arXiv subjects

Boyang Li

Publications and source records attributed to Boyang Li.

At least 55 records · Page 3Linked to original sources

arXiv2026

Injecting Knowledge from Social Science Journals to Improve Indonesian Cultural Understanding by LLMs

Recently there have been intensifying efforts to improve the understanding of Indonesian cultures by large language models (LLMs). An attractive source of cultural knowledge that has been largely overlooked is local journals of social science, which likely contain substantial cultural studies from a native perspective. We present a novel text dataset of journal article passages, created from 151 open-source Indonesian social science journals, called IndoSoSci. We demonstrate an effective recipe for injecting Indonesian cultural knowledge therein into LLMs: extracting the facts related to Indonesian culture, and apply retrieval-augmented generation (RAG) with LLM-generated hypothetical documents as queries during retrieval. The proposed recipe yields strong performance gains over several strong baselines on the IndoCulture benchmark. Additionally, by combining IndoSoSci with Indonesian Wikipedia, we set a new state-of-the-art accuracy on the IndoCulture benchmark.

cs.CL↗

arXiv2026

Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs

Vision-Language Models (VLMs) are increasingly used in safety-critical applications that require reliable visual grounding. However, these models often hallucinate details that are not present in the image to satisfy user prompts. While recent datasets and benchmarks have been introduced to evaluate systematic hallucinations in VLMs, many hallucination behaviors remain insufficiently characterized. In particular, prior work primarily focuses on object presence or absence, leaving it unclear how prompt phrasing and structural constraints can systematically induce hallucinations. In this paper, we investigate how different forms of prompt pressure influence hallucination behavior. We introduce Ghost-100, a procedurally generated dataset of synthetic scenes in which key visual details are deliberately removed, enabling controlled analysis of absence-based hallucinations. Using a structured 5-Level Prompt Intensity Framework, we vary prompts from neutral queries to toxic demands and rigid formatting constraints. We evaluate three representative open-weight VLMs: MiniCPM-V 2.6-8B, Qwen2-VL-7B, and Qwen3-VL-8B. Across all three models, hallucination rates do not increase monotonically with prompt intensity. All models exhibit reductions at higher intensity levels at different thresholds, though not all show sustained reduction under maximum coercion. These results suggest that current safety alignment is more effective at detecting semantic hostility than structural coercion, revealing model-specific limitations in handling compliance pressure. Our dataset is available at: https://github.com/bli1/tone-matters

cs.CV↗

arXiv2025

E-Navi: Environmental Adaptive Navigation for UAVs on Resource Constrained Platforms

The ability to adapt to changing environments is crucial for the autonomous navigation systems of Unmanned Aerial Vehicles (UAVs). However, existing navigation systems adopt fixed execution configurations without considering environmental dynamics based on available computing resources, e.g., with a high execution frequency and task workload. This static approach causes rigid flight strategies and excessive computations, ultimately degrading flight performance or even leading to failures in UAVs. Despite the necessity for an adaptive system, dynamically adjusting workloads remains challenging, due to difficulties in quantifying environmental complexity and modeling the relationship between environment and system configuration. Aiming at adapting to dynamic environments, this paper proposes E-Navi, an environmental-adaptive navigation system for UAVs that dynamically adjusts task executions on the CPUs in response to environmental changes based on available computational resources. Specifically, the perception-planning pipeline of UAVs navigation system is redesigned through dynamic adaptation of mapping resolution and execution frequency, driven by the quantitative environmental complexity evaluations. In addition, E-Navi supports flexible deployment across hardware platforms with varying levels of computing capability. Extensive Hardware-In-the-Loop and real-world experiments demonstrate that the proposed system significantly outperforms the baseline method across various hardware platforms, achieving up to 53.9% navigation task workload reduction, up to 63.8% flight time savings, and delivering more stable velocity control.

cs.RO↗

arXiv2025

AskNearby: An LLM-Based Application for Neighborhood Information Retrieval and Personalized Cognitive-Map Recommendations

The "15-minute city" envisions neighborhoods where residents can meet daily needs via a short walk or bike ride. Realizing this vision requires not only physical proximity but also efficient and reliable access to information about nearby places, services, and events. Existing location-based systems, however, focus mainly on city-level tasks and neglect the spatial, temporal, and cognitive factors that shape localized decision-making. We conceptualize this gap as the Local Life Information Accessibility (LLIA) problem and introduce AskNearby, an AI-driven community application that unifies retrieval and recommendation within the 15-minute life circle. AskNearby integrates (i) a three-layer Retrieval-Augmented Generation (RAG) pipeline that synergizes graph-based, semantic-vector, and geographic retrieval with (ii) a cognitive-map model that encodes each user's neighborhood familiarity and preferences. Experiments on real-world community datasets demonstrate that AskNearby significantly outperforms LLM-based and map-based baselines in retrieval accuracy and recommendation quality, achieving robust performance in spatiotemporal grounding and cognitive-aware ranking. Real-world deployments further validate its effectiveness. By addressing the LLIA challenge, AskNearby empowers residents to more effectively discover local resources, plan daily activities, and engage in community life.

cs.IR↗

arXiv2025

Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding

Video Temporal Grounding (VTG) aims to localize a temporal segment in a video corresponding to a natural language query. However, existing VTG models assume that a relevant segment always exists, causing them to always predict a target segment even when the query is irrelevant to the video. While recent approaches attempt to handle irrelevant queries, they can only reject those that are entirely unrelated to the video and still fail to handle hard-irrelevant queries that are semantically similar but not actually relevant. To address this, we propose Refusal-Aware Reinforcement Fine-Tuning (RA-RFT) to effectively refuse hard-irrelevant queries in VTG. Our method is based on the Group Relative Policy Optimization (GRPO) framework and integrates four reward objectives-format, refuse-IoU, explain, and query correction-to improve both relevance discrimination and fine-grained semantic reasoning. In addition, to effectively support RA-RFT, we construct a Hard-Irrelevant VTG (HI-VTG) dataset, which includes hard-irrelevant queries and their refusal answers. We demonstrate the effectiveness of our method across various relevance-aware VTG scenarios, including hard-irrelevant VTG, simply-shuffled RA-VTG, and human-annotated RA-VTG settings. We also show that the proposed method is scalable by applying it to various LVLM-based VTG models. Our code is available at https://github.com/JINSUBY/RA-RFT.

cs.CV↗

arXiv2025

Two Causally Related Needles in a Video Haystack

Properly evaluating the ability of Video-Language Models (VLMs) to understand long videos remains a challenge. We propose a long-context video understanding benchmark, Causal2Needles, that assesses two crucial abilities insufficiently addressed by existing benchmarks: (1) extracting information from two separate locations (two needles) in a long video and understanding them jointly, and (2) modeling the world in terms of cause and effect in human behaviors. Causal2Needles evaluates these abilities using noncausal one-needle, causal one-needle, and causal two-needle questions. The most complex question type, causal two-needle questions, require extracting information from both the cause and effect events from a long video and the associated narration text. To prevent textual bias, we introduce two complementary question formats: locating the video clip containing the answer, and verbal description of a visual detail from that video clip. Our experiments reveal that models excelling on existing benchmarks struggle with causal 2-needle questions, and the model performance is negatively correlated with the distance between the two needles. These findings highlight critical limitations in current VLMs. The dataset is available at: https://huggingface.co/datasets/causal2needles/Causal2Needles

cs.CV↗

arXiv2025

Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective

With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how a problem is decomposed into subproblems and on the topological organization of these subproblems whether sequential, parallel, or tree-structured. This perspective allows us to unify diverse approaches such as Chain-of-Thought, Branch-Solve-Merge, and Tree-of-Thought under a common lens. We further synthesize existing analyses of these techniques, highlighting their respective strengths and weaknesses, and conclude by outlining promising directions for future research

cs.CL↗

arXiv2025

RRCANet: Recurrent Reusable-Convolution Attention Network for Infrared Small Target Detection

Infrared small target detection is a challenging task due to its unique characteristics (e.g., small, dim, shapeless and changeable). Recently published CNN-based methods have achieved promising performance with heavy feature extraction and fusion modules. To achieve efficient and effective detection, we propose a recurrent reusable-convolution attention network (RRCA-Net) for infrared small target detection. Specifically, RRCA-Net incorporates reusable-convolution block (RuCB) in a recurrent manner without introducing extra parameters. With the help of the repetitive iteration in RuCB, the high-level information of small targets in the deep layers can be well maintained and further refined. Then, a dual interactive attention aggregation module (DIAAM) is proposed to promote the mutual enhancement and fusion of refined information. In this way, RRCA-Net can both achieve high-level feature refinement and enhance the correlation of contextual information between adjacent layers. Moreover, to achieve steady convergence, we design a target characteristic inspired loss function (DpT-k loss) by integrating physical and mathematical constraints. Experimental results on three benchmark datasets (e.g. NUAA-SIRST, IRSTD-1k, DenseSIRST) demonstrate that our RRCA-Net can achieve comparable performance to the state-of-the-art methods while maintaining a small number of parameters, and act as a plug and play module to introduce consistent performance improvement for several popular IRSTD methods.

cs.CV↗

arXiv2025

GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving

Multi-sensor fusion is crucial for improving the performance and robustness of end-to-end autonomous driving systems. Existing methods predominantly adopt either attention-based flatten fusion or bird's eye view fusion through geometric transformations. However, these approaches often suffer from limited interpretability or dense computational overhead. In this paper, we introduce GaussianFusion, a Gaussian-based multi-sensor fusion framework for end-to-end autonomous driving. Our method employs intuitive and compact Gaussian representations as intermediate carriers to aggregate information from diverse sensors. Specifically, we initialize a set of 2D Gaussians uniformly across the driving scene, where each Gaussian is parameterized by physical attributes and equipped with explicit and implicit features. These Gaussians are progressively refined by integrating multi-modal features. The explicit features capture rich semantic and spatial information about the traffic scene, while the implicit features provide complementary cues beneficial for trajectory planning. To fully exploit rich spatial and semantic information in Gaussians, we design a cascade planning head that iteratively refines trajectory predictions through interactions with Gaussians. Extensive experiments on the NAVSIM and Bench2Drive benchmarks demonstrate the effectiveness and robustness of the proposed GaussianFusion framework. The source code will be released at https://github.com/Say2L/GaussianFusion.

cs.RO↗

arXiv2025

Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between task-specific experts and the unified model, either from a parameter-level or a task-loss perspective. However, parameter-level methods exhibit a significant performance gap compared to the upper bound, while task-loss approaches entail costly secondary training procedures. In contrast, we observe that performance degradation closely correlates with feature drift, i.e., differences in feature representations of the same sample caused by model merging. Motivated by this observation, we propose Layer-wise Optimal Task Vector Merging (LOT Merging), a technique that explicitly minimizes feature drift between task-specific experts and the unified model in a layer-by-layer manner. LOT Merging can be formulated as a convex quadratic optimization problem, enabling us to analytically derive closed-form solutions for the parameters of linear and normalization layers. Consequently, LOT Merging achieves efficient model consolidation through basic matrix operations. Extensive experiments across vision and vision-language benchmarks demonstrate that LOT Merging significantly outperforms baseline methods, achieving improvements of up to 4.4% (ViT-B/32) over state-of-the-art approaches. The source code is available at https://github.com/SunWenJu123/model-merging.

cs.LG↗

arXiv2025

Advancing AI-Driven Analysis in X-ray Absorption Spectroscopy: Spectral Domain Mapping and Universal Models

In recent years, rapid progress has been made in developing artificial intelligence (AI) and machine learning (ML) methods for x-ray absorption spectroscopy (XAS) analysis. Compared to traditional XAS analysis methods, AI/ML approaches offer dramatic improvements in efficiency and help eliminate human bias. To advance this field, we advocate an AI-driven XAS analysis pipeline that features several inter-connected key building blocks: benchmarks, workflows, databases, and AI/ML models. Specifically, we present two case studies for XAS ML. In the first study, we demonstrate the importance of reconciling the discrepancies between simulation and experiment using spectral domain mapping (SDM). Our ML model, which is trained solely on simulated spectra, predicts an incorrect oxidation state trend for Ti atoms in a combinatorial zinc titanate film. After transforming the experimental spectra into a simulation-like representation using SDM, the same model successfully recovers the correct oxidation state trend. In the second study, we explore the development of universal XAS ML models that are trained on the entire periodic table, which enables them to leverage common trends across elements. Looking ahead, we envision that an AI-driven pipeline can unlock the potential of real-time XAS analysis to accelerate scientific discovery.

cond-mat.mtrl-sci↗

arXiv2025

Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection

Infrared small target detection presents significant challenges due to the limited intrinsic features of the target and the overwhelming presence of visually similar background distractors. We contend that background semantics are critical for distinguishing between objects that appear visually similar in this context. To address this challenge, we propose a task, clustered infrared small target detection, and introduce DenseSIRST, a benchmark dataset that provides per-pixel semantic annotations for background regions. This dataset facilitates the shift from sparse to dense target detection. This dataset facilitates the shift from sparse to dense target detection. Building on this resource, we propose the Background-Aware Feature Exchange Network (BAFE-Net), a multi-task architecture that jointly tackles target detection and background semantic segmentation. BAFE-Net incorporates a dynamic cross-task feature hard-exchange mechanism, enabling the effective exchange of target and background semantics between the two tasks. Comprehensive experiments demonstrate that BAFE-Net significantly enhances target detection accuracy while mitigating false alarms. The DenseSIRST dataset, along with the code and trained models, is publicly available at https://github.com/GrokCV/BAFE-Net.

cs.CV↗

arXiv2025

MolmoAct: Action Reasoning Models that can Reason in Space

Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of robotic foundation models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes observations and instructions into depth-aware perception tokens, generates mid-level spatial plans as editable trajectory traces, and predicts precise low-level actions, enabling explainable and steerable behavior. MolmoAct-7B-D achieves strong performance across simulation and real-world settings: 70.5% zero-shot accuracy on SimplerEnv Visual Matching tasks, surpassing closed-source Pi-0 and GR00T N1.5; 86.6% average success on LIBERO, including an additional 6.3% gain over ThinkAct on long-horizon tasks; and in real-world fine-tuning, an additional 10% (single-arm) and an additional 22.7% (bimanual) task progression over Pi-0-FAST. It also outperforms baselines by an additional 23.3% on out-of-distribution generalization and achieves top human-preference scores for open-ended instruction following and trajectory steering. Furthermore, we release, for the first time, the MolmoAct Dataset -- a mid-training robot dataset comprising over 10,000 high quality robot trajectories across diverse scenarios and tasks. Training with this dataset yields an average 5.5% improvement in general performance over the base model. We release all model weights, training code, our collected dataset, and our action reasoning dataset, establishing MolmoAct as both a state-of-the-art robotics foundation model and an open blueprint for building ARMs that transform perception into purposeful action through structured reasoning. Blogpost: https://allenai.org/blog/molmoact

cs.RO↗

arXiv2025

Copycat vs. Original: Multi-modal Pretraining and Variable Importance in Box-office Prediction

The movie industry is associated with an elevated level of risk, which necessitates the use of automated tools to predict box-office revenue and facilitate human decision-making. In this study, we build a sophisticated multimodal neural network that predicts box offices by grounding crowdsourced descriptive keywords of each movie in the visual information of the movie posters, thereby enhancing the learned keyword representations, resulting in a substantial reduction of 14.5% in box-office prediction error. The advanced revenue prediction model enables the analysis of the commercial viability of "copycat movies," or movies with substantial similarity to successful movies released recently. We do so by computing the influence of copycat features in box-office prediction. We find a positive relationship between copycat status and movie revenue. However, this effect diminishes when the number of similar movies and the similarity of their content increase. Overall, our work develops sophisticated deep learning tools for studying the movie industry and provides valuable business insight.

cs.MM↗

arXiv2025

Leveraging OS-Level Primitives for Robotic Action Management

End-to-end imitation learning frameworks (e.g., VLA) are increasingly prominent in robotics, as they enable rapid task transfer by learning directly from perception to control, eliminating the need for complex hand-crafted features. However, even when employing SOTA VLA-based models, they still exhibit limited generalization capabilities and suboptimal action efficiency, due to the constraints imposed by insufficient robotic training datasets. In addition to addressing this problem using model-based approaches, we observe that robotic action slices, which consist of contiguous action steps, exhibit strong analogies to the time slices of threads in traditional operating systems. This insight presents a novel opportunity to tackle the problem at the system level. In this paper, we propose AMS, a robot action management system enhanced with OS-level primitives like exception, context switch and record-and-replay, that improves both execution efficiency and success rates of robotic tasks. AMS first introduces action exception, which facilitates the immediate interruption of robotic actions to prevent error propagation. Secondly, AMS proposes action context, which eliminates redundant computations for VLA-based models, thereby accelerating execution efficiency in robotic actions. Finally, AMS leverages action replay to facilitate repetitive or similar robotic tasks without the need for re-training efforts. We implement AMS in both an emulated environment and on a real robot platform. The evaluation results demonstrate that AMS significantly enhances the model's generalization ability and action efficiency, achieving task success rate improvements ranging from 7x to 24x and saving end-to-end execution time ranging from 29% to 74% compared to existing robotic system without AMS support.

cs.OS↗

arXiv2025

Stable Tracking of Eye Gaze Direction During Ophthalmic Surgery

Ophthalmic surgical robots offer superior stability and precision by reducing the natural hand tremors of human surgeons, enabling delicate operations in confined surgical spaces. Despite the advancements in developing vision- and force-based control methods for surgical robots, preoperative navigation remains heavily reliant on manual operation, limiting the consistency and increasing the uncertainty. Existing eye gaze estimation techniques in the surgery, whether traditional or deep learning-based, face challenges including dependence on additional sensors, occlusion issues in surgical environments, and the requirement for facial detection. To address these limitations, this study proposes an innovative eye localization and tracking method that combines machine learning with traditional algorithms, eliminating the requirements of landmarks and maintaining stable iris detection and gaze estimation under varying lighting and shadow conditions. Extensive real-world experiment results show that our proposed method has an average estimation error of 0.58 degrees for eye orientation estimation and 2.08-degree average control error for the robotic arm's movement based on the calculated orientation.

cs.RO↗

arXiv2025

EANS: Reducing Energy Consumption for UAV with an Environmental Adaptive Navigation Strategy

Unmanned Aerial Vehicles (UAVS) are limited by the onboard energy. Refinement of the navigation strategy directly affects both the flight velocity and the trajectory based on the adjustment of key parameters in the UAVS pipeline, thus reducing energy consumption. However, existing techniques tend to adopt static and conservative strategies in dynamic scenarios, leading to inefficient energy reduction. Dynamically adjusting the navigation strategy requires overcoming the challenges including the task pipeline interdependencies, the environmental-strategy correlations, and the selecting parameters. To solve the aforementioned problems, this paper proposes a method to dynamically adjust the navigation strategy of the UAVS by analyzing its dynamic characteristics and the temporal characteristics of the autonomous navigation pipeline, thereby reducing UAVS energy consumption in response to environmental changes. We compare our method with the baseline through hardware-in-the-loop (HIL) simulation and real-world experiments, showing our method 3.2X and 2.6X improvements in mission time, 2.4X and 1.6X improvements in energy, respectively.

cs.RO↗

arXiv2025

SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation

Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception and Hierarchical Evaluation of REasoning), a hierarchical evaluation framework supported by a new human-annotated dataset. SPHERE systematically probes models across increasing levels of complexity, from fundamental skills to multi-skill integration and high-level reasoning that combines spatial, visual, and logical understanding. Benchmark evaluation of state-of-the-art models reveals significant deficiencies, especially in reasoning about distance and proximity, understanding both egocentric and allocentric perspectives, and applying spatial logic in physical contexts. These findings expose critical blind spots in existing models and underscore the need for more advanced spatial reasoning techniques, driving the development of vision-language models that align more closely with human spatial cognition. The SPHERE benchmark is available at https://github.com/zwenyu/SPHERE-VLM.

cs.CV↗