enforce local consistency among overlapping views w.r.t. cross-view homography. Last but not least, MVPbev further allows test-time instance-level controllability by refining a pre-trained text-to-image diffusion model. Our extensive experiments on NuScenes demonstrate that our method is capable of generating high-resolution photorealistic images from text descriptions with thousands of training samples, surpassing the state-of-the-art methods under various evaluation metrics. We further demonstrate the advances of our method in terms of generalizability and controllability with the help of novel evaluation metrics and comprehensive human analysis. Our code, data, and model can be found in \url{https://github.com/kkaiwwana/MVPbev}.

cs.CV↗