arXiv subjects

Bo Zhang

Publications and source records attributed to Bo Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2025

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.

cs.AI↗

arXiv2025

GuangMing-Explorer: A Four-Legged Robot Platform for Autonomous Exploration in General Environments

Autonomous exploration is a fundamental capability that tightly integrates perception, planning, control, and motion execution. It plays a critical role in a wide range of applications, including indoor target search, mapping of extreme environments, resource exploration, etc. Despite significant progress in individual components, a holistic and practical description of a completely autonomous exploration system, encompassing both hardware and software, remains scarce. In this paper, we present GuangMing-Explorer, a fully integrated autonomous exploration platform designed for robust operation across diverse environments. We provide a comprehensive overview of the system architecture, including hardware design, software stack, algorithm deployment, and experimental configuration. Extensive real-world experiments demonstrate the platform's effectiveness and efficiency in executing autonomous exploration tasks, highlighting its potential for practical deployment in complex and unstructured environments.

cs.RO↗

arXiv2025

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

We introduce QwenLong-L1.5, a model that achieves superior long-context reasoning capabilities through systematic post-training innovations. The key technical breakthroughs of QwenLong-L1.5 are as follows: (1) Long-Context Data Synthesis Pipeline: We develop a systematic synthesis framework that generates challenging reasoning tasks requiring multi-hop grounding over globally distributed evidence. By deconstructing documents into atomic facts and their underlying relationships, and then programmatically composing verifiable reasoning questions, our approach creates high-quality training data at scale, moving substantially beyond simple retrieval tasks to enable genuine long-range reasoning capabilities. (2) Stabilized Reinforcement Learning for Long-Context Training: To overcome the critical instability in long-context RL, we introduce task-balanced sampling with task-specific advantage estimation to mitigate reward bias, and propose Adaptive Entropy-Controlled Policy Optimization (AEPO) that dynamically regulates exploration-exploitation trade-offs. (3) Memory-Augmented Architecture for Ultra-Long Contexts: Recognizing that even extended context windows cannot accommodate arbitrarily long sequences, we develop a memory management framework with multi-stage fusion RL training that seamlessly integrates single-pass reasoning with iterative memory-based processing for tasks exceeding 4M tokens. Based on Qwen3-30B-A3B-Thinking, QwenLong-L1.5 achieves performance comparable to GPT-5 and Gemini-2.5-Pro on long-context reasoning benchmarks, surpassing its baseline by 9.90 points on average. On ultra-long tasks (1M~4M tokens), QwenLong-L1.5's memory-agent framework yields a 9.48-point gain over the agent baseline. Additionally, the acquired long-context reasoning ability translates to enhanced performance in general domains like scientific reasoning, memory tool using, and extended dialogue.

cs.CL↗

arXiv2025

Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework

Visualizations play a crucial part in effective communication of concepts and information. Recent advances in reasoning and retrieval augmented generation have enabled Large Language Models (LLMs) to perform deep research and generate comprehensive reports. Despite its progress, existing deep research frameworks primarily focus on generating text-only content, leaving the automated generation of interleaved texts and visualizations underexplored. This novel task poses key challenges in designing informative visualizations and effectively integrating them with text reports. To address these challenges, we propose Formal Description of Visualization (FDV), a structured textual representation of charts that enables LLMs to learn from and generate diverse, high-quality visualizations. Building on this representation, we introduce Multimodal DeepResearcher, an agentic framework that decomposes the task into four stages: (1) researching, (2) exemplar report textualization, (3) planning, and (4) multimodal report generation. For the evaluation of generated multimodal reports, we develop MultimodalReportBench, which contains 100 diverse topics served as inputs along with 5 dedicated metrics. Extensive experiments across models and evaluation methods demonstrate the effectiveness of Multimodal DeepResearcher. Notably, utilizing the same Claude 3.7 Sonnet model, Multimodal DeepResearcher achieves an 82% overall win rate over the baseline method.

cs.CL↗

arXiv2025

EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce

Foundation agents have rapidly advanced in their ability to reason and interact with real environments, making the evaluation of their core capabilities increasingly important. While many benchmarks have been developed to assess agent performance, most concentrate on academic settings or artificially designed scenarios while overlooking the challenges that arise in real applications. To address this issue, we focus on a highly practical real-world setting, the e-commerce domain, which involves a large volume of diverse user interactions, dynamic market conditions, and tasks directly tied to real decision-making processes. To this end, we introduce EcomBench, a holistic E-commerce Benchmark designed to evaluate agent performance in realistic e-commerce environments. EcomBench is built from genuine user demands embedded in leading global e-commerce ecosystems and is carefully curated and annotated through human experts to ensure clarity, accuracy, and domain relevance. It covers multiple task categories within e-commerce scenarios and defines three difficulty levels that evaluate agents on key capabilities such as deep information retrieval, multi-step reasoning, and cross-source knowledge integration. By grounding evaluation in real e-commerce contexts, EcomBench provides a rigorous and dynamic testbed for measuring the practical capabilities of agents in modern e-commerce.

cs.AI↗

arXiv2025

WaggleNet: A LoRa and MQTT-Based Monitoring System for Internal and External Beehive Conditions

Bee populations are declining globally due to habitat loss, pesticide exposure, and climate change, threatening agricultural productivity and food security. While existing smart beehive systems monitor internal conditions, they typically overlook external environmental factors that significantly influence colony health, and are constrained by high cost, limited scalability, and inadequate contextual analysis. We present WaggleNet, a novel dual-scope monitoring system that simultaneously captures both internal hive conditions and external environmental parameters using a cost-effective LoRa-MQTT architecture. Our system deploys modular worker nodes ($\sim$\$15 each) equipped with temperature, humidity, light, and GPS sensors both inside and around beehives. A master node functions as a LoRa-MQTT gateway, forwarding data to a cloud server with a mobile application interface. Field experiments confirmed reliable operation with 100\% packet delivery over 110 meters in line-of-sight conditions and 95 meters in obstructed environments, including successful deployment inside wooden hive structures. Our system demonstrated stable end-to-end latency under 5 seconds and continuous operation over a two-month period across diverse environmental conditions. By bridging the gap between internal and external monitoring, WaggleNet enables contextual anomaly detection and supports data-driven precision beekeeping in resource-constrained settings.

cs.NI↗

arXiv2025

Simultaneous Heterogeneity and Reduced-rank Learning for Multivariate Response Regression

Heterogeneous data are now ubiquitous in many applications in which correctly identifying the subgroups from a heterogeneous population is critical. Although there is an increasing body of literature on subgroup detection, existing methods mainly focus on the univariate response setting. In this paper, we propose a joint heterogeneity and reduced-rank learning framework to simultaneously identify the subgroup structure and estimate the covariate effects for heterogeneous multivariate response regression. In particular, our approach uses rank-constrained pairwise fusion penalization and conducts the subgroup analysis without requiring prior knowledge regarding the individual subgroup memberships. We implement the proposed approach by an alternating direction method of multipliers (ADMM) algorithm and show its convergence. We also establish the asymptotic properties for the resulting estimators under mild and interpretable conditions. A predictive information criterion is proposed to select the rank of the coefficient matrix with theoretical support. The effectiveness of the proposed approach is demonstrated through simulation studies and a real data application.

stat.ME↗

arXiv2025

Circuit Quantum Acoustodynamics in a Scalable Phononic Integrated Circuit Architecture

Previous demonstrations of quantum acoustic systems have been limited to isolated devices, with limited capability to route phonons and interconnect multi-port acoustic elements for further extension. Here, we demonstrate a scalable architecture for circuit quantum acoustodynamics (cQAD) by integrating superconducting qubits with suspension-free phononic integrated circuits (PnICs). Coherent coupling between tunable transmon qubits and waveguide-integrated phononic cavities, including Fabry-Perot cavities via monolithic integration and microring cavities via flip-chip assembly, has been achieved, producing a pronounced enhancement of phonon emission with a Purcell factor of ~19. These devices represent elementary building blocks for scalable phononic circuits, establishing the foundation for phonon-based quantum information processors and the testbed for novel quantum acoustic phenomena.

quant-ph↗

arXiv2025

Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning

The growing exploration of Large Language Models (LLM) and Vision-Language Models (VLM) has opened avenues for enhancing the effectiveness of reinforcement learning (RL). However, existing LLM-based RL methods often focus on the guidance of control policy and encounter the challenge of limited representations of the backbone networks. To tackle this problem, we introduce Enhanced Semantic Motion Representations (Semore), a new VLM-based framework for visual RL, which can simultaneously extract semantic and motion representations through a dual-path backbone from the RGB flows. Semore utilizes VLM with common-sense knowledge to retrieve key information from observations, while using the pre-trained clip to achieve the text-image alignment, thereby embedding the ground-truth representations into the backbone. To efficiently fuse semantic and motion representations for decision-making, our method adopts a separately supervised approach to simultaneously guide the extraction of semantics and motion, while allowing them to interact spontaneously. Extensive experiments demonstrate that, under the guidance of VLM at the feature level, our method exhibits efficient and adaptive ability compared to state-of-art methods. All codes are released.

cs.CV↗

arXiv2025

Elastic scattering problems by penetrable obstacles with embedded objects

This paper considers 3-D elastic scattering problems by penetrable obstacles with embedded objects. The well-posedness of transmission problem is proved by employing integral equation method. Then the Inverse Problems , which is to recover the obstacle by the far-field pattern measurement, is considered. It is shown that the inhomogeneous penetrable obstacle can be uniquely determined from the far-field pattern at a fixed frequency.

math.AP↗

arXiv2025

LongCat-Flash-Omni Technical Report

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

cs.MM↗

arXiv2025

Banach neural operator for Navier-Stokes equations

Classical neural networks are known for their ability to approximate mappings between finite-dimensional spaces, but they fall short in capturing complex operator dynamics across infinite-dimensional function spaces. Neural operators, in contrast, have emerged as powerful tools in scientific machine learning for learning such mappings. However, standard neural operators typically lack mechanisms for mixing or attending to input information across space and time. In this work, we introduce the Banach neural operator (BNO) -- a novel framework that integrates Koopman operator theory with deep neural networks to predict nonlinear, spatiotemporal dynamics from partial observations. The BNO approximates a nonlinear operator between Banach spaces by combining spectral linearization (via Koopman theory) with deep feature learning (via convolutional neural networks and nonlinear activations). This sequence-to-sequence model captures dominant dynamic modes and allows for mesh-independent prediction. Numerical experiments on the Navier-Stokes equations demonstrate the method's accuracy and generalization capabilities. In particular, BNO achieves robust zero-shot super-resolution in unsteady flow prediction and consistently outperforms conventional Koopman-based methods and deep learning models.

cs.NE↗

arXiv2025

ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection

Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as harmful content can emerge from individual modalities or their interaction. Existing safety methods are often text-only, require prior knowledge of the risk category, or operate as post-generation auditors, struggling to proactively mitigate such compositional, multimodal risks. To address this challenge, we present ConceptGuard, a unified safeguard framework for proactively detecting and mitigating unsafe semantics in multimodal video generation. ConceptGuard operates in two stages: First, a contrastive detection module identifies latent safety risks by projecting fused image-text inputs into a structured concept space; Second, a semantic suppression mechanism steers the generative process away from unsafe concepts by intervening in the prompt's multimodal conditioning. To support the development and rigorous evaluation of this framework, we introduce two novel benchmarks: ConceptRisk, a large-scale dataset for training on multimodal risks, and T2VSafetyBench-TI2V, the first benchmark adapted from T2VSafetyBench for the Text-and-Image-to-Video (TI2V) safety setting. Comprehensive experiments on both benchmarks show that ConceptGuard consistently outperforms existing baselines, achieving state-of-the-art results in both risk detection and safe video generation. Our code is available at https://github.com/Ruize-Ma/ConceptGuard.

cs.CV↗

arXiv2025

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence

Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended periods, which is essential for long-form video production like movies. We propose MovieDreamer, a novel hierarchical framework that integrates the strengths of autoregressive models with diffusion-based rendering to pioneer long-duration video generation with intricate plot progressions and high visual fidelity. Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering. This method is akin to traditional movie production processes, where complex stories are factorized down into manageable scene capturing. Further, we employ a multimodal script that enriches scene descriptions with detailed character information and visual style, enhancing continuity and character identity across scenes. We present extensive experiments across various movie genres, demonstrating that our approach not only achieves superior visual and narrative quality but also effectively extends the duration of generated content significantly beyond current capabilities. Homepage: https://aim-uofa.github.io/MovieDreamer/.

cs.CV↗

arXiv2025

Stellar Parameters of BOSS M dwarfs in SDSS-V DR19

We utilized the Stellar LAbel Machine (SLAM), a data-driven model based on Support Vector Regression, to derive stellar parameters ([Fe/H], $T_{\rm eff}$, and $\log{g}$) for SDSS-V M dwarfs using low-resolution optical spectra (R$\sim$2000) obtained with the BOSS spectrographs. These parameters are calibrated using LAMOST F, G or K dwarf companions ([Fe/H]), and APOGEE Net ($T_{\rm eff}$ and $\log{g}$), respectively. Comparisons of SLAM predicted [Fe/H] values between two components of M+M dwarfs wide binaries show no bias but with a scatter of 0.11 dex. Further comparisons with two other works, which also calibrated the [Fe/H] of M dwarfs by using the F/G/K companions, reveal biases of -0.06$\pm$0.16 dex and 0.02$\pm$0.14 dex, respectively. The SLAM-derived effective temperatures agree well with the temperature which is calibrated by using interferometric angular diameters (bias: -27$\pm$92 K) and those of the LAMOST (bias: -34$\pm$65 K), but are systematically lower than those from an empirical relationship between the color index and $T_{\rm eff}$ by 146$\pm$45 K. The SLAM surface gravity aligns well with those of LAMOST (bias: -0.01$\pm$0.07 dex) and those derived from the stellar mass and radius (bias: -0.04$\pm$0.09 dex). Finally, we investigated a bias in [Fe/H] between SLAM and APOGEE ASPCAP. It depends on ASPCAP's [Fe/H] and $T_{\rm eff}$, we provide an equation to correct the ASPCAP metallicities.

astro-ph.SR↗

arXiv2025

Debiasing hazard-based, time-varying vaccine effects using vaccine-irrelevant infections: An observational extension of a pivotal Phase 3 COVID-19 vaccine efficacy trial

Understanding how vaccine effectiveness (VE) changes over time can provide evidence-based guidance for public health decision making. While commonly reported by practitioners, time-varying VE estimates obtained using Cox regression are vul- nerable to hidden biases. To address these limitations, we describe how to leverage vaccine-irrelevant infections to identify hazard-based, time-varying VE in the pres- ence of unmeasured confounding and selection bias. We articulate assumptions under which our approach identifies a causal effect of an intervention deferring vaccination and interaction with the community in which infections circulate. We develop sieve and efficient influence curve-based estimators and discuss imposing monotone shape constraints and estimating VE against multiple variants. As a case study, we examine the observational booster phase of the Coronavirus Vaccine Efficacy (COVE) trial of the Moderna mRNA-1273 COVID-19 vaccine which used symptom-triggered multi- plex PCR testing to identify acute respiratory illnesses (ARIs) caused by SARS-CoV-2 and 20 off-target pathogens previously identified as compelling negative controls for COVID-19. Accounting for vaccine-irrelevant ARIs supported that the mRNA-1273 booster was more effective and durable against Omicron COVID-19 than suggested by Cox regression. Our work offers an approach to mitigate bias in hazard-based, time- varying treatment effects in randomized and non-randomized studies using negative controls.

stat.ME↗

arXiv2025

CareCom: Generative Image Composition with Calibrated Reference Features

Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features.

cs.CV↗

arXiv2025

Agentar-DeepFinance-100K: A Large-Scale Financial Dataset via Systematic Chain-of-Thought Synthesis Optimization

Recent advancements in large language models (LLMs) have demonstrated remarkable general reasoning capabilities, holding significant potential for applications in the financial domain, a field that requires robust and reliable reasoning. It has been demonstrated that distilling high-quality chain-of-thought (CoT) rationales from advanced general reasoning models offers a promising and efficient path to the financial reasoning model. However, existing CoT synthesis methods suffer from shallow CoT sampling, leaving the question of how to construct a well-designed knowledge space for finance reasoning unexplored. In this paper, we present Agentar-DeepFinance-100K, a large-scale financial reasoning dataset characterized by its systematic CoT synthesis optimization. We first introduce a comprehensive CoT synthesis pipeline featuring Multi-perspective Knowledge Extraction (MKE) and Self-Corrective Rewriting (SCR) to generate exhaustive and deep financial reasoning trajectories. Furthermore, a systematic investigation, termed CoT Cube, is conducted to analyze critical factors that influence CoT effectiveness, such as necessity, length and synthesizer, yielding valuable insights for high-quality financial CoT construction. Experiments demonstrate that models trained on our Agentar-DeepFinance-100K achieve significant improvements on financial benchmarks. We publicly release Agentar-DeepFinance-100K , hoping to advance the research in financial reasoning models.

cs.CE↗