arXiv subjects

Biao Wu

Publications and source records attributed to Biao Wu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Story2Proposal: A Scaffold for Structured Scientific Paper Writing

Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment.

cs.CL↗

arXiv2026

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).

cs.CV↗

arXiv2026

The Erdős-Ko-Rado Theorem in $\ell_2$-Norm

The codegree squared sum ${\rm co}_2(\cal F)$ of a family (hypergraph) $\cal F \subseteq \binom{[n]} k$ is defined to be the sum of codegrees squared $d(E)^2$ over all $E\in \binom{[n]}{k-1}$, where $d(E)=|\{F\in \cal F: E\subseteq F\}|$. Given a family of $k$-uniform families $\mathscr H$, Balogh, Clemen and Lidický recently introduced the problem to determine the maximum codegree squared sum ${\rm co}_2(\cal F)$ over all $\mathscr H$-free $\cal F$. In the present paper, we consider the families which has as forbidden configurations all pairs of sets with intersection sizes less than $t$, that is, the well-known $t$-intersecting families. We prove the following Erdős-Ko-Rado Theorem in $\ell_2$-norm, which confirms a conjecture of Brooks and Linz. Let $t,k,n$ be positive integers such that $t\leq k\leq n$. If a family $\mathcal F\subseteq \binom{[n]}{k}$ is $t$-intersecting, then for $n\ge (t+1)(k-t+1)$, we have \[{\rm co}_2(\cal F)\le {\binom{n-t}{k-t}}(t+(n-k+1)(k-t)),\] equality holds if and only if $\mathcal{F}=\{F\in {\binom{[n]}{k}}: T\subset F\}$ for some $t$-subset $T$ of $[n]$. In addition, we prove a Frankl-Hilton-Milner Theorem in $\ell_2$-norm for $t\ge 2$, and a generalized Turán result, i.e., we determine the maximum number of copies of tight path of length 2 in $t$-intersecting families.

math.CO↗

arXiv2026

Physics and computation: An insight from non-Hermitian quantum computing

We elucidate the profound connection between physics and computation by proposing and examining the model of the non-Hermitian quantum computer (NQC). In addition to conventional quantum gates such as the Hadamard, phase, and CNOT gates, this model incorporates a non-unitary quantum gate $G$. We show that NQC is extraordinarily powerful, capable of solving not only all NP problems but also all problems within the complexity class $\text{P}^{\sharp\text{P}}$ in polynomial time. We investigate two physical schemes for implementing the non-unitary gate $G$ and find that the remarkable computational power of NQC originates from the exponentially large physical resources required.

quant-ph↗

arXiv2026

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workflows. However, existing systems largely rely on runtime-centric execution paradigms, repeatedly reading, summarizing, and reasoning over large volumes of scientific literature online. This on-the-spot computation strategy incurs high computational cost, suffers from context window limitations, and often leads to brittle reasoning and hallucination. We propose Idea2Story, a pre-computation-driven framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction. Idea2Story continuously collects peer-reviewed papers together with their review feedback, extracts core methodological units, composes reusable research patterns, and organizes them into a structured methodological knowledge graph. At runtime, underspecified user research intents are aligned to established research paradigms, enabling efficient retrieval and reuse of high-quality research patterns instead of open-ended generation and trial-and-error. By grounding research planning and execution in a pre-built knowledge graph, Idea2Story alleviates the context window bottleneck of LLMs and substantially reduces repeated runtime reasoning over literature. We conduct qualitative analyses and preliminary empirical studies demonstrating that Idea2Story can generate coherent, methodologically grounded, and novel research patterns, and can produce several high-quality research demonstrations in an end-to-end setting. These results suggest that offline knowledge construction provides a practical and scalable foundation for reliable autonomous scientific discovery.

cs.CE↗

arXiv2026

VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

Understanding cultural heritage artifacts such as ancient Greek pottery requires expert-level reasoning that remains challenging for current MLLMs due to limited domain-specific data. We introduce VaseVQA, a benchmark of 31,773 images and 67,614 question-answer pairs across seven expert-defined categories, enabling systematic evaluation of expert-level cultural heritage understanding. Using this dataset, we explore effective training strategies for domain-specific reasoning. While supervised fine-tuning improves adaptation to domain knowledge, it struggles with deeper reasoning tasks. We propose VaseVL, which augments SFT with reinforcement learning using verifiable rewards. Experiments show that VaseVL consistently outperforms supervised baselines, especially on reasoning-intensive questions, highlighting the value of targeted reinforcement learning for cultural heritage visual question answering. Our code and dataset will be released at https://github.com/AIGeeksGroup/VaseVQA.

cs.CV↗

arXiv2026

Quantum Hall Effect at 0.002T

Graphene enables precise carrier-density control via gating, making it an ideal platform for studying electronic interactions. However, sample inhomogeneities often limit access to the low-density regimes where these interactions dominate. Enhancing carrier mobility is therefore crucial for exploring fundamental properties and developing device applications. Here, we demonstrate a significant reduction in external inhomogeneity using a double-layer graphene architecture separated by an ultra-thin hexagonal boron nitride layer. Mutual screening between the layers reduces scattering from random Coulomb potentials, resulting in a quantum mobility exceeding. Shubnikov de-Haas oscillations emerge at magnetic fields below 1 mT, while integer quantum Hall features are observed at 0.002T. Furthermore, we identify a fractional quantum Hall plateau at a filling factor of at 2T. These results demonstrate the platform's suitability for investigating strongly correlated electronic phases in graphene-based heterostructures.

cond-mat.mes-hall↗

arXiv2026

How Are Quantum Eigenfunctions of Hydrogen Atom Related To Its Classical Elliptic Orbits?

We show that a highly-excited energy eigenfunction $ψ_{nlm}(\vec{r})$ of hydrogen atom can be approximated as an equal-weight superposition of classical elliptic orbits with energy $E_n$ and angular momentum $L=\sqrt{l(l+1)}\hbar$, and $z$ component of angular momentum $L_z=m\hbar$. This correspondence is established by comparing the quantum probability distribution $|ψ_{nlm}(\vec{r})|^2$ and the classical probability distribution $p_c(\vec{r})$ of an ensemble of such orbits. This finding illustrates a general principle: in the semi-classical limit, an energy eigenstate of a quantum system is in general reduced to a collection of classical orbits, rather than a single classical orbit.

quant-ph↗

arXiv2026

Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach

Recent advances in vision-language models have opened up new possibilities for reasoning-driven image geolocalization. However, existing approaches often rely on synthetic reasoning annotations or external image retrieval, which can limit interpretability and generalizability. In this paper, we present Geo-R, a retrieval-free framework that uncovers structured reasoning paths from existing ground-truth coordinates and optimizes geolocation accuracy via reinforcement learning. We propose the Chain of Region, a rule-based hierarchical reasoning paradigm that generates precise, interpretable supervision by mapping GPS coordinates to geographic entities (e.g., country, province, city) without relying on model-generated or synthetic labels. Building on this, we introduce a lightweight reinforcement learning strategy with coordinate-aligned rewards based on Haversine distance, enabling the model to refine predictions through spatially meaningful feedback. Our approach bridges structured geographic reasoning with direct spatial supervision, yielding improved localization accuracy, stronger generalization, and more transparent inference. Experimental results across multiple benchmarks confirm the effectiveness of Geo-R, establishing a new retrieval-free paradigm for scalable and interpretable image geolocalization. To facilitate further research and ensure reproducibility, both the model and code will be made publicly available.

cs.CL↗

arXiv2025

I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses

This paper explores an intriguing observation: fine-tuning a large language model (LLM) with responses generated by a LLM often yields better results than using responses generated by humans, particularly in reasoning tasks. We conduct an in-depth investigation to understand why this occurs. Contrary to the common belief that these instances is due to the more detailed nature of LLM-generated content, our study identifies another contributing factor: an LLM is inherently more "familiar" with LLM generated responses. This familiarity is evidenced by lower perplexity before fine-tuning. We design a series of experiments to understand the impact of the "familiarity" and our conclusion reveals that this "familiarity" significantly impacts learning performance. Training with LLM-generated responses not only enhances performance but also helps maintain the model's capabilities in other reasoning tasks after fine-tuning on a specific task.

cs.CL↗

arXiv2025

Remote Sensing-Oriented World Model

World models have shown potential in artificial intelligence by predicting and reasoning about world states beyond direct observations. However, existing approaches are predominantly evaluated in synthetic environments or constrained scene settings, limiting their validation in real-world contexts with broad spatial coverage and complex semantics. Meanwhile, remote sensing applications urgently require spatial reasoning capabilities for disaster response and urban planning. This paper bridges these gaps by introducing the first framework for world modeling in remote sensing. We formulate remote sensing world modeling as direction-conditioned spatial extrapolation, where models generate semantically consistent adjacent image tiles given a central observation and directional instruction. To enable rigorous evaluation, we develop RSWISE (Remote Sensing World-Image Spatial Evaluation), a benchmark containing 1,600 evaluation tasks across four scenarios: general, flood, urban, and rural. RSWISE combines visual fidelity assessment with instruction compliance evaluation using GPT-4o as a semantic judge, ensuring models genuinely perform spatial reasoning rather than simple replication. Afterwards, we present RemoteBAGEL, a unified multimodal model fine-tuned on remote sensing data for spatial extrapolation tasks. Extensive experiments demonstrate that RemoteBAGEL consistently outperforms state-of-the-art baselines on RSWISE.

cs.LG↗

arXiv2025

Quadratic Quantum Speedup for Finding Independent Set of a Graph

A quadratic speedup of the quantum adiabatic algorithm (QAA) for finding independent sets (ISs) in a graph is proven analytically. In comparison to the best classical algorithm with $O(n^2)$ scaling, where $n$ is the number of vertexes, our quantum algorithm achieves a time complexity of $O(n^2)$ for finding a large IS, which reduces to $O(n)$ for identifying a size-2 IS. The complexity bounds we obtain are confirmed numerically for a specific case with the $O(n^2)$ quantum algorithm outperforming the classical greedy algorithm, that also runs in $O(n^2)$. The definitive analytical and numerical evidence for the quadratic quantum speedup benefited from an analytical framework based on the Magnus expansion in the interaction picture (MEIP), which overcomes the dependence on the ground state degeneracy encountered in conventional energy gap analysis. In addition, our analysis links the performance of QAA to the spectral structure of the median graph, bridging algorithmic complexity, graph theory, and experimentally realizable Rydberg Hamiltonians. The understanding gained provides practical guidance for optimizing near-term Rydberg atom experiments by revealing the significant impact of detuning on blockade violations.

quant-ph↗

arXiv2025

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse layouts. We introduce layoutRL, an end-to-end reinforcement learning framework that trains models to be explicitly layout-aware by optimizing a composite reward of normalized edit distance, paragraph count accuracy, and reading order preservation. Leveraging our newly released dataset, Infinity-Doc-55K, which combines 55K high-fidelity synthetic scanned document parsing data with expert-filtered real-world documents, we instantiate layoutRL in a vision-language-model-based parser called Infinity-Parser. Evaluated on English and Chinese benchmarks for OCR, table and formula extraction, and reading order detection, Infinity-Parser achieves new state-of-the-art performance in both accuracy and structural fidelity, outpacing specialist pipelines and general-purpose vision-language models. We will publicly release our code and dataset to accelerate progress in robust document understanding.

cs.CV↗

arXiv2025

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

Document parsing from scanned images into structured formats remains a significant challenge due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Existing supervised fine-tuning methods often struggle to generalize across diverse document types, leading to poor performance, particularly on out-of-distribution data. This issue is further exacerbated by the limited availability of high-quality training data for layout-aware parsing tasks. To address these challenges, we introduce LayoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation. To support this training, we construct the Infinity-Doc-400K dataset, which we use to train Infinity-Parser, a vision-language model demonstrating robust generalization across various domains. Extensive evaluations on benchmarks including OmniDocBench, olmOCR-Bench, PubTabNet, and FinTabNet show that Infinity-Parser consistently achieves state-of-the-art performance across a broad range of document types, languages, and structural complexities, substantially outperforming both specialized document parsing systems and general-purpose vision-language models. We will release our code, dataset, and model to facilitate reproducible research in document parsing.

cs.CL↗

arXiv2025

UniVid: The Open-Source Unified Video Model

Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow-based generation due to text-visual token imbalance and the limitations of uniform cross-modal attention across the flow trajectory, and efficiently extending image-centric MLLMs to video without costly retraining. We present UniVid, a unified architecture that couples an MLLM with a diffusion decoder through a lightweight adapter, enabling both video understanding and generation. We introduce Temperature Modality Alignment to improve prompt adherence and Pyramid Reflection for efficient temporal reasoning via dynamic keyframe selection. Extensive experiments on standard benchmarks demonstrate state-of-the-art performance, achieving a 2.2% improvement on VBench-Long total score compared to EasyAnimateV5.1, and 1.0% and 3.3% accuracy gains on MSVD-QA and ActivityNet-QA, respectively, compared with the best prior 7B baselines. Code: https://github.com/AIGeeksGroup/UniVid. Website: https://aigeeksgroup.github.io/UniVid.

cs.CV↗

arXiv2025

Automotive-ENV: Benchmarking Multimodal Agents in Vehicle Interface Systems

Multimodal agents have demonstrated strong performance in general GUI interactions, but their application in automotive systems has been largely unexplored. In-vehicle GUIs present distinct challenges: drivers' limited attention, strict safety requirements, and complex location-based interaction patterns. To address these challenges, we introduce Automotive-ENV, the first high-fidelity benchmark and interaction environment tailored for vehicle GUIs. This platform defines 185 parameterized tasks spanning explicit control, implicit intent understanding, and safety-aware tasks, and provides structured multimodal observations with precise programmatic checks for reproducible evaluation. Building on this benchmark, we propose ASURADA, a geo-aware multimodal agent that integrates GPS-informed context to dynamically adjust actions based on location, environmental conditions, and regional driving norms. Experiments show that geo-aware information significantly improves success on safety-aware tasks, highlighting the importance of location-based context in automotive environments. We will release Automotive-ENV, complete with all tasks and benchmarking tools, to further the development of safe and adaptive in-vehicle agents.

cs.RO↗

arXiv2025

StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes

Underwater stereo depth estimation provides accurate 3D geometry for robotics tasks such as navigation, inspection, and mapping, offering metric depth from low-cost passive cameras while avoiding the scale ambiguity of monocular methods. However, existing approaches face two critical challenges: (i) parameter-efficiently adapting large vision foundation encoders to the underwater domain without extensive labeled data, and (ii) tightly fusing globally coherent but scale-ambiguous monocular priors with locally metric yet photometrically fragile stereo correspondences. To address these challenges, we propose StereoAdapter, a parameter-efficient self-supervised framework that integrates a LoRA-adapted monocular foundation encoder with a recurrent stereo refinement module. We further introduce dynamic LoRA adaptation for efficient rank selection and pre-training on the synthetic UW-StereoDepth-40K dataset to enhance robustness under diverse underwater conditions. Comprehensive evaluations on both simulated and real-world benchmarks show improvements of 6.11% on TartanAir and 5.12% on SQUID compared to state-of-the-art methods, while real-world deployment with the BlueROV2 robot further demonstrates the consistent robustness of our approach. Code: https://github.com/AIGeeksGroup/StereoAdapter. Website: https://aigeeksgroup.github.io/StereoAdapter.

cs.CV↗

arXiv2025

Foundations and Recent Trends in Multimodal Mobile Agents: A Survey

Mobile agents are essential for automating tasks in complex and dynamic mobile environments. As foundation models evolve, the demands for agents that can adapt in real-time and process multimodal data have grown. This survey provides a comprehensive review of mobile agent technologies, focusing on recent advancements that enhance real-time adaptability and multimodal interaction. Recent evaluation benchmarks have been developed better to capture the static and interactive environments of mobile tasks, offering more accurate assessments of agents' performance. We then categorize these advancements into two main approaches: prompt-based methods, which utilize large language models (LLMs) for instruction-based task execution, and training-based methods, which fine-tune multimodal models for mobile-specific applications. Additionally, we explore complementary technologies that augment agent performance. By discussing key challenges and outlining future research directions, this survey offers valuable insights for advancing mobile agent technologies. A comprehensive resource list is available at https://github.com/aialt/awesome-mobile-agents

cs.AI↗