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.CL

Analyzing Occupational Gender Bias across the LLM Training Lifecycle

Manthan Gadhia, Alexander Hoyle, Karolina Stańczak

Post-training is widely assumed to reduce the social biases language models inherit from pretraining, yet direct evidence for this assumption remains mixed. In this paper, we examine how gender disparities evolve across the language modeling pipeline. In particular, we study occupational gender bias in OLMo 3, a fully open language model family, across its post-training stages by prompting each checkpoint to generate open-ended narratives about synthetic personas given their occupation and educa…

arXiv → PDF
cs.CL

MARS: Memory-Aware Routing for Session-Level LLM Assistants

Minghan Wang, Jinhang Zuo, Zhongxiang Dai, Zhiyong Wang, Fang Kong

Long-term LLM assistants must repeatedly decide what prior context to expose and which model should answer as an interaction evolves. Existing memory systems and model routers usually make these decisions separately, although memory construction changes the evidence, distractors, and difficulty of the resulting input. We introduce MARS, a memory-aware routing framework that uses session state as a shared control interface between memory construction and model selection. A Query and Topic Manager…

arXiv → PDF
cs.CV

CLEAR: Cooperative Latent Flow for Visual Counterfactual Explanations with Accurate Region Preservation

Yan Zeng, Changlu Guo, Oskar Kristoffersen, Anders Nymark Christensen, Morten Rieger Hannemose, Anders Bjorholm Dahl

Visual counterfactual explanations (VCEs) should alter a classifier's prediction while remaining realistic and preserving decision-irrelevant content. Image-space methods provide high-quality counterfactuals but are computationally costly, whereas latent-space methods are more efficient but often less faithful. We identify two sources responsible for this gap. First, latent generation recovers a natural sample from a perturbed representation, whereas classifier guidance pushes it toward a target…

arXiv → PDF
cs.AI

Darwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving Agents

Mingze Yin, Xiaohan Wang, Dian Li, Longfei Luo, Jiahong Yan, Yiheng Zhu, Chang-Yu Hsieh

While Large Language Model (LLM) agents have demonstrated remarkable capabilities across complex tasks, they predominantly operate in isolated sessions, lacking the ability to continually learn from historical interactions or adapt to user-specific environments. Existing self-evolution paradigms often indiscriminately inject raw interaction trajectories into memory or skill modules, leading to obscured behavioral patterns and compromised update controllability. Furthermore, as foundational LLM r…

arXiv → PDF
cs.LG

BMuon: Budgeting Muon's Spectral Geometry for Structured Compressibility

Rida Assalouh, Tom Jacobs, Rebekka Burkholz, Yani Ioannou, Umut Şimşekli

Muon has emerged as a strong optimizer for neural network training and admits an interpretation as steepest descent under a spectral-norm geometry. Yet we find that Muon-trained Transformers can degrade sharply when their MLP hidden channels are pruned after training. To reconcile Muon's optimization performance with structured compressibility, we introduce Budget Muon (BMuon), which modifies Muon's spectral geometry so that hidden channels across blocks compete for a shared allocation budget. T…

arXiv → PDF
stat.MLcs.LGmath.OCstat.ME

A general recipe for data-adaptive anytime-valid envelopes for iterative algorithms

Soham Bonnerjee, Aaditya Ramdas

Most convergence guarantees for iterative stochastic algorithms are stated at a fixed iteration count and do not justify stopping at a data-dependent time. Recent work has constructed anytime-valid envelopes that do, but deterministic envelopes are typically too conservative for practical stopping, and existing data-adaptive ones are derived case-by-case, each coupling a specific algorithm to a specific noise model and boundary construction. This paper provides a general recipe for constructing…

arXiv → PDF
cs.CV

From Adult Renal Masses to Pediatric Wilms Tumors: Evaluating Cross-Domain Generalization of Kidney Lesion Segmentation on MRI

Sarah de Boer, Myrthe A. D. Buser, Hartmut Häntze, Jawed Nawabi, Lisa C. Adams, Alida F. W. van der Steeg, Marry M. van den Heuvel-Eibrink, Annemieke S. Littooij et al.

Deep learning segmentation models for pediatric oncology are often trained on small, single-center cohorts, whereas much larger datasets exist for adult diseases, such as kidney cancer. Whether models trained on adult renal lesions generalize to pediatric Wilms tumors remains unclear. We trained a segmentation model on single-sequence T1- or T2-weighted adult kidney MRI and evaluated it on a held-out adult test set and a pediatric Wilms tumor cohort, where it was compared with a pediatric-specif…

arXiv → PDF
cs.LGstat.ML

Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search

Quynh Trinh, Trung Nguyen, Nam Nguyen, Tuan Dam

Monte-Carlo Tree Search (MCTS) typically stores only scalar mean estimates, which makes it poorly suited for tail-risk objectives such as conditional value-at-risk (CVaR). We introduce Categorical Thompson Sampling with Optimism (CATSO) and Particle Thompson Sampling with Optimism (PATSO), two distributional MCTS algorithms that maintain finite-support empirical backup laws at Q-edges. CATSO represents Q-edge laws with categorical atoms and Dirichlet Thompson sampling, while PATSO represents the…

arXiv → PDF
cs.CV

LiveSync: Iterative Self-Training for Lip-Sync Generation

Huaishao Luo, Huan Zhang, Guanbo Bao, Yinglu Liu, Youzheng Wu, Xiaodong He

Audio-driven lip synchronization aims to match target speech through localized mouth and jaw articulation while preserving subject identity, head pose, and surrounding facial context. Naturally recorded videos provide synchronized reconstruction targets but rarely offer pairs that are matched in identity and pose yet differ primarily in speech-related articulation. Mask-based training enables reconstruction from these videos, but random-reference inputs differ from the aligned self-reference use…

arXiv → PDF
eess.SPcs.LG

Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection

Wei-Hsiang Ma, Ya-Tse Wu, Hsing-Hang Chou, Chi-Chun Lee

Stress detection based on heart rate variability (HRV) has received increasing attention. However, existing personalized approaches integrate personal attributes with HRV through latent representations, limiting the interpretability of their interactions. In this work, we propose an LLM-enhanced personalized stress detection framework that integrates HRV features and personal attributes through LLM-based semantic interpretation. The proposed framework achieves a 29.9% relative MCC improvement ov…

arXiv → PDF
cs.AI

SkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents

Jin Ye, Yifan Jiang, Lan-zhe Guo

Large language model agents increasingly rely on skills to extend their capabilities in complex tasks. However, scalable skill use requires Selective Skill Exposure (SSE): providing relevant procedural content when needed while avoiding unnecessary exposure that may disrupt reasoning. Existing paradigms fall short in complementary ways. Progressive disclosure exposes metadata for a growing skill library, introducing context pollution; retrieval limits catalog exposure, but static retrieval from…

arXiv → PDF
cs.ROcs.AI

Reason-guided Human Reward Modeling for Preference-based Reinforcement Learning

Anshul Nayak, Shahil Shaik, Jonathan Smereka, Yue Wang

Reinforcement learning (RL) policies optimized for task rewards may produce behaviors that are efficient but misaligned with human expectations, safety preferences, or intent. This paper presents a reason-guided preference-based reinforcement learning (PbRL) framework that learns a human reward model from trajectory-level feedback. In addition to preference labels, the framework incorporates reason tags explaining why a behavior is preferred, enabling the learned reward to capture both human cho…

arXiv → PDF
stat.MEcs.LGstat.ML

Causal Discovery beyond Conditional Independence: Identifiability, Algorithms, and Statistical Inference for Directed Acyclic and Cyclic Graphs

Yang Ni

Learning causal structure from data requires assumptions about mechanisms, noises, observation schemes, and interventions. Historically, causal discovery has relied primarily on conditional independence. This review focuses on modern causal discovery methods that exploit properties of distributions beyond conditional independence. Our organizing principle separates the source of identification from the statistical estimator and its computational implementation. This perspective connects conditio…

arXiv → PDF
cs.CVcs.CL

Execution Before Memory: Diagnosing Memory Failures in Video World Models

Weiyang Jin, Jiwen Yu, Sihan Xu, Yuwei Niu, Xihui Liu

A memory test for a video world model should say whether the scene was set, whether the asked change was carried out, and whether the last frame shows the result. Current tests fold these into one number, so a low score is easy to read as forgetting. When the change is not carried out, the hidden state transition cannot appear, so the test is not really a test of memory. We introduce MIST, an evaluation that separates the change from the memory it should leave behind. The model first sets the sc…

arXiv → PDF
cs.CLcs.SDeess.AS

ConvexLLM: Scaling Convex-Hull Speech Interfaces to General-Purpose Audio Intelligence

Ming-Hao Hsu, Shujie Liu, Yuxuan Hu, Yuxiang Wang, Yingda Shen, Jinyu Li, Zhizheng Wu

Speech and audio language models connect continuous acoustic representations to decoders pretrained primarily on text data. Most such models use MLP or Q-Former interfaces to map acoustic features into the decoder's input space, requiring the decoder to learn how to interpret the resulting representations. We investigate whether grounding these representations in the decoder's existing text embeddings can help it use acoustic information while better preserving its pretrained text capabilities.…

arXiv → PDF
cs.CV

PanoBench: A Panoptic Occupancy Prediction Benchmark for Autonomous Driving

Yi Feng, Zizhan Guo, Junwu E, Yu Ma, Mengtan Zhang, Jin Wu, Wei Ye, Hanli Wang et al.

Panoptic occupancy unifies 3D geometry, semantics, and instance identities, but its development is limited by scarce instance-aware annotations. Existing benchmarks mainly provide semantic labels reconstructed from incomplete sensor observations, while panoptic datasets have limited domain coverage or annotation completeness. We introduce PanoBench, a camera-centric panoptic occupancy prediction benchmark spanning synthetic and real-world driving scenes. It combines PanoBench-CarlaOcc, PanoBench…

arXiv → PDF
cs.CV

PreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image Editing

Jingyi Wang, Xiao Lu

Recent one-step text-to-image (T2I) models enable efficient image synthesis, opening up new possibilities for interactive Web-based image editing. However, existing one-step editing methods often construct a global transport field through simple vector operations between conditional predictions. While such strong transport can effectively drive the image toward the target semantics, it may be released along unreliable directions or over non-edited regions, leading to structural distortions withi…

arXiv → PDF
cs.CRcs.AI

From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation

Gabriel Hortea, Simon Pietro Romano, Juan Tapiador, Mario Varlese

Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computational footprint. These characteristics also make them candidates for future autonomous malware, where connectivity, latency, privacy, or operational constraints may preclude cloud-based inference. Yet the ability of ultra-compact models to support malware during post-exploitation remains poorly understood. We systematically evaluate seven open-source SLMs (20M-1.5B parameters)…

arXiv → PDF
cs.CV

ReVision: Reprogramming Image Generators for Dense Visual Perception

Yitong Yang, Yinglin Wang, Xuexin Liu, Wei Chen, Zhaoyang Xu, Jiaxin Lin, Rui Chen, Shuting He et al.

Recent image generators exhibit rich visual priors that can support dense visual perception. However, existing approaches typically encode multiple perception tasks into a shared parameterization, making joint training sensitive to the mixture and weighting of heterogeneous data and prone to cross-task interference. To address this issue, we introduce ReVision, an instruction-conditioned parameter generation framework built on a frozen multimodal understanding model and a frozen image generator.…

arXiv → PDF
cs.CV

PONDER: Learning to Generate in the Right Order

Julius Erbach, Dominik Narnhofer, Bernt Schiele, Jan Eric Lenssen, Konrad Schindler

We introduce PONDER, a method that learns in which order an image generator should fill in content and which of its earlier predictions to revise. Masked generative models construct a sample by repeatedly filling in subsets of missing variables. The order of these partial predictions determines the context available in subsequent steps and therefore affects the quality of the final sample. Common strategies are to choose the order randomly or based on local confidence estimates. Conditioned on t…

arXiv → PDF
cs.CL

EduWild: How Teacher-Configured Chatbots Fail in Real-World Use and How to Fix Them

Ziqi Liu, Ruiwei Xiao, Yuxuan Li, John Stamper

Teachers increasingly configure educational chatbots through natural-language instructions, but how these bots fail in real-world use remains poorly understood. We introduce EduWild, a dataset of 1,726 conversations with 217 teacher-configured chatbots, each paired with the instructions and configuration behind it, including 900 conversations from the intended end users of 35 deployed chatbots. We develop a 29-code taxonomy covering factual, workflow, diagnostic, and pedagogical failures and app…

arXiv → PDF
cs.LG

Out of Support, Not Out of Reach: In-Context Learning with Unsupported Instructions and Composed Tasks

Xuhan Tong, Yuchen Zeng, Jiawei Zhang

In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks from a small set of input-output demonstrations, without parameter updates. Yet existing theory primarily explains ICL as identifying a latent task already represented in pretraining, leaving unclear whether ICL can succeed when either the instruction or the target task falls outside the pretraining support. We develop a theoretical framework under mild assumptions that separates these two forms of distribution shift.…

arXiv → PDF
cs.CLcs.AI

Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods

Ponhvoan Srey, Jason Lucas, Pittawat Taveekitworachai, Junyoung Lee, Anh Tuan Luu

Large Language Models (LLMs) encode substantial factual knowledge. Yet, estimating confidence in factual claims reliably remains challenging. We study likelihood-based factual confidence from the complementary perspectives of discrimination and calibration across multilingual factual statements. Specifically, we instantiate contrastive generative likelihoods as Contrastive Factual Evidence (CFE), which compares the likelihood of the same claim under competing factual and non-factual conditions,…

arXiv → PDF
cs.SDcs.LG

Interpreting SSL Representations for Spoof Detection: a WavLM Study

Mohamed Mallat, Michele Panariello, Massimiliano Todisco, Nicholas Evans, Anthony Larcher

Self-supervised speech models such as WavLM achieve strong spoofing detection performance, yet which layers encode the most spoof-relevant information and what acoustic properties they capture remain opaque. We present a layer-wise interpretability study of WavLM using the ASVspoof 5 database, combining three complementary analyses: (i) per-layer linear probing with attack-level evaluation across speech synthesis, voice conversion, and adversarial attacks; (ii) a canonical correlation analysis (…

arXiv → PDF
cs.AI

Trapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language Models

Runtai Yang, Dandan Zhu, Kaiwei Zhang, Guangtao Zhai

Large language models (LLMs) are known to exhibit sycophancy by adjusting their responses toward users' expressed views. However, real users often justify their opinions through reasons, personal experiences, causal explanations, and broader narratives, raising the question of whether such narratives can further steer model judgments. We construct a controlled benchmark of 500 debatable questions across ten domains, where the user stance is held fixed while its justification is systematically va…

arXiv → PDF
cs.CL

Perceive, Solve, Reason: Progressive Capability Formation in Time Series-LLMs

Xin Qiu, Junlong Tong, Wei Zhang, Xiaoyu Shen

Large language models (LLMs) can now perceive, describe, and reason about images and audio, yet time series understanding remains underestimated: most work uses LLMs as forecasters and classifiers, reasoning studies are few and narrow, and no suite trains and evaluates the full range of capabilities. In this paper, we build the first such suite, with 337K training and 44K evaluation samples across three progressive capabilities, Perceive, Solve, and Reason, and use it to ask how time series shou…

arXiv → PDF
cs.LG

Uncertainty-aware AI-enabled framework for predicting hydrogen dispersion in confined spaces to enhance operator situational awareness

Niclas Flehmig, Mary Ann Lundteigen, Shen Yin

We present a two-stage AI-enabled framework for enhancing operator situational awareness during compressed hydrogen bunkering in maritime confined spaces. In the event of a leak, the framework first estimates the unknown leakage rate from early sensor readings and then forecasts how the hydrogen cloud will disperse over the next time steps, providing operators with a predicted concentration map together with confidence bounds. The framework is based on two independent AI models building one AI s…

arXiv → PDF
cs.AI

LocalIntent: Outcome-Specific Structured Generation for Backend-Compatible Smart Building Automation with Local LLMs

Tianyang Liu, Jiayue Wang, Zhanhao Cheng, Changyang Wang, Shaoshu Zhu, Zhenghao Wu, Hadi Tabatabaee Malazi

Locally deployed large language models (LLMs) can reduce reliance on remote cloud services for natural language smart building automation, but backend-facing processing requires correct outcome selection, alignment with local capabilities, and valid structured outputs. We investigate whether a complete outcome-specific prompting design improves compact-model outputs beyond generic route-then-generate prompting. The proposed LocalIntent approach routes requests to ordinary or persistent-rule bran…

arXiv → PDF
stat.MLcs.LG

Adaptive conformal prediction on the Grassmannian

Dimitrios Loukrezis, Zachary J. Grey, Dimitris G. Giovanis

We introduce a conformal prediction framework for regression with Grassmann-valued responses. The proposed method constructs prediction regions in the form of metric balls directly on the Grassmann manifold, using basis-invariant geometric distances as non-conformity measures and scaling the corresponding non-conformity scores through a learned prediction difficulty estimator. This yields locally adaptive, input-dependent prediction regions that respect the underlying manifold geometry, while re…

arXiv → PDF
cs.LGcs.AI

A Topological Signature of Learning under Noisy Labels

Zhongtian Sun, Fan Mo, Prayag Tiwari, Kelin Xia

How does noisy supervision change the representations learned by a neural network? Training accuracy measures agreement with training labels but provides little information about representation geometry. We use persistent homology to track loop structure across distance thresholds in neural activations. Experiments span image classification, text classification, and modular arithmetic. On a fixed CIFAR-10/ResNet-18 training probe, equally sized clean-label and corrupted-label subsets show no det…

arXiv → PDF
御社でもAIを使ってみませんか
まずはここから 御社でもAIを使ってみませんか？ 御社の実際の業務を題材に、AIで何ができるかを一緒に考えます。 「ChatGPTの使い方」を教えるだけの研修ではありません。 AI研修・AI活用相談 →
AI検索で自社がどう見えるか知りたい ChatGPTやPerplexityで自社が言及されるかを実際に測ります。 引用を約束するものではなく、まず現状を測るサービスです。 AI検索可視性診断 → Webサイトを改善したい 測った結果、サイト側に原因があった場合の改善まで対応します。 Web制作25年・1000案件の実績があります。 SEO・Webサイト改善 →