arXiv subjects

Yi Zhao

Publications and source records attributed to Yi Zhao.

At least 37 records · Page 2Linked to original sources

arXiv2026

Measuring the Novelty of Biomedical Papers Using the Latent Distances between Knowledge Units

Measuring the novelty of scientific papers is a central concern in research evaluation and scientometrics. From a recombination perspective, prior studies have largely focused on the co-occurrence of knowledge units to assess the novelty of scientific papers. However, these studies often overlook other relationships between knowledge units. This narrow view may result in inaccurate or incomplete evaluations of novelty for scientific papers. To fill this gap, this study introduces a comprehensive novelty measurement that incorporates three types of relationships between knowledge units: network, semantic, and hierarchical. These relationships are used to quantify the latent distances among knowledge units. Using a dataset of 142,036 articles published in PLoS ONE and a validation dataset from the H1 Connect platform, our results demonstrate that (1) each relationship type captures distinct latent distances between MeSH terms; (2) compared to the widely used indicators proposed by Uzzi et al. (2013), our measures show stronger alignment with peer judgements; and (3) combining all three distance metrics yields more effective identification of novel papers than using any single perspective alone.

cs.DL↗

arXiv2026

A Universal Context-Reuse Layer for Cross-Model KV Sharing

Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own prefill computation even when another model has already processed the same input. Existing KV-cache reuse mechanisms substantially reduce redundant computation within a single model, but generally assume that the producer and consumer of a cache are identical. We study \emph{cross-model KV sharing}, which translates the KV state produced by a source model into a representation that can be consumed by a different target model, including models that differ in scale, architecture, attention configuration, tokenizer, and model family. We evaluate the approach in both within-family and cross-family settings. For Qwen2.5-7B $\rightarrow$ Qwen2.5-1.5B, translated KV states improve LongBench2 accuracy from 27.59\% to 34.48\%, a gain of 6.89 percentage points over the native 1.5B baseline, while reducing handoff cost relative to native target prefill. For the cross-family Qwen2.5-1.5B $\rightarrow$ Gemma-2-2B setting, KV handoff reduces target-side prefill cost by up to 67.05\% at 4K context length while maintaining decoding perplexity close to native-model baselines. In a more heterogeneous Llama3.1-70B $\rightarrow$ Qwen2.5-7B setting, cross-family handoff achieves 44.0\% accuracy compared with 45.7\% for native Qwen2.5-7B inference, while reducing measured latency from 899ms to 138ms. These results provide initial evidence that KV states can serve as transferable computational representations rather than strictly model-local caches, and motivate \emph{context mobility} as a systems abstraction for reducing redundant prefill across heterogeneous LLM and multi-agent inference workflows.

cs.LG↗

arXiv2026

ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation

Value signals are aggregated user-level moral representations that capture users' inferred value-related tendencies from their online discourse. User behavior on social media is shaped not only by what users say or whom they interact with, but also by the value signal through which they express attitudes. Existing user representation methods largely miss this value-relevant dimension. We propose ValueGraph, a graph pre-training framework that uses automatically inferred moral-value signals as noisy auxiliary signals for contextualized user representation. From post-reply graphs, ValueGraph learns semantic and structural representations and further aligns users through relative value similarity with contrastive and clustering objectives. Rather than treating inferred values as gold psychological labels, ValueGraph uses them as soft constraints for representation learning. Experiments on stance detection and twitter bot detection show consistent gains over strong text-based, graph-based, and text-only LLM baselines, highlighting value-signal guidance as a useful inductive bias for socially informed user modeling.

cs.CL↗

arXiv2026

Direct or Mediated? Task-Dependent Audio Information Routing in Large Audio Language Models

Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio understanding tasks. However, they are typically evaluated on single, coherent audio segments, leaving their behavior under less familiar input configurations underexplored. We study this issue through a controlled setting in which two audio segments are concatenated into a single input. Across multiple LALMs, we observe a striking task-dependent robustness gap: automatic speech recognition (ASR) remains comparatively stable, whereas audio question answering (AQA) degrades substantially. To investigate the mechanisms underlying this disparity, we analyze how audio information is routed through LALM decoders using layer-wise attention knockout. The results reveal distinct task-dependent pathways. ASR relies primarily on direct retrieval from audio tokens by answer tokens, whereas AQA depends more strongly on a mediated route in which audio information is first integrated into prompt tokens and subsequently accessed during generation. We further probe prompt-token representations under audio concatenation and find that task-relevant audio attributes remain readily decodable, particularly in middle and later decoder layers, even when AQA performance deteriorates sharply. This dissociation indicates that the failure cannot be explained by complete loss of audio information from the decoder states and is instead consistent with a downstream bottleneck in retrieving or utilizing prompt-mediated information during answer generation. Together, our findings reveal task-dependent audio information routing in LALMs and highlight information utilization as a potential limitation on their generalization.

cs.SD↗

arXiv2026

CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations

The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network (GNN)-based methods primarily prioritize accuracy over diversity, overlooking their inherent trade-off. To address this, we previously proposed CPGRec, a balance-oriented gaming recommender system. However, CPGRec fails to account for critical disparities in player-game interactions, which carry varying significance in reflecting players' personal preferences and may exacerbate over-smoothness issues inherent in GNN-based models. Moreover, existing approaches underutilize the reasoning capabilities and extensive knowledge of large language models (LLMs) in addressing these limitations. To bridge this gap, we propose two new modules. First, Preference-informed Edge Reweighting (PER) module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions. Second, Preference-informed Representation Generation (PRG) module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests, thereby refining representations of players and games. Experiments on \textcolor{black}{two Steam datasets} demonstrate CPGRec+'s superior accuracy and diversity over state-of-the-art models. The code is accessible at https://github.com/HsipingLi/CPGRec-Plus.

cs.IR↗

arXiv2026

VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation

AI-based Visually Impaired Assistance (VIA) remains challenging, largely due to the high cost of human evaluation. The VLM-as-a-Judge paradigm may offer a promising alternative, although it has mostly been studied in general domains. We therefore ask whether such judges can be trusted for VIA tasks. To investigate this question, we introduce VIABLE (Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation), the first benchmark for VLM-as-a-Judge evaluation in VIA. VIABLE contains over 300K judgment samples across three scenarios and introduces an Effectiveness--Impartiality--Stability framework with a 12-mode failure taxonomy. Based on VIABLE, our systematic study of seven judges across different model scales shows that existing models are largely unreliable across all evaluation axes. The strongest judge, GPT-5.4, achieves only 52.6% single-failure diagnostic accuracy, yet exhibits the highest self-preference rate at 94.2%; while open-source judges are strongly biased and adversarially fragile. To address these issues, we propose VIA-Judge-Agent, a model-agnostic inference-time harness that augments judges with visual evidence extraction and a taxonomy-guided workflow. It enables positive improvements in diagnostic accuracy and downstream VIA responses more preferred by BLV users. Data and code are available at: https://github.com/YiyiyiZhao/VIABLE

cs.CL↗

arXiv2026

Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach

Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts. Recently, large language models (LLMs) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort. Existing research highlights the importance of incorporating candidate entity type information for accurate entity recognition and classification by LLMs. However, when too many candidate entity types are provided in the prompt, LLMs struggle to accurately recognize and label entities in scientific texts, where entity types are more complex than in general domains. To address this challenge, we propose TdSciNER, a type-driven approach that effectively leverages entity type information to enhance SciNER performance. In TdSciNER, we first design an entity type filter model to identify the most likely entity types present in a given sentence. Subsequently, we introduce an auxiliary multi-class entity typing task within a multi-task learning framework alongside SciNER to obtain richer contextual representations. Then, we develop a novel demonstration selection strategy based on sentence similarity and entity type diversity to activate the in-context learning capabilities of LLMs, thereby improving entity recognition accuracy across diverse scientific domains. Experiments on three datasets demonstrate that our method achieves performance comparable to fully supervised models. Further analysis validates that each entity type-driven component in TdSciNER contributes to the improvement of SciNER performance. This work provides valuable insights for future advancements in SciNER and broader information extraction tasks in scientific text mining.

cs.CL↗

arXiv2026

Tripartite Zarankiewicz numbers and norm graphs

For fixed integers $s\ge t\ge2$, let $\operatorname{ex}(n,n,n,K_{s,t})$ denote the maximum number of edges in a tripartite $K_{s,t}$-free graph with $n$ vertices in each part. When $s\ge(t-1)!+1$, let $r$ be the largest integer satisfying $s\ge(t-1)!r^{t-1}+1$. Using the quotient norm graphs of Alon, Rónyai and Szabó, we prove that \[ \operatorname{ex}(n,n,n,K_{s,t}) \ge \left(\frac{3}{2^{1/t}}r^{1-1/t}+o(1)\right)n^{2-1/t}. \] Improving an upper bound of Tait and Timmons, we prove that, for all $s\ge t\ge 2$, \[ \operatorname{ex}(n,n,n,K_{s,t})\le \left(\frac{3}{2^{1/t}}(s-t+1)^{1/t}+o(1)\right)n^{2-1/t}. \] Together, these bounds recover the results for $t=2$, and give the new asymptotic formula \[ \operatorname{ex}(n,n,n,K_{3,3}) =\left(\frac{3}{\sqrt[3]{2}}+o(1)\right)n^{5/3}. \] Analogous results extend to $k$-partite graphs containing no $K_{s, t}$ whose $s$-vertex or $t$-vertex side lies in a single part. As an application of our tripartite construction, we determine the tripartite multicolor Ramsey number of $K_{3,3}$ asymptotically.

math.CO↗

arXiv2026

Sighted by Default: Addressing Implicit Vision Assumptions in Real-Time VLM Assistance for BLV Users

Vision-Language Model (VLM)-based assistance is reshaping independence for blind and low-vision (BLV) users, yet current tools fail in dynamic settings. While request-response architectures like BeMyAI impose prohibitive latencies, our formative study (N = 15) reveals that even real-time alternatives like Doubao fail due to a deeper structural problem: sighted-default bias -- the implicit assumption that users possess parallel visual access to their surroundings. This bias manifests as verbose, vision-centric narratives that overlook the serial nature of auditory perception, flooding the user's limited cognitive bandwidth with information that is neither timely nor actionable. To address this, we derive three design principles: Continuity, Conciseness, and Calibrated Honesty. We present VIA-Agent, which co-optimizes a specialized cognitive core with a low-latency Real-Time Communication (RTC) architecture for continuous bidirectional streaming. In a within-subjects evaluation (N = 9), VIA-Agent matched Doubao's success rate, significantly reducing mean task time by 21.4% (91.7s vs. 116.7s) and conversational turns from 5.9 to 4.3 while achieving higher trust.

cs.HC↗

arXiv2026

HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation

Recently, a line of works can generate impressive 3D objects from a single image, but they are limited by restricted representation resolution, making them unsuitable for 3D scene generation. In this work, we introduce HIVE-3D, a novel method for high-quality 3D scene generation based on hierarchical voxel enhancement framework. Specifically, given a single scene image as input, we first produce a coarse initial scene, then introduce image segmentation and attention-based retrieval to align 2D image components with 3D scene components. Subsequently, we organize these scene relations into a hierarchical component tree, where nodes closer to the leaves denote finer-grained components. Finally, we propose a voxel super-resolution model that generates refined voxels for the target instance while maintaining strong consistency with the coarse voxels. Equipped with this model, we perform coarse-to-fine hierarchical super-resolution on images and voxels for each component, producing a high-resolution and high-quality 3D scene. Extensive experiments demonstrate that our method significantly outperforms previous approaches, achieving state-of-the-art performance.

cs.CV↗

arXiv2026

Pressure-induced Superconductivity in Thermoelectric Semiconductor Mg3Sb2

The intrinsic electronic structures of narrow bandgap thermoelectric (TE) materials serve as a platform for the investigation of coupling effects of quasi-particles under high pressure, enabling the exploration of emerging electronic and phonon transport, superconductivity, and topological transition. Here, we report the discovery of pressure-induced superconductivity in the TE semiconductor Mg3Sb2. Upon the increased pressure, the metallization occurs at 8.7 GPa, followed by a superconducting transition concomitant with a carrier-type crossover from p- to n-type. This phenomenon arises from a pressure-induced structural phase transition from the semiconducting P-3m1 to the metallic C2/m-I phase. The superconducting critical temperature (Tc) exhibits a dome-shaped pressure dependence, peaking at 3.3 K at 12.6 GPa. Combined theoretical calculations, high-pressure Raman spectroscopy, and X-ray diffraction (XRD) measurements reveal an additional structural transition above 20 GPa, yielding a distinct C2/m-II phase. Our findings establish the high-pressure phase diagram of Mg3Sb2, elucidate its pressure-dependent electronic properties, and provide valuable insights for future investigations of TE materials under high pressure.

cond-mat.supr-con↗

arXiv2026

Pressure induced magnetic-field-free superconducting diode effect in NbSe2 flake

The superconducting diode effect (SDE) is a fascinating nonreciprocal phenomenon where the critical current is different for opposite current directions. It is widely believed that realizing SDE requires breaking both inversion symmetry (IS) and time-reversal symmetry (TRS), which are usually achieved via heterostructure engineering and applying external magnetic fields. Here, we report a pressure-induced magnetic-field-free SDE in NbSe2 flakes without any heterostructures. We show that pressure alone breaks the IS, as confirmed by the second harmonic generation. Crucially, upon applying an out-of-plane magnetic field (B), the SDE exhibits even-in-B behavior, implying the absence of explicit TRS breaking. This finding challenges the prevailing theoretical paradigm and demonstrates that a magnetic-field-free SDE can emerge without explicitly breaking TRS. Thereby, our work establishes pressure engineering as a powerful tool for inducing nonreciprocal superconductivity and designing versatile, magnetic-field-free superconducting devices.

cond-mat.supr-con↗

arXiv2026

Emergence of Double-Dome Superconductivity in the Pressurized Dirac Semimetal BaMg2Bi2

Dirac semimetal BaMg2Bi2 is reported to be a unique topological material that manifests surface superconductivity that coexistswith bulk band topology at ambient pressure. Here, we present a comprehensive investigation of high-pressure superconductingproperties in BaMg2Bi2 single crystal. Significantly, a pressure-driven double-dome superconducting behavior was revealed, withthe superconducting transition temperature Tc approaching the maximum values of 6.67 K at 4.5 GPa and 7.22 K at 10.4 GPafor the first and second superconducting domes, respectively. The combination of high-pressure X-ray diffraction, Hall resistivitymeasurements, and theoretical calculations demonstrates that, the first superconducting regime is closely related to the pressure-modulated Lifshitz transition, whereas the second superconducting phase emerges concurrently with a structural transition fromthe ambient-pressure P3m1 phase to a high-pressure Pnma phase.

cond-mat.supr-con↗

arXiv2026

Pressure-induced concurrent amorphization and superconductivity in topological material NbNiTe5

We have systematically studied the structural and electronic properties of a topological material NbNiTe5 under high pressure. The evolution of the normal state resistance shows a non-monotonic trend from 0.7 GPa to 5.1 GPa, in accordance with the second-order transition along the inter-layer direction observed in X-ray diffraction and Raman spectra. At around 10 GPa, the sample starts amorphization, which is concurrent with the emergence of superconductivity. Upon further compression, the structural disorder enhances and the superconducting transition becomes clearer, suggesting that the superconductivity is modulated by the degree of disorder in NbNiTe5 under high pressure. Within 45.7 GPa, the superconducting transition temperature (Tc) slowly rises from 0.6 K at 9.5 GPa to 1.4 K at 45.7 GPa. Our findings extend the family of transition metal chalcogenide superconductors and shed new light on understanding superconductivity in disordered systems.

cond-mat.supr-con↗

arXiv2026

Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction

Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact models that can serve as an on-device brain, preserving the broad general intelligence of LLMs while enabling effective high-level interaction with embodied environments. Existing approaches, however, often prioritize either general-purpose intelligence or specialized embodied capabilities, making it challenging to satisfy both requirements within a single model. We present \textbf{Athena-Brain-8B}, an 8B LLM designed to serve as an on-device brain for embodied intelligence for embodied intelligence. Through a multi-stage post-training pipeline consisting of General Supervised Fine-Tuning, General Reinforcement Learning, Embodied Expert training, and Model Merge, Athena-Brain-8B maintains strong general capabilities while acquiring strong high-level embodied interaction capabilities and generating concise responses for efficient embodied interaction. Experimental results demonstrate the effectiveness of Athena across both general and embodied evaluations. Compared with the corresponding Qwen3-8B thinking model, Athena-Brain-8B achieves comparable performance on general language and reasoning benchmarks while generating substantially shorter responses. On in-domain embodied benchmarks, Athena-Brain-8B consistently outperforms models of similar scale and surpasses several substantially larger frontier models evaluated zero-shot, demonstrating that compact language models can effectively integrate strong general intelligence with embodied capabilities.

cs.AI↗

arXiv2026

Genre Bias or Aesthetic Perception? Identifying and Mitigating Shortcut Learning in Music Evaluation

Music aesthetics scoring plays a critical role in applications such as dataset curation, generative model evaluation, and reward modeling for music generation. Recent approaches rely on deep neural networks trained on human-annotated ratings, but these models may exploit spurious correlations rather than capturing perceptually meaningful aesthetics. In this work, we identify a previously underexplored failure mode in music evaluation models: genre-induced shortcut learning. Through a systematic analysis of SongEval, we show that biases in training data lead to strong correlations between genre-related features and predicted scores, causing the model to use them as a proxy for aesthetics. This results in systematic overestimation of pop music and undervaluation of high-quality samples from other genres, leading to predictions that are inconsistent with human preferences. To address this issue, we propose a training objective that jointly reweights hard samples and regularizes group-level performance, encouraging the model to learn genre-invariant representations of musicality. Experimental results demonstrate that our method reduces genre-dependent bias and improves alignment with human preferences, as reflected by gains in both cross-genre and within-genre preference alignment.

cs.SD↗

arXiv2026

Understanding before Naming! Enhancing LLM-based Method Name Prediction with Code Summarization

Method names are critical to software quality, affecting code comprehensibility, maintainability, and developer collaboration. However, manually designing meaningful method names is challenging. Method Name Prediction (MNP), which automatically generates method names from code snippets, has recently attracted attention. Although large language models (LLMs) show promising performance for MNP, two challenges remain. First, existing evaluations mainly rely on token similarity metrics, which often fail to reflect human judgments of semantic quality. Second, current LLM-based MNP methods usually generate names through direct code-to-name mapping, which differs from the human process of understanding functionality before naming. To address these challenges, we conduct empirical studies on LLM-based evaluation and MNP strategies. We compare 6 metric-based evaluators, 5 LLM-based evaluators, and 6 human evaluators. Results show that LLM-based evaluators, especially DeepSeek-based evaluators, are more consistent with human judgments than traditional metrics. We further compare direct generation and summarization-and-refinement strategies. Results indicate that summarization and refinement generally improve the semantic quality of generated names. Case studies reveal three limitations: inaccurate summaries, semantic misalignment, and close semantic scores. Based on these findings, we propose SMNP, an MNP approach combining MNP-oriented summarization and chain-of-thought enhanced refinement. Experiments on 5 LLMs and 2 datasets demonstrate the effectiveness and robustness of SMNP.

cs.SE↗

arXiv2026

LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification

Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs. To address this, we propose LSTrans, a lightweight hybrid model designed for efficient and sensitive ECG analysis. LSTrans introduces a specialized 1D convolutional backbone with an interleaved layer architecture to capture both macroscopic rhythmic trends and microscopic morphological variations. This backbone is cascaded with a Transformer encoder to model long-range temporal dependencies, incorporating Low-Rank Adaptation across critical layers to compress the model and reduce the trainable parameter space. We further employ homogeneous and heterogeneous knowledge distillation to transfer diagnostic expertise from high-capacity teacher models to the student. Experimental results on multiple benchmark datasets demonstrate that LSTrans achieves a competitive balance between diagnostic sensitivity and resource efficiency, substantially reducing peak memory footprints and training latency during downstream adaptation. The source code is available for review at https://github.com/zyee00128/LSTrans4BIBM.

cs.LG↗