arXiv subjects

Heng Wang

Publications and source records attributed to Heng Wang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retrievers and rerankers optimize solely for relevance, often selecting either trivial, answer-revealing passages or evidence that lacks the critical information required to answer the question, without considering whether the evidence is suitable for the generator. We propose BAR-RAG, which reframes the reranker as a boundary-aware evidence selector that targets the generator's Goldilocks Zone -- evidence that is neither trivially easy nor fundamentally unanswerable for the generator, but is challenging yet sufficient for inference and thus provides the strongest learning signal. BAR-RAG trains the selector with reinforcement learning using generator feedback, and adopts a two-stage pipeline that fine-tunes the generator under the induced evidence distribution to mitigate the distribution mismatch between training and inference. Experiments on knowledge-intensive question answering benchmarks show that BAR-RAG consistently improves end-to-end performance under noisy retrieval, achieving an average gain of 10.3 percent over strong RAG and reranking baselines while substantially improving robustness. Code is publicly avaliable at https://github.com/GasolSun36/BAR-RAG.

cs.CL↗

arXiv2026

MotionBeat: Motion-Aligned Music Representation via Embodied Contrastive Learning and Bar-Equivariant Contact-Aware Encoding

Music is both an auditory and an embodied phenomenon, closely linked to human motion and naturally expressed through dance. However, most existing audio representations neglect this embodied dimension, limiting their ability to capture rhythmic and structural cues that drive movement. We propose MotionBeat, a framework for motion-aligned music representation learning. MotionBeat is trained with two newly proposed objectives: the Embodied Contrastive Loss (ECL), an enhanced InfoNCE formulation with tempo-aware and beat-jitter negatives to achieve fine-grained rhythmic discrimination, and the Structural Rhythm Alignment Loss (SRAL), which ensures rhythm consistency by aligning music accents with corresponding motion events. Architecturally, MotionBeat introduces bar-equivariant phase rotations to capture cyclic rhythmic patterns and contact-guided attention to emphasize motion events synchronized with musical accents. Experiments show that MotionBeat outperforms state-of-the-art audio encoders in music-to-dance generation and transfers effectively to beat tracking, music tagging, genre and instrument classification, emotion recognition, and audio-visual retrieval. Our project demo page: https://motionbeat2025.github.io/.

cs.SD↗

arXiv2026

Superconductor-insulator transitions in infinite-layer nickelates controlled via ${operando}$ monitored reduction

Nickelates represent an emerging class of superconductors that demand innovative approaches for structural and electronic phase modulations. Continuous control over superconductor-insulator transition (SIT) in nickelates remains particularly challenging, hindering both fundamental understanding and potential applications. Here, we demonstrate SIT in infinite-layer nickelate superconductors utilizing multiple techniques, including an ${operando}$ monitored reduction (OMR) method. OMR enables ultrawide-range continuous modulation of the Ni 3${d}$ orbital electron occupancy from ~3${d}^7$ to ~3${d}^9$. The 3${d}$ occupancy is calibrated through systematic synchrotron X-ray absorption (XAS), combined with scanning transmission electron microscopy (STEM) annular bright field (ABF) analysis of oxygen atoms. SIT is further modulated via ionic liquid gating and magnetic field. Strikingly different from cuprates, our Nernst effect measurements show that pairing initiates at the onset of the resistive drop. The subsequent emergence of the Meissner effect at zero resistance marks the establishment of global phase coherence. Angle-dependent magnetotransport within the transition temperature regime indicates a mixture of two-dimensional (2D) and three-dimensional (3D) superconducting characters, suggesting the observed SIT deviates from the canonical 2D model. Our results provide a unique perspective on the interplay of structural and electronic phase transitions in the infinite-layer nickelates across the oxygen content-magnetic field-temperature parameter space.

cond-mat.supr-con↗

arXiv2026

Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart

Scaling test-time compute via Long Chain-of-Thought (Long-CoT) significantly enhances reasoning capabilities, yet extended generation does not guarantee correctness: after an early wrong commitment, models may keep elaborating a self-consistent but incorrect prefix. Through fine-grained trajectory analysis, we identify Thinking Traps, prefix-dominant deadlocks where later reflection, alternative attempts, or verification fails to revise the root error. On a curated subset of DAPO-MATH, 89\% of failures exhibit such traps. To solve this problem, we introduce TAAR (Trap-Aware Adaptive Restart), a test-time control framework that trains a diagnostic policy to predict two signals from partial trajectories: a trap index for where to truncate and an escape probability for whether and how strongly to intervene. At inference time, TAAR truncates the trajectory before the predicted trap segment and adaptively restarts decoding; for severely trapped cases, it applies stronger perturbations, including higher-temperature resampling and an optional structured reboot suffix. Experiments on challenging mathematical and scientific reasoning benchmarks (AIME24, AIME25, GPQA-Diamond, HMMT25, BRUMO25) show that TAAR improves reasoning performance without fine-tuning base model parameters.

cs.AI↗

arXiv2026

CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation

Role-playing language agents (RPLAs) have emerged as promising applications of large language models (LLMs). However, simulating established characters presents a challenging task for RPLAs, due to the lack of authentic character datasets and nuanced evaluation methods using such data. In this paper, we present CoSER, a collection of a high-quality dataset, open models, and an evaluation protocol towards effective RPLAs of established characters. The CoSER dataset covers 17,966 characters from 771 renowned books. It provides authentic dialogues with real-world intricacies, as well as diverse data types such as conversation setups, character experiences and internal thoughts. Drawing from acting methodology, we introduce given-circumstance acting for training and evaluating role-playing LLMs, where LLMs sequentially portray multiple characters in book scenes. Using our dataset, we develop CoSER 8B and CoSER 70B, i.e., advanced open role-playing LLMs built on LLaMA-3.1 models. Extensive experiments demonstrate the value of the CoSER dataset for RPLA training, evaluation and retrieval. Moreover, CoSER 70B exhibits state-of-the-art performance surpassing or matching GPT-4o on our evaluation and three existing benchmarks, i.e., achieving 75.80% and 93.47% accuracy on the InCharacter and LifeChoice benchmarks respectively.

cs.CL↗

arXiv2025

Step-DeepResearch Technical Report

As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency.

cs.CL↗

arXiv2025

Manipulating fractional Shapiro steps in twisted cuprate Josephson junctions

High$-$quality Josephson junctions made of twisted cuprate superconductors offer unprecedented opportunities in addressing fundamental problems and realizing next$-$generation superconducting devices at relatively high temperatures. Whether or not the twisted cuprates possess high$-$temperature topological superconductivity remains an outstanding issue. Here, we tackle this problem via an in$-$depth study of the key predicted feature $--$ half$-$integer Shapiro steps. We show that half$-$integer Shapiro steps do occur in samples at a twist angle of 45$^\circ$ but are unstable with thermal cycling. Interestingly, fractional steps can be introduced by training the sample with a small magnetic field or annealing with a large electrical current, attesting to a tunable current$-$phase relation (CPR) in twisted cuprates. We extend the current annealing to realize fractional steps with odd denominators too. Furthermore, half$-$integer steps can be induced in the regime that is well beyond the expectation of topological superconductivity, favoring an alternative mechanism involving trapped vortices. Our results not only caution the direct association of half$-$integer Shapiro steps with the exotic mechanism but also open a distinct pathway toward a Josephson junction with electrically tunable CPR at high temperatures.

cond-mat.supr-con↗

arXiv2025

OpenCUA: Open Foundations for Computer-Use Agents

Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain closed. As these agents will increasingly mediate digital interactions and execute consequential decisions on our behalf, the research community needs access to open CUA frameworks to study their capabilities, limitations, and risks. To bridge this gap, we propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models. Our framework consists of: (1) an annotation infrastructure that seamlessly captures human computer-use demonstrations; (2) AgentNet, the first large-scale computer-use task dataset spanning 3 operating systems and 200+ applications and websites; (3) a scalable pipeline that transforms demonstrations into state-action pairs with reflective long Chain-of-Thought reasoning that sustain robust performance gains as data scales. Our end-to-end agent models demonstrate strong performance across CUA benchmarks. In particular, OpenCUA-72B achieves an average success rate of 45.0% on OSWorld-Verified, establishing a new state-of-the-art (SOTA) among open-source models. Further analysis confirms that our approach generalizes well across domains and benefits significantly from increased test-time computation. We release our annotation tool, datasets, code, and models to build open foundations for further CUA research.

cs.AI↗

arXiv2025

Dual-Mode Magnetic Continuum Robot for Targeted Drug Delivery

Magnetic continuum robots (MCRs) enable minimally invasive navigation through tortuous anatomical channels, yet axially magnetized designs have largely been limited to bending-only motion. To expand deformation capabilities, this paper presents a simple assembly that embeds permanent magnets radially within the catheter wall, allowing a single externally steered permanent magnet to independently induce either bending or torsion. A physics-based formulation together with finite-element analysis establishes the actuation principles, and benchtop experiments validate decoupled mode control under practical fields. Building on this, a dual-layer blockage mechanism consisting of outer grooves and inner plates leverages torsional shear to achieve on-demand drug release. Finally, an in-phantom intervention experiment demonstrates end-to-end operation: lumen following by bending for target approach, followed by twist-activated release at the site. The resulting compact, cable-free platform combines versatile deformation with precise payload delivery, indicating strong potential for next-generation, site-specific therapies.

cs.RO↗

arXiv2025

Quantum superconducting diode effect with perfect efficiency above liquid-nitrogen temperature

The superconducting diode is an emergent device that juggles between the Cooper-paired state and the resistive state with unpaired quasiparticles. Here, we report a quantum version of the superconducting diode, which operates solely between Cooper-paired states. This type of quantum superconducting diode takes advantage of quantized Shapiro steps for digitized outputs. The devices consist of twisted high-temperature cuprate superconductors, and exhibit the following distinguished characteristics: (1) a non-reciprocal diode behavior can be simply initiated by current training without applying an external magnetic field; (2) perfect diode efficiency is achieved under microwave irradiations at a record-high working temperature; (3) the quantized nature of the output offers high resilience against input noises. These features open up unprecedented opportunities toward developing practical dissipationless quantum circuits.

cond-mat.supr-con↗

arXiv2025

DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction

Multi-sensor fusion significantly enhances the accuracy and robustness of 3D semantic occupancy prediction, which is crucial for autonomous driving and robotics. However, most existing approaches depend on high-resolution images and complex networks to achieve top performance, hindering their deployment in practical scenarios. Moreover, current multi-sensor fusion approaches mainly focus on improving feature fusion while largely neglecting effective supervision strategies for those features. To address these issues, we propose DAOcc, a novel multi-modal occupancy prediction framework that leverages 3D object detection supervision to assist in achieving superior performance, while using a deployment-friendly image backbone and practical input resolution. In addition, we introduce a BEV View Range Extension strategy to mitigate performance degradation caused by lower image resolution. Extensive experiments demonstrate that DAOcc achieves new state-of-the-art results on both the Occ3D-nuScenes and Occ3D-Waymo benchmarks, and outperforms previous state-of-the-art methods by a significant margin using only a ResNet-50 backbone and 256*704 input resolution. With TensorRT optimization, DAOcc reaches 104.9 FPS while maintaining 54.2 mIoU on an NVIDIA RTX 4090 GPU. Code is available at https://github.com/AlphaPlusTT/DAOcc.

cs.CV↗

arXiv2025

MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts

Online movie review websites are valuable for information and discussion about movies. However, the massive spoiler reviews detract from the movie-watching experience, making spoiler detection an important task. Previous methods simply focus on reviews' text content, ignoring the heterogeneity of information in the platform. For instance, the metadata and the corresponding user's information of a review could be helpful. Besides, the spoiler language of movie reviews tends to be genre-specific, thus posing a domain generalization challenge for existing methods. To this end, we propose MMoE, a multi-modal network that utilizes information from multiple modalities to facilitate robust spoiler detection and adopts Mixture-of-Experts to enhance domain generalization. MMoE first extracts graph, text, and meta feature from the user-movie network, the review's textual content, and the review's metadata respectively. To handle genre-specific spoilers, we then adopt Mixture-of-Experts architecture to process information in three modalities to promote robustness. Finally, we use an expert fusion layer to integrate the features from different perspectives and make predictions based on the fused embedding. Experiments demonstrate that MMoE achieves state-of-the-art performance on two widely-used spoiler detection datasets, surpassing previous SOTA methods by 2.56% and 8.41% in terms of accuracy and F1-score. Further experiments also demonstrate MMoE's superiority in robustness and generalization. Our code is available at https://github.com/zzqbjt/Spoiler-Detection.

cs.AI↗

arXiv2025

Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models

In Large Language Models (LLMs) generation, there exist knowledge conflicts and scenarios where parametric knowledge contradicts knowledge provided in the context. Previous works studied tuning, decoding algorithms, or locating and editing context-aware neurons to adapt LLMs to be faithful to new contextual knowledge. However, they are usually inefficient or ineffective for large models, not workable for black-box models, or unable to continuously adjust LLMs' sensitivity to the knowledge provided in the context. To mitigate these problems, we propose CSKS (Continuously Steering Knowledge Sensitivity), a simple framework that can steer LLMs' sensitivity to contextual knowledge continuously at a lightweight cost. Specifically, we tune two small LMs (i.e. proxy models) and use the difference in their output distributions to shift the original distribution of an LLM without modifying the LLM weights. In the evaluation process, we not only design synthetic data and fine-grained metrics to measure models' sensitivity to contextual knowledge but also use a real conflict dataset to validate CSKS's practical efficacy. Extensive experiments demonstrate that our framework achieves continuous and precise control over LLMs' sensitivity to contextual knowledge, enabling both increased sensitivity and reduced sensitivity, thereby allowing LLMs to prioritize either contextual or parametric knowledge as needed flexibly. Our data and code are available at https://github.com/OliveJuiceLin/CSKS.

cs.CL↗

arXiv2025

BannerAgency: Advertising Banner Design with Multimodal LLM Agents

Advertising banners are critical for capturing user attention and enhancing advertising campaign effectiveness. Creating aesthetically pleasing banner designs while conveying the campaign messages is challenging due to the large search space involving multiple design elements. Additionally, advertisers need multiple sizes for different displays and various versions to target different sectors of audiences. Since design is intrinsically an iterative and subjective process, flexible editability is also in high demand for practical usage. While current models have served as assistants to human designers in various design tasks, they typically handle only segments of the creative design process or produce pixel-based outputs that limit editability. This paper introduces a training-free framework for fully automated banner ad design creation, enabling frontier multimodal large language models (MLLMs) to streamline the production of effective banners with minimal manual effort across diverse marketing contexts. We present BannerAgency, an MLLM agent system that collaborates with advertisers to understand their brand identity and banner objectives, generates matching background images, creates blueprints for foreground design elements, and renders the final creatives as editable components in Figma or SVG formats rather than static pixels. To facilitate evaluation and future research, we introduce BannerRequest400, a benchmark featuring 100 unique logos paired with 400 diverse banner requests. Through quantitative and qualitative evaluations, we demonstrate the framework's effectiveness, emphasizing the quality of the generated banner designs, their adaptability to various banner requests, and their strong editability enabled by this component-based approach.

cs.CV↗

arXiv2025

Enhanced Superconductivity and Mixed-dimensional Behaviour in Infinite-layer Samarium Nickelate Thin Films

Rare-earth infinite-layer nickelates represent an emerging class of unconventional superconductors, with materials synthesis largely limited to early lanthanide compounds. Here, we report the synthesis and characterization of phase-pure superconducting samarium-based infinite-layer nickelate thin films, including the first demonstration of Sm$_{1-x}$Sr$_x$NiO$_2$, along with co-doped variants incorporating europium and calcium. These films, grown on LSAT (001) substrates, exhibit coherent lattice structures up to $\sim$ 9 nm thickness with minimal stacking faults. The co-doped compounds achieve a record-small $c$-axis parameter of 3.26 Å and display remarkable superconducting transition temperatures up to 32.5 K. These results establish a clear correlation between decreasing $c$-axis parameter and increasing critical temperature across different rare-earth systems. In addition, angle-dependent magnetoresistance investigations reveal the existence of a hybrid mixture of 2D and 3D superconductivity in this novel system with enhanced coupling between the rare-earth 5d and Ni 3d orbitals, confirmed by resonant inelastic X-ray scattering experiments. As the concentration of Eu increases, the system exhibits a clear tendency towards 3D superconductivity. Furthermore, we observe distinctive negative magnetoresistance in the europium-containing samples. These findings advocate clear materials design principles for higher transition temperatures and exotic physics in infinite-layer nickelate superconductors through structural engineering of the rare-earth site.

cond-mat.supr-con↗

arXiv2025

Nonlinear chiral response from linearly achiral membrane metasurfaces

Chiral photonics aims to control and engineer light handedness for many applications in optical communications, biological and chemical sensing, and quantum technologies. While traditional approaches focus on engineering strong linear chiroptical response, nonlinear chiral phenomena remain largely unexplored. Here, we demonstrate experimentally a pronounced nonlinear chiral response in free-standing silicon membrane metasurfaces that are effectively achiral in the linear regime. By employing patterned membranes with both $C_4$-symmetry and intentionally broken in-plane symmetry, we reveal that strong nonlinear circular dichroism can be observed in third-harmonic generation. An unperturbed metasurface exhibits strong cross-polarized third-harmonic signal with nonlinear circular dichroism of the value $-0.83$, whereas in-plane symmetry breaking enables a co-polarized channel, and it reverses the sign of nonlinear circular dichroism that may be as large as the value $0.41$. Our findings suggest a novel approach for engineering nonlinear chiral responses in metasurfaces, complementing traditional approaches and paving the way towards advanced chiral metadevices.

physics.optics↗

arXiv2025

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment

Previous research has sought to enhance the graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. While these led to specialized LLMs better at solving graph algorithm problems, we don't need LLMs for shortest path: we need generalization from synthetic graph data to real-world tasks with implicit graph structures. In this work, we propose to unlock generalizable learning of graph with post-training alignment with synthetic data. We first design solution-based and process-based rewards for synthetic graph problems: instead of rigid memorizing response patterns in direct fine-tuning, we posit that post-training alignment would help LLMs grasp the essentials underlying graph reasoning and alleviate overfitting on synthetic data. We employ post-training alignment algorithms such as GRPO and DPO, aligning both off-the-shelf LLMs and LLMs fine-tuned on synthetic graph data. We then compare them against existing settings on both in-domain synthetic tasks and out-of-domain real-world tasks with implicit graph structures such as multi-hop QA, structured planning, and more. Extensive experiments demonstrate that our post-training alignment recipe leads to statistically significant improvement on 5 datasets, with an average gain of 12.9% over baseline settings. Further analysis reveals that process-based rewards consistently outperform solution-based rewards on synthetic data but not on real-world tasks, and compositionality and explainable intermediate steps remains a critical challenge even after post-training alignment.

cs.LG↗

arXiv2025

Gotta Hear Them All: Towards Sound Source Aware Audio Generation

Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existing methods solely rely on the global scene and overlook details of local sounding objects (i.e., sound sources). To address this issue, we propose a Sound Source-Aware Audio (SS2A) generator. SS2A is able to locally perceive multimodal sound sources from a scene with visual detection and cross-modality translation. It then contrastively learns a Cross-Modal Sound Source (CMSS) Manifold to semantically disambiguate each source. Finally, we attentively mix their CMSS semantics into a rich audio representation, from which a pretrained audio generator outputs the sound. To model the CMSS manifold, we curate a novel single-sound-source visual-audio dataset VGGS3 from VGGSound. We also design a Sound Source Matching Score to clearly measure localized audio relevance. With the effectiveness of explicit sound source modeling, SS2A achieves state-of-the-art performance in extensive image-to-audio tasks. We also qualitatively demonstrate SS2A's ability to achieve intuitive synthesis control by compositing vision, text, and audio conditions. Furthermore, we show that our sound source modeling can achieve competitive video-to-audio performance with a straightforward temporal aggregation mechanism.

cs.MM↗