Searcharxiv⌕ Search

arXiv subjects

Chen Shen

Publications and source records attributed to Chen Shen.

At least 37 records · Page 2Linked to original sources

MedUAG: Unified Understanding and Generation for Medical Multimodal Models

Recent Multimodal Large Language Models (MLLMs) are rapidly evolving into unified understanding and generation (UAG) frameworks. However, extending these unified paradigms to the medical domain is hindered by: the absence of comprehensive training and evaluation benchmarks, and the lack of broadly validated unified medical model. To address these gaps, we present a comprehensive foundation for medical UAG. First, we construct MedUAGCorpus, the largest unified medical understanding and generation dataset to date, comprising over 6 million instances across 14 imaging modalities. Second, we introduce MedUAGBench, a systematic benchmark that expands medical generation evaluation to 12 diverse tasks under standardized protocols. Finally, leveraging these resources, we develop MedUAG, an end-to-end trained unified medical model. Extensive experiments demonstrate that MedUAG achieves strong performance across a wide array of understanding and generation tasks, establishing a competitive baseline and paving the way for next-generation medical multimodal systems.

cs.CL↗

Empowering Polymeric Materials Discovery by Artificial Intelligence

Polymeric materials underpin modern technologies spanning energy storage, microelectronics, healthcare and sustainable manufacturing. Yet their rational design remains exceptionally challenging because material performance emerges from complex interactions among molecular composition, chain architecture, processing history and hierarchical structural evolution across multiple length and time scales. Consequently, polymer research has long relied on labor-intensive experimentation and fragmented modeling approaches, limiting both mechanistic understanding and innovation efficiency. Recent advances in data infrastructure, machine learning, large artificial intelligence (AI) models and laboratory automation are beginning to reshape this landscape. Rather than functioning as isolated tools, polymer databases, predictive models, AI agents and automated laboratories are increasingly converging into interconnected discovery ecosystems. As a result, the central challenge is shifting from improving predictive accuracy alone to enabling reliable decision-making, adaptive learning and seamless integration across computation, experimentation and scientific reasoning. We argue that polymer science is entering an era of autonomous discovery, in which data, simulation, reasoning and experimentation operate within self-improving feedback loops that continuously generate hypotheses, design materials, execute experiments and refine predictive models. By unifying molecular design, process optimization, experimental validation and industrial translation, such autonomous ecosystems establish a more predictive, reproducible and scalable paradigm for polymer innovation, fundamentally transforming how polymer research is conducted.

physics.chem-ph↗

Complete strategy spaces reveal hidden pathways to cooperation

Understanding how cooperation emerges and persists is a central challenge in evolutionary game theory. Existing models often rely on restricted, hand-picked strategy sets, which can overlook critical behavioural pathways. A recent four-strategy framework showed that cheap talk can promote cooperation through local interactions, yet it remained unclear whether modelled strategies might alter these conclusions. Here, we extend this framework to the complete set of eight strategies that naturally arise from communication and decision-making rules. We show that incorporating the full strategy space dramatically changes the evolutionary landscape. Cooperation becomes both more robust and more versatile, driven by novel pathways absent in the restricted model. In particular, we uncover a previously overlooked mechanism in which suspicious cooperation catalyses a cyclic dynamic that sustains cooperation. Conversely, the assumed role of strategic defection in the biased model is fragile, acting mainly as a spoiler rather than a genuine evolutionary attractor. The complete model further reveals a rich spectrum of long-term behaviours, including stable coexistence among up to seven strategies and time-varying patterns of partial coexistence. These results demonstrate that the full strategy space unlocks hidden routes to cooperative behaviour and highlight the importance of comprehensive modelling when explaining the emergence of cooperation.

q-bio.PE↗

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs. We audit two widely used safety-guard training datasets, WildGuardMix and GR-Train, and find that among responses to harmful prompts, refusal expressions co-occur almost exclusively with unharmful labels. This imbalance motivates what we term the refusal-cue shortcut: inserting a refusal cue into a harmful response could flip the guard's verdict from harmful to unharmful. The shortcut affects not only guards trained on these datasets but also officially released models such as LlamaGuard3 and Qwen3Guard whose training data is undisclosed. It persists across response positions and is generally stronger in smaller variants within a family. To mitigate it, we adapt sparse complementary masking as a lightweight post-hoc intervention that identifies and suppresses a small set of shortcut-associated attention heads and MLP neurons without retraining. On two primary benchmarks, the intervention achieves an approximately 79% relative reduction in response-initial detection failures induced by refusal cues, while preserving standard detection performance. Although optimized using cues at a single response position, the suppression effect transfers to unseen positions and datasets, suggesting that shortcut manifestations across positions are partly mediated by shared internal components. Further analysis provides evidence that shortcut reliance and legitimate refusal recognition are partially functionally separable, as suppressing the shortcut broadly preserves the guard's ability to recognize genuine refusals.

cs.AI↗

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy

Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the supporting evidence within those papers. Conventional retrieval-augmented generation typically addresses both through similarity search over fixed-length passages, flattening document structure and separating scientific claims from their methodological and argumentative context. We present VecTree-RAG, an agentic framework that assigns these tasks to complementary retrieval mechanisms. Vector search ranks compact document and section representations across the corpus, whereas reasoning-guided traversal of source-verified section trees localizes evidence within shortlisted papers. Full text is retained in a page store and exposed progressively only after structural localization. We evaluate VecTree-RAG on 300 QASPER questions, an open-access subset of 54 LitQA2 questions, and 49 multi-document MOSAIC questions. Compared with Dense RAG, reranked Dense RAG, RAPTOR, and Search-o1, VecTree-RAG obtained the highest observed answer score on all three benchmarks, reaching 0.800 LLM-judge correctness on QASPER, 0.925 accuracy on LitQA2, and a 0.547 composite score on MOSAIC. On QASPER, its evidence-page precision was 0.274, compared with 0.046--0.071 for the baselines. LitQA2 ablations further showed that the complete vector--tree architecture required fewer inference tokens than variants without tree navigation or corpus-level vector routing. These results indicate that vector retrieval narrows the corpus-level search space and tree navigation concentrates reading on structurally relevant evidence. Although multi-turn inference remains more expensive than single-call retrieval, VecTree-RAG provides a structure-aware and traceable architecture for scientific literature question answering.

cs.IR↗

Strain-Tunable Shift Current and Magneto-Optical Kerr Effect in Multiferroic Altermagnet Fe2Mo3O8

Altermagnetism has recently emerged as a compelling frontier in spintronics, seamlessly merging the agile tunability of ferromagnets with the hallmark merits of antiferromagnets. As a prototypical polar multiferroic featuring distinctive altermagnetism, Fe2Mo3O8 hosts an ideal playground for exploring the intricate interplay among ferroelectric polarization, altermagnetic order, and spin-dependent responses. Here, employing first-principles calculations, we systematically investigate the coupling among polarization, spin splitting, shift current, and magneto-optical responses in Fe2Mo3O8. Our findings reveal that switching the ferroelectric polarization not only inverts the sign of the shift current but also comprehensively reshapes the momentum-space spin-splitting texture. Furthermore, the shift current and magneto-optical spectrum exhibits strong tunability under mechanical strain. Remarkably, the application of a-axis uniaxial strain breaks the crystalline symmetry, thereby activating a finite magneto-optical Kerr effect that is otherwise forbidden in the pristine phase.

cond-mat.mtrl-sci↗

Deep-learning Hamiltonian reveals twist-tunable flat bands and nonlinear photocurrents in SrTiO3 moire bilayers

The extension of moire physics to complex oxides offers new ways to manipulate electronic states, but the large oxide moire supercells make systematic first-principles calculations demanding. Here, we combine density functional theory with the E(3)-equivariant deep-learning Hamiltonian framework DeepH-E3 to investigate the twist-angle-dependent electronic structure and optical responses of twisted bilayer SrTiO3. The model is trained on untwisted bilayers with different interlayer-sliding configurations and then applied to commensurate twisted bilayers with twist angles from 8.80 degrees to 53.13 degrees. Compared with the untwisted bilayer, decreasing twist angle systematically flattens the valence bands and leads to nearly dispersionless bands at the smallest angles studied. Based on the predicted Hamiltonians, we evaluate the dielectric response, second-harmonic generation (SHG), shift current, and spin Hall conductivity. The dielectric response and spin Hall conductivity remain close to those of the untwisted bilayer, whereas the nonlinear optical responses are more strongly affected by twisting. SHG is strongly enhanced relative to the weak untwisted response, and the shift current shows a clear twist-angle dependence within the response-calculation range (53.13 degrees-22.62 degrees). These results show that twist engineering can control electronic and optoelectronic responses in oxide moire systems.

cond-mat.mtrl-sci↗

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think

On-policy self-distillation (OPSD) has emerged as a promising paradigm for improving LLM reasoning, where a privileged teacher with access to reference solutions provides token-level supervision on the student's own generated trajectories. However, we find that OPSD consistently fails on long chain-of-thought (long-CoT) reasoning models, yielding at best marginal gains while destabilizing the reflective reasoning capability these models depend on. Through a novel decomposition of the teacher's supervision signal, we identify the root cause: the teacher's supervision is dominated by a reference-induced component that drives rote memorization of reference-specific shortcuts, while the question-conditioned, inference-transferable component is ignored or actively opposed. Based on this diagnosis, we propose a two-step solution. First, we construct a reference-only teacher (the same model conditioned on the reference without the question) to isolate the non-transferable component of the supervision signal; the residual after subtracting this component captures the question-conditioned, inference-transferable correction. Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution that the student can directly distill from, filtering out the reference-induced shortcut. Experiments on four long-CoT models across two datasets demonstrate consistent improvements over both the base model and standard OPSD, while preserving the models' natural epistemic behavior throughout training.

cs.AI↗

Thermal Transport in SiC with Intrinsic Defects and Mg Transmutation Products

Silicon carbide is a leading candidate material for advanced nuclear energy systems, but irradiation-induced defects and transmutation products can severely degrade its thermal conductivity. In fusion environments, Mg is predicted to be a major solid transmutant in SiC, yet it is not well understood how different Mg-related defects affect phonon transport. Here, we develop a machine-learning interatomic potential, MLIP4SiC-Mg, for 3C-SiC containing intrinsic point defects, Mg-related defects, and Mg-defect complexes. The potential is trained on a large DFT dataset and reproduces DFT energies, forces, equation-of-state behavior, phonon dispersions, and lattice thermal conductivities with near-DFT accuracy. Combined with Green-Kubo molecular dynamics, force-error correction, and a resistance-based treatment for dilute defective systems, MLIP4SiC-Mg enables quantitative thermal-conductivity calculations in large defective supercells. The corrected thermal conductivity of pristine 3C-SiC is 421 W/(mK) at 300 K, in good agreement with available experimental data. All defects considered strongly reduce thermal conductivity, but their scattering strengths are highly configuration dependent. V_C and Mg_TC act as strong phonon scatterers, whereas isolated Mg_Si is comparatively weak. Residual thermal resistivity analysis shows that defect-induced thermal resistance is not strictly linear with concentration and should be treated as an effective temperature- and concentration-dependent scattering metric. Mg_Si-V_C clustering enhances scattering relative to isolated Mg_Si, but reduces the total excess resistance relative to spatially separated Mg_Si and V_C defects. These results clarify the configuration-dependent role of Mg transmutation in irradiation-degraded SiC and provide an atomistic framework for quantifying defect-controlled heat transport in nuclear ceramics.

cond-mat.mtrl-sci↗

Quantifying surfactant adsorption at fluid interfaces by combining X-ray reflectivity and simulations

Adsorption of surfactants to fluid interfaces occurs in numerous daily-life and technological contexts. The surfactant surface coverage $Γ$ governs interface characteristics like tension $γ$, viscoelastic properties, and the stability of thin foam films. Directly measuring $Γ$ as a function of the bulk concentration $c$ is highly desirable but challenging, particularly for non-ionic surfactants that lack easily detectable labels. Neutron reflectometry is currently the only generally applicable method, but it is not available for routine experiments. Here, we propose a simulation-assisted approach to deduce the adsorption isotherm $Γ(c)$ from X-ray reflectivity data: As a first step, we use atomistic molecular dynamics simulations of surfactant-loaded air/water interfaces with prespecified $Γ$ to obtain interfacial electron density profiles. From these profiles, we compute theoretical X-ray reflectivity curves and compare them with experimental measurements to determine the matching bulk concentration. We focus on two non-ionic surfactants (C$_{12}$EO$_6$ and $β$-C$_{12}$G$_2$}) with previously established force fields to illustrate how this combined approach of experiments and simulations can determine the adsorption isotherm. Additional insights are gained through comparison with the measured surface tension isotherms $γ(c)$, based on the equation of state $γ(Γ)$ from simulations.

cond-mat.soft↗

How Can Machine Learning Accelerate CALPHAD Free Energy Modeling?

The CALPHAD framework provides a rigorous basis for thermodynamic modeling, yet its ability to predict new chemistries is restricted by limited data and by functional forms that rely heavily on composition alone. Here, we show that machine learning (ML) can address these challenges through a hybrid strategy that learns Redlich-Kister (RK) interaction coefficients directly from physically informed elemental descriptors. Using formation energies of 14-element FCC alloys generated by a universal machine-learning interatomic potential (MLIP), we benchmark three classes of models: (1) composition-based RK and ML models, (2) descriptor-based ML models, and (3) a combined ML-augmented RK approach (ML4RK). Leave-one-element-out tests highlight complementary strengths. RK models, class (1), remain the most data-efficient when binary information is available, while descriptor-based ML models, class (2), enable genuine zero-shot extrapolation to elements absent from the training set. By embedding elemental descriptors into the RK framework, the hybrid approach unifies these regimes and enables prediction of interaction parameters for otherwise unknown or data-scarce binaries, class (3). This work demonstrates a physically grounded and data-efficient route to extend CALPHAD models by combining the transferability of ML with the physical grounding, interpretability, data efficiency, and robustness of thermodynamic formalisms.

cond-mat.mtrl-sci↗

Medium-Throughput Evaluation of Quantum Geometry-Driven Topological Transports in Altermagnets

Altermagnets provide a promising platform for a wide spectrum of applications integrating advantages of conventional ferromagnets and antiferromagnets. In this work, we implement a medium-throughput first-principles workflow and evaluate topological transport properties driven by quantum geometry for 135 altermagnets in the MAGNDATA database. Based on automated Wannier construction, both linear and nonlinear responses, including the anomalous Hall effect, magneto-optical Kerr effect, and bulk photovoltaic effect, are evaluated with further symmetry verifications. Detailed analysis is done on representative cases like metallic VNb3S6 with enhanced anomalous Hall conductivity, CaIrO3 with giant MOKE, and CuFeS2 with large shift current in non-centrosymmetric. These results establish a symmetry-guided computational route for identifying experimentally accessible fingerprints and functional transport properties in altermagnets.

cond-mat.mtrl-sci↗

Enhanced-BLE: A Hybrid BLE-ESB Framework for Dynamically Reconfigurable and Energy-Efficient 2.4 GHz IoT Communication

Bluetooth Low Energy (BLE) is widely used in IoT systems because of its low power consumption, interoperability, and reliable bidirectional communication. However, its connection-oriented architecture introduces trade-offs among wake-up latency, throughput, and energy efficiency, limiting its suitability for burst-mode and on-demand sensing applications. Enhanced ShockBurst (ESB), a lightweight connectionless protocol supported by the same 2.4 GHz Nordic Semiconductor hardware, enables fast wake-up and efficient data transmission, but does not provide BLE-level robustness for sustained bidirectional communication. This work systematically benchmarks BLE and ESB on a unified Nordic nRF54L15 platform and proposes Enhanced-BLE, a hybrid framework that integrates the two protocols to extend conventional BLE operation. Experimental results show that ESB nearly halves packet transmission time and energy compared with BLE, doubles the achievable forward throughput, and reduces wake-up latency and energy by nearly twentyfold during intermittent operation. However, ESB reverse transmission may suffer packet loss, whereas BLE maintains reliable bidirectional communication. Enhanced-BLE addresses this trade-off through adaptive radio scheduling and coexistence-aware connection management, combining ESB-based high-throughput forward transmission with BLE-based reliable reverse communication. The framework enables BLE-to-ESB handover within approximately 18 ms and restores BLE operation within 49 ms from standby mode. Enhanced-BLE also achieves approximately twofold higher forward throughput than BLE while reducing wake-up latency. These results demonstrate a practical and hardware-compatible strategy for low-latency, high-throughput, energy-efficient, and reliable 2.4 GHz IoT communication.

cs.NI↗

Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection

The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critical research topic. Traditional MD approaches based on small models typically perform binary classification through a black-box process. Recently, the rise of Large Language Models (LLMs) has enabled explainable MD, where models generate rationales that explain their decisions, thereby enhancing transparency. Existing explainable MD methods primarily focus on crafting sophisticated prompts to elicit rationales from off-the-shelf LLMs. In this work, we propose a pipeline to fine-tune a dedicated LLM specifically for explainable MD. Our pipeline begins by collecting large-scale fact-checked articles, and then uses multiple strong LLMs to produce veracity predictions and rationales. To ensure high-quality training data, we leverage a filtering strategy that selects only the correct instances for fine-tuning. While this pipeline is intuitive and prevalent, our experiments reveal that naive filtering based solely on label correctness is insufficient in practice and suffers from two critical limitations: (1) Coarse-grained labels cause insufficient rationales: Rationales filtered solely based on binary labels are insufficient to adequately support their decisions; (2) Over-verification behavior causes unnecessary rationales: Stronger LLMs tend to exhibit over-verification behavior, producing excessively verbose and unnecessary rationales. To address these issues, we introduce LONSREX, a novel data synthesis pipeline to Locate Necessary and Sufficient Rationales for Explainable MD. Specifically, we propose a metric that quantifies the contribution of each verification step to the final prediction, thereby evaluating its necessity and sufficiency. Experimental results demonstrate the effectiveness of LONSREX.

cs.CL↗

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation

Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computational overhead hinders real-world deployment. LLM reasoning distillation addresses this by transferring reasoning capabilities from formidable teacher models to compact student models. However, existing distillation paradigms face a fundamental dilemma. Typical off-policy distillation strictly utilizes teacher-generated golden trajectories, suffering from an exposure bias due to the mismatch between training distributions and student-generated inference contexts, which leads to error cascades in long CoT reasoning. To address this, on-policy distillation allows students to explore their own trajectories, but we demonstrate that it inherently introduces a reciprocal reversed exposure bias: the teacher model also struggles to provide positive guidance when conditioned on student-generated sub-optimal contexts. To resolve this dual exposure biases problem, we propose Monitoring Trajectories and Backtracking when it strays (MOTAB), a new LLM reasoning distillation pipeline. Specifically, MOTAB dynamically monitors the student's on-policy generation against an adaptive safety boundary. When the generation strays and exceeds this threshold, MOTAB backtracks to the last safe state and leverages teacher intervention to correct the course. This approach inherently tolerates minor student errors to mitigate exposure bias, while preventing sub-optimal contexts to circumvent reversed exposure bias. Extensive experiments on the LIMO-v2 and AceReason datasets demonstrate that MOTAB effectively alleviates the dual exposure biases, yielding a roughly 3% average performance improvement in reasoning tasks.

cs.CL↗

Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables

LLM-curated tables can appear source-grounded while containing unsupported rows: the curator may recall entries from parametric memory and retroactively attach page-level citations that are not the actual source. We study this hazard in Seed2Frontier discovery: the task of finding complement Wikipedia pages from a seed page to assemble a structured table. Stage-Audit addresses it with disjoint curator-auditor write rights, a row-level source-citation gate, and a 12-check audit taxonomy over keys, schema, source roles, cardinality, and scope. On a curated 51-instance Seed2Frontier evaluation set spanning 15 top-level domains, Stage-Audit improves source-frontier precision over a vanilla LLM curator from 0.356 to 0.505 (+42% relative) and F1 from 0.334 to 0.451 (+35%), while maintaining explicit per-row source traceability. The vanilla-LLM-vs-Stage-Audit comparison isolates the policy contribution rather than LLM-based discovery in general.

cs.CL↗

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization

LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is hindered by unreliable semantic rewards derived from sparse test cases or restrictive reference translations. We argue that a robust semantic reward for code translation must be derived directly from the source code. In this paper, we propose CTO to improve code translation with syntax-guided and semantic-aware preference optimization. Through contrastive learning, we train a cross-lingual semantic model to directly assess functional equivalence between source and translated code. By formulating code translation as a multi-objective optimization problem, this robust semantic signal is seamlessly unified with compiler-based syntactic feedback within the direct preference optimization framework. Extensive experiments on C++, Java, and Python translations demonstrate that CTO significantly outperforms existing baselines and alternative preference optimization strategies.

cs.AI↗

Physics-Grounded Understanding of Thermal Boundary Conductance between Ga$_2$O$_3$ and SiC from a Feedforward Neural Network Potential

Ga$_2$O$_3$/SiC heterointegration is attractive for ultra-wide-bandgap power electronics, but interfacial thermal boundary conductance (TBC) remains a major heat-removal bottleneck. Direct experimental access to intrinsic atomistic interfacial transport remains limited, particularly for ideally synthesized materials with defect-free interfacial contact. First-principles simulations are too expensive at relevant length and time scales, while empirical Molecular Dynamics (MD) potentials often lack transferability across oxide and carbide bonding environments. We develop a unified feedforward neural network potential and validate it against density-functional data, bulk phonon dispersions, and anisotropic thermal-conductivity trends in both $β$-Ga$_2$O$_3$ and SiC. Nonequilibrium simulations show that TBC decreases with transport length, increases with temperature, and is consistently higher for Ga$_2$O$_3$$(\bar{2}01)$/SiC(0001) than for Ga$_2$O$_3$(100)/SiC(0001). These trends are explained by attenuation of long-mean-free-path carriers, enhanced incoherent and anharmonic interfacial exchange within broadly unchanged spectral channels, and stronger bonding and vibrational coupling at the $(\bar{2}01)$ interface. The results show how a single transferable feedforward neural network potential can enable large-scale transport prediction and physics-grounded mechanistic understanding of thermal boundary conductance. Code for NEP training and simulation workflows is available at the project repository https://github.com/knowhow07/TBC_Ga2O3_SiC.git

cond-mat.mtrl-sci↗