AIの鬼

研究動向 (arXiv)

機械学習・自然言語処理・コンピュータビジョンの最新プレプリント。

cs.CVcs.AIcs.LG

Multi-Scale ViT Inference with Habitat-Fit Priors and kNN Retrieval for Multi-Species Plant Identification

Alper Erten, Murilo Gustineli, Adrian Cheung

This paper describes DS@GT ARC's third-place solution to the PlantCLEF 2026 challenge on multi-species plant identification in vegetation quadrat images, where systems must predict every species present in high-resolution (~3000 x 3000 pixel) plot photographs while training only on single-label images of individual plants. The pipeline is built around a fine-tuned DINOv2 ViT-L/14 classifier applied over a multi-scale tile decomposition of each quadrat, with per-tile predictions blended with a FA…

arXiv → PDF
cs.LGcs.AI

Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards

Yuxuan Zhu, Rohan Alur, Daniel Kang

While reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capabilities of large language models (LLMs), the generalizability of the resulting models remains poorly understood. In this work, we establish the first non-vacuous generalization bounds for parameter-efficient RLVR fine-tuning at the billion-parameter scale. Our approach adapts PAC-Bayes compression bounds to this setting, and addresses the inherent stochasticity of token generation by applying…

arXiv → PDF
cs.AI

Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions

Yijiang Li, Huiqi Zou, Bingyang Wang, Ziang Xiao

Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a framework that recasts evaluation as a three-party inter…

arXiv → PDF
cs.CV

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation

Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu, Xu Zheng, Zidong Cao, Lutao Jiang, Zixin Zhang, Huiyu Zhou et al.

Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (MLLMs) to interact with the real world. However, existing MLLMs struggle to perform effective spatial reasoning in complex egocentric scenes due to their limited spatial perception capabilities. To this end, we introduce Ego Scene Augmentation (ESA), an egocentric spatial perception framework, which actively enhances the spatial perception capabilities…

arXiv → PDF
cs.AIcs.IRcs.LG

SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation

Yiming Zhang, Koji Tsuda

Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form. We study the latter paradigm. Recent large language model agents make semantic parsing interactive: they alternate between reasoning, querying the knowledge base, and extending a partial SPARQL query. This interleaving reduces reliance on one-shot generation, but makes the quality of \emph{KB grounding}…

arXiv → PDF
cs.SIcs.CL

Manufactured Divisiveness: Decomposing the Hostile Content of Seven Social Media Influence Operations

Emilio Ferrara

State-backed influence operations are routinely measured as high-prevalence sources of ``hate'' and ``toxicity.'' We argue those rates rest on a measurement error: the detectors behind them are validated to catch a broader definition inclusive of hostility or divisiveness aimed at an out-group, and so over-attribute hate to content better described as partisan or geopolitical invective. Across 25.08M tweets from seven government-attributed campaigns in the Twitter Information Operations archive…

arXiv → PDF
cs.DCcs.AI

EdgeFaaS: A Function-based Framework for Edge Computing

Neha Vadnere, Yu-Ting Wang, Yitao Chen, Sreehari Sadesh, Ming Zhao

Edge computing brings unique challenges as the resources on the edge are highly diverse in capabilities and capacities, and highly distributed across many users and the physical world. Existing distributed computing frameworks cannot adequately handle this level of heterogeneity and distribution. This paper proposes EdgeFaaS, a novel function-based edge computing framework to enable edge applications to effectively utilize heterogeneous resources distributed across the Internet of Things (IoT),…

arXiv → PDF
physics.chem-phcond-mat.mtrl-scics.LG

Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields

Sheng Bi, Yi-Ze Wang, Jun Cheng

Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard model-committee uncertainty is impractical for foundation MLFFs because each committee member requires a separate fine-tuning run. We present an active-learning workflow based on last-layer-projection regression (LLPR),…

arXiv → PDF
cs.AI

Step-Level Preference Learning for Generative Agents in Social Simulations

Wenchang Gao, Pingyue Sheng, Lanlan Qiu, Yunfei Ma, Jian Zhao, Baicheng Chen, Kangda Wang, Yuyang Tian et al.

Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection. However, fine-grained human annotations of these intermediate steps remain scarce, and existing agents are not grounded in human preferences over such intermediate decisions. To address this gap, we introduce \method, an interactive simulation interface that enables us to co…

arXiv → PDF
cs.CV

Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency

Andreas Meuleman, Linus Franke, Boris Zhestiankin, Camille Montemagni, George Drettakis

3D Gaussian Splatting (3DGS) has become the method of choice for reconstructing and real-time rendering of captured scenes. To capture a scene with good visual quality, continuous image sequences are usually combined with out-of-order shots for better scene coverage. Structure from motion can reconstruct such captures, but only after they are all available and often with high computational cost. Incremental reconstruction methods -- often derived from SLAM solutions -- provide immediate feedback…

arXiv → PDF