arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 73 records · Page 4Linked to original sources

arXiv2026

Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving

While multimodal reasoning has advanced rapidly, solving complex geometry problems critically hinges on active visual assistance, such as constructing auxiliary lines, spurring the rise of Visual Chain-of-Thought (VCoT). However, existing evaluations typically assess visual generation quality and final answer accuracy in isolation, failing to examine whether intermediate visual aids are geometrically valid, effectively utilized in subsequent reasoning, or causally responsible for task success. To bridge this gap, we introduce GeoVAD-Bench, a diagnostic benchmark that pairs a fine-grained five-dimensional trajectory diagnosis covering perception, auxiliary quality, utilization, deductive reasoning, and final correctness with controlled No-Aux, Auto-Aux, and GT-Aux intervention settings to systematically isolate intermediate error modes, the causal gains of visual aids, and the resulting autonomy gap. Our findings reveal that while high-quality auxiliary aids offer substantial theoretical gains for geometric problem solving, autonomous generation is frequently hampered by compounding errors across geometric perception, faithful visual manipulation, visual-state grounding, and deductive reasoning. Guided by these diagnostic insights, we establish a specialized data construction pipeline encompassing geometric perception, diagram editing, and interleaved visual-textual reasoning trajectories, and develop a progressive SFT and multimodal RL training framework. The resulting model, GeoWeave-8B, outperforms the base model by +25.3% in final geometric accuracy and achieves a +30.4% gain in process average across the four intermediate diagnostic dimensions.

cs.AI↗

arXiv2026

Oriented Paths with Few Direction Flips Are Tournament Anti-Sidorenko

An oriented graph $H$ is said to be tournament anti-Sidorenko (TAS) if a uniformly random tournament asymptotically maximizes the homomorphism density of $H$ among all tournaments. For an oriented path $P$, a direction flip is a non-leaf source or sink. Sah, Sawhney and Zhao proved that consistently directed paths (paths with no direction flips) are TAS. He, Mani, Nie, Tung and Wei proved that for $3\le k\le 7$, every oriented path of length $k$ with exactly one direction flip is TAS, and Chen, Clemen and Noel recently extended this to every $k\ge 3$. In this paper, we extend these results by proving that for every integer $r\ge 0$, every oriented path of length at least $1665r+1454$ with $r$ direction flips is tournament anti-Sidorenko.

math.CO↗

arXiv2026

Construction of the $a_4$ family

The COMPASS Collaboration recently reported a new broad $J^{PC}=4^{++}$ structure, denoted as $a_4(2610)$, which has sparked our interest in studying the $a_4$ family with $I^GJ^{PC}=1^{-}4^{++}$. In this work, we investigate the mass spectra and Okubo-Zweig-Iizuka-allowed two-body strong decays of the $a_4$ family using the modified Godfrey-Isgur quark model and the quark-pair creation model. We also explore the possibility of identifying $a_4(2610)$ as a $4F$ or $2H$ state, and our numerical results suggest that it could be a promising candidate for the $a_4(2H)$ state. In addition, we predict the masses and the widths of the $a_4(1H)$ and $a_4(3F)$ states.

hep-ph↗

arXiv2026

An encoded asymmetric ligand for metal-selective topological assembly of two-dimensional metal-organic frameworks

Two-dimensional metal-organic frameworks (2D MOFs), with diverse topological architectures, provide a powerful platform for exploring unconventional electronic and lattice-dynamical responses. Yet their structural diversity remains fundamentally constrained by the fixed geometry of high-symmetry ligands. Here, we introduce an encoded asymmetric ligand, benzo[b]triphenylene-2,3,6,7,11,12-hexaol (BTH), for metal-selective topological assembly. By integrating multi-site coordination fields with sterically differentiated environments, BTH exhibits distinct topological programmability: different divalent metal ions direct divergent framework architectures. Specifically, coordination of BTH with divalent Cu(II) and Zn(II) ions assembles Cu-BTH-MOF with a dual-mode hexagonal pore topology and Zn-BTH-MOF with uniform hexagonal channels, respectively, as supported by PXRD Pawley refinement, structural simulations, and pore-size distribution analysis. Furthermore, this topological divergence is accompanied by a significant divergence in charge-transport properties, with Cu-BTH-MOF reaching an electrical conductivity of 1.186 x 10-3 S cm-1, more than six orders of magnitude higher than that of Zn-BTH-MOF (3.38 x 10-10 S cm-1). This work establishes ligand desymmetrization as a programmable strategy for metal-selective topological diversification in 2D MOFs.

cond-mat.mtrl-sci↗

arXiv2026

"Tab, Tab, Bug": Security Pitfalls of Next Edit Suggestions in AI-Integrated IDEs

Modern AI-integrated IDEs are shifting from passive code completion to proactive Next Edit Suggestions (NES). Unlike traditional autocompletion, NES is designed to construct a richer context from both recent user interactions and the broader codebase to suggest multi-line, cross-line, or even cross-file modifications. This evolution significantly streamlines the programming workflow into a tab-by-tab interaction and enhances developer productivity. Consequently, NES introduces a more complex context retrieval mechanism and sophisticated interaction patterns. However, existing studies focus almost exclusively on the security implications of standalone LLM-based code generation, ignoring the potential attack vectors posed by NES in modern AI-integrated IDEs. The underlying mechanisms of NES remain under-explored, and their security implications are not yet fully understood. In this paper, we conduct the first systematic security study of NES systems. First, we perform an in-depth dissection of the NES mechanisms to understand the newly introduced threat vectors. It is found that NES retrieves a significantly expanded context, including inputs from imperceptible user actions and global codebase retrieval, which increases the attack surfaces. Second, we conduct a comprehensive in-lab study to evaluate the security implications of NES. The evaluation results reveal that NES is susceptible to context poisoning and is sensitive to transactional edits and human-IDE interactions. Third, we perform a large-scale online survey involving over 200 professional developers to assess the perceptions of NES security risks in real-world development workflows. The survey results indicate a general lack of awareness regarding the potential security pitfalls associated with NES, highlighting the need for increased education and improved security countermeasures in AI-integrated IDEs.

cs.CR↗

arXiv2026

Cursive: The Trace from the Curse of Dimensionality

Modern data are increasingly high-dimensional or non-Euclidean. As dimension grows, new statistical patterns can emerge in the relations among observations, while a conventional statistical summary may fail to retain the signal they carry. This paper names and organizes a research program around this observation, calling it Cursive. Cursive asks which relational information is lost when the summary is formed and how the analysis should be redesigned around that information. The canonical example is the generalized edge-count test, which keeps the two within-sample edge counts whose opposing deviations can cancel in the classical between-sample count. This paper traces how the same design question has led to task-specific methods built from graphs, graph-based ranks, kernels, and dissimilarity profiles for testing, change-point detection, covariate-balance assessment, clustering, classification, and generative-model evaluation.

stat.ME↗

arXiv2026

MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation

Robotic manipulation often requires acting on information that is no longer visible, yet Vision-Language-Action policies are usually evaluated when the current observation largely determines the next action. Existing robotic memory benchmarks expose this gap, but they still rely mainly on final task success and therefore conflate forgetting with manipulation failure. We present \textbf{MEMOBench}, a benchmark for process level memory evaluation in robotic manipulation. MEMOBench includes 30 history dependent tasks, 1{,}500 expert demonstrations, and 4{,}200 executable checkpoint instances from 84 templates. Each checkpoint pairs coarse to fine language with a simulator predicate and labels one memory operation: Storage, Update, or Compression. These annotations define Memory Storage Rate, Memory Update Rate, and Memory Compression Rate, which measure memory fidelity alongside task success. Across standard and memory augmented VLA policies, the strongest memory module baseline reaches only 31.9\% average success rate, and high storage often coexists with weak update and compression. Checkpoint language also supervises semantic, contrastive, and framewise memory alignment objectives, yielding modest gains across different memory operations. MEMOBench provides a diagnostic evaluation suite and training supervision for memory grounded robotic policies. The project page is available at https://github.com/Collab-Gen/MEMOBench.

cs.RO↗

arXiv2026

Energy-Energy Correlator at Hadron Colliders: Celestial Blocks and Singularities

Energy-energy correlator (EEC) is an event shape observable that characterizes the distribution of energy flux in collision events. We initiate the study of full-range EEC at hadron colliders, generalizing the extensively studied EEC in $e^+e^-$ collision as well as the transverse EEC in hadron collisions. We derive celestial blocks from Lorentz symmetry to perform partial wave decomposition of the EEC at hadron colliders. These celestial blocks are essentially conformal blocks on the 2d celestial sphere, which have additional dependence on the collinear spin of ``light-ray transition matrix'' along the collision axis. In this work, we perform the leading-order (LO) analytic calculation of this observable in pure Yang-Mills theory and use it as an example to illustrate the block decomposition. Numerically, the block expansion demonstrates superior accuracy in the collinear limit compared to conventional power series expansion. Analytically, we observe in this example that the block coefficients exhibit analyticity in both collinear and transverse spin. In addition, we analyze several kinematic limits at LO -- collinear, back-to-back, opposite coplanar and Regge limit. While the first three limits naturally generalize their $e^+e^-$ collision counterparts or transverse EEC and are governed by soft-collinear dynamics, the Regge limit requires complete angular dependence and reveals BFKL physics. Phenomenologically, we propose a realistic experimental setup and briefly discuss how the convolution of parton distribution function modifies the perturbative EEC result. Our work suggests that the full-range EEC at hadron colliders is an elegant observable which probes a broader kinematic space and connects various regimes of different QCD dynamics through a single measurement.

hep-ph↗

arXiv2026

Graph-Based Change-Point Detection for Partially Observed High-Dimensional Data

Partial missingness is common in high-dimensional data, but most existing change-point procedures are developed for fully observed sequences. We introduce gMiss, a graph-based framework for testing and localizing a change in the observed-data distribution of a partially observed high-dimensional sequence. The method treats the observed values together with the missingness indicators as the object of inference, so the target alternative is a change in the induced observed data law. It is designed for general distributional changes and requires neither sparsity nor Gaussianity. When the augmented observations are independent, the full permutation test controls type I error in finite samples. The procedure combines graph scans based on elementwise imputation and distance imputation. The two scans capture complementary graph patterns. Simulation results indicate that gMiss maintains accurate null calibration across the MCAR and MAR designs considered, remains competitive under Gaussian location alternatives, and exhibits strong power and localization performance in many non-Gaussian location and scale settings. We further illustrate the practical utility of the method through an application to genomic copy-number data, where gMiss identifies additional candidate boundaries that are visually plausible in the raw heatmap.

stat.ME↗

arXiv2026

Proximity3D: Shape from Capacitive Proximity on Sensing Manifold

Most shape reconstruction methods assume measurements defined over planar sensing domains, such as RGB images or depth maps. In this paper, we use a curved capacitive textile as a shape sensor, treating its surface as a non-planar sensing manifold. Each scan is represented as a capacitive proximity field on this manifold, induced by the interaction between the curved electrode layout and nearby object geometry. We introduce a multi-view feedforward reconstruction model that aggregates these fields across known sensor views and recovers the observed object shape. Simulated and physical experiments demonstrate robust reconstruction from capacitive proximity signals acquired on curved sensing surfaces, pointing toward a new route to robotic near-field geometric awareness via embodied sensing.

cs.CV↗

arXiv2026

TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems

In the pursuit of enhancing domain-specific Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) emerges as a promising solution to mitigate issues such as hallucinations, outdated knowledge, and limited expertise in highly specialized queries. However, existing approaches to RAG fall short by neglecting system state variables, which are crucial for ensuring adaptive control, retrieval halting, and system convergence. In this paper, we introduce the TC-RAG through rigorous proof, a novel framework that addresses these challenges by incorporating a Turing Complete System to manage state variables, thereby enabling more efficient and accurate knowledge retrieval. By leveraging a memory stack system with adaptive retrieval, reasoning, and planning capabilities, TC-RAG not only ensures the controlled halting of retrieval processes but also mitigates the accumulation of erroneous knowledge via Push and Pop actions. In the case study of the medical domain, our extensive experiments on real-world healthcare datasets demonstrate the superiority of TC-RAG over existing methods in accuracy by over 7.20\%. Our dataset and code have been available at https://github.com/Artessay/TC-RAG .

cs.IR↗

arXiv2026

VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models

Long-video understanding depends not only on the capability of a vision-language model (VLM), but also on how its limited context is constructed from a much longer video. Existing systems typically introduce hand-designed sampling, retrieval, memory, or agentic control strategies, making the context-construction program itself difficult to study as an independent optimization target. We introduce VideoHarness-RSI, a controlled framework that recursively searches executable context constructors around a frozen VLM while keeping the answering model and interface fixed. We study this baseline under complementary weak- and strong-initialization regimes. From a weak uniform constructor, recursive search progressively discovers more structured context-construction programs; from a stronger AKS harness, the same process further advances an already competitive hand-crafted frontier. The resulting harness retains its advantage under a matched cumulative visual-token control and transfers directly to additional long-video benchmarks without further search. Together, these results establish executable context construction as a distinct optimization layer and provide an auditable baseline for studying harness discovery, transfer, and efficiency around frozen VLMs.

cs.AI↗

arXiv2026

Generalized Independence Test

Testing independence is a widely encountered problem in modern data analysis, especially in high-dimensional settings where complex dependency structures are common. Traditional methods often lack power in such scenarios. To address this, we propose a novel test statistic that leverages both similarity and dissimilarity information to capture intricate relationships within the data. The proposed test demonstrates strong power across a wide range of alternatives in high-dimensional settings, as shown through extensive simulation studies. Under mild conditions, we prove that the permutation null distribution of the statistic converges to the $χ^2_4$ distribution, enabling straightforward control of the type I error. Our theoretical analysis further advances the moment method to establish joint asymptotic normality for a class of double-indexed permutation statistics. Moreover, we prove the power consistency of the proposed test without imposing explicit restrictions on the data dimension, under mild conditions that allow for detecting complex dependencies. We illustrate the proposed test using gene-expression data from the Genotype-Tissue Expression project, where GIT rejects independence between the GTEx category "Breast - Mammary Tissue" and the cell-line category "Cells - EBV-transformed lymphocytes."

stat.ME↗

arXiv2026

Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis

Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G networks remains challenging due to complex cross-layer dependencies. While large language models (LLMs) offer promising capabilities for reasoning and knowledge integration, directly applying vanilla LLMs to telecom RCA often leads to hallucination, unstable reasoning, and poor alignment with structured network evidence. This work first reviews the evolution of telecom RCA from rule-based and machine learning (ML) approaches to emerging LLM-enabled techniques, and provides an overview of recent paradigms, including structured reasoning, retrieval-augmented knowledge grounding, agentic orchestration, and verifiable reasoning. Building upon these insights, we propose a structured reasoning framework for LLM-enabled telecom RCA that aligns diagnostic reasoning with telecom-specific evidence and domain knowledge. The proposed approach first organizes heterogeneous network telemetry into canonical contexts, and then enforces decision-path reasoning during diagnosis, and finally generates evidence-grounded explanations for reliable fault identification. Experimental results on two 5G RCA datasets, TeleLogs and TelecomTS, demonstrate that the proposed framework consistently improves diagnostic accuracy and decision consistency compared with baseline techniques. These cross-dataset results highlight the importance of structured reasoning design for practical LLM-based RCA systems in next-generation telecom networks.

cs.AI↗

arXiv2026

GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping

Existing feed-forward 3D reconstruction methods typically process a bounded number of images and recover cameras and geometry in local or internally normalized frames. Extending them to large-scale UAV mapping requires scalable multi-chunk processing and reliable aggregation, while full Sim(3) alignment can become unstable for near collinear trajectories. We present GeoFF3D, which combines a coordinate-anchored model with a spatial large-scale reconstruction framework (SLRF). The model uses georeferenced camera translations and optional geometric priors to predict camera poses and dense point maps directly in a gravity-aligned Z-up metric frame. SLRF partitions images into spatially overlapping chunks, propagates shared-view priors, and aggregates local reconstructions hierarchically, while remaining applicable to different bounded-view models. Across nine aerial mapping blocks, GeoFF3D achieves the best average reconstruction quality, improving F@5 from 0.829 for Pi3X + SLRF to 0.877. On long UAVScenes sequences, it reaches 0.848, compared with 0.687 for Pi3X + SLRF and 0.451 for the strongest evaluated SLAM/streaming baseline. GeoFF3D reconstructs 2,000 images in approximately five minutes, demonstrating scalable and robust large-scale UAV reconstruction.The code is available at https://github.com/yanxian-ll/GeoFF3D.

cs.CV↗

arXiv2026

Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift

Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, often involving multiple turns of clarification and revision. However, existing benchmarks primarily evaluate execution accuracy, leaving the unfolding and shifting of user intent across turns largely uncovered. To address this, we introduce TIDE-Bench, a benchmark for conversational text-to-SQL under chain ambiguity and intent drift evaluation, targeting two recurring patterns: chain ambiguity, where an underspecified question triggers layered clarification with conditional dependencies, and intent drift, where the user retracts and replaces a previously committed request element. Built on 514 anchor SQLs from BIRD, TIDE-Bench comprises 1,542 samples and introduces dedicated metrics for chain identification and drift recognition-resolution beyond execution accuracy. Evaluating 12 advanced LLMs reveals a persistent chain identification bottleneck unaffected by clarification frequency, a wide drift recognition-resolution gap, and overlap between failure modes when jointly activated. The corresponding code of TIDE-Bench is released for further research.

cs.CL↗

arXiv2026

Dual-Stream Semantic Guidance with Prototype Anchor Calibration for Source-Fully-Free Adaptation of Vision-Language Models

Source-Fully-Free Domain Adaptation (SFF-DA) has emerged as a strategic paradigm to adapt Vision-Language Models (VLMs) without any access to source data or task-specific source models. However, we identify a critical Dual Semantic Drift that hinders this process: static drift arising from the rigidity of fixed class embeddings, and dynamic drift stemming from the divergence of generated captions, causing severe semantic misalignment that intensifies the stability-plasticity dilemma. To address this, we propose DSSG (Dual-Stream Semantic Guidance), an end-to-end framework that reconciles fine-grained plasticity with global stability. Our core contribution is the Dual Semantic Guidance (DSG) module, which integrates a caption stream for domain-specific knowledge with a class-anchor stream to anchor global categorical consistency. Furthermore, a Dynamic Cross-Modal Knowledge Distillation (CMKD) module is introduced to leverage the evolving teacher distribution for calibrating teacher-student consistency. Building upon DSSG, we further introduce Prototype Anchor Calibration (PAC), yielding DSSG-PAC, which periodically calibrates prototype anchors and caches them until the next calibration. This design reduces redundant text-side computation while preserving the adaptability of class guidance to the evolving text space. We further establish SFF-DA risk bounds that relate student risk to semantic-teacher quality and teacher--student discrepancy. Extensive experiments demonstrate that DSSG consistently outperforms current state-of-the-art methods across multiple benchmarks, while DSSG-PAC largely preserves its adaptation performance with 18.9% lower total adaptation time. The code is available at https://github.com/mrmenand/DSSG.

cs.CV↗

arXiv2026

Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL

Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly elaborate pipelines around the base generator, yet existing studies typically report aggregate end-to-end accuracy, without quantifying the marginal accuracy-cost contribution of individual design choices. Consequently, providing a unified, paradigm-level cost-accuracy quantification remains a critical challenge for understanding and configuring modern text-to-SQL. To address this, we instantiate 17 paradigm-level configurations across five recurring modules of the ICL text-to-SQL pipeline under a single controlled implementation, and attribute each paradigm's marginal contribution and incurred cost across all four backbones spanning diverse capability levels and reasoning styles. Our analysis reveals that execution-feedback refinement is the only paradigm whose benefit holds universally at consistently low cost, while most other modules help only under backbone-dependent conditions. Token accounting shows that input demand is more closely tied to pipeline structure, whereas output demand is more sensitive to backbone generation behavior. Cross-module analysis further shows that stacking improves accuracy on most backbones, although how the gains compose varies with backbone capability. We also find that a fixed budget is often better spent engineering a more elaborate pipeline over a mid-tier backbone than upgrading to a frontier model with a lean pipeline. These findings distill into an actionable, cost-aware tiered guideline that transfers to five additional backbones without per-paradigm search.

cs.CL↗