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.LG

Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive Diagnosis

Arif Hassan Zidan, Yi Pan, Bowen Guo, Xiang Li, Yu Bao, Yingfeng Wang, Tianming Liu, Wei Zhang et al.

Q-matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires. Data-driven Q-matrix estimation remains challenging when assessments involve many correlated skills and when real response patterns depart from idealized generative assumptions. We introduce a novel quantum sparse autoencoder (QSAE) for Q-matrix estimation, which, to the best of our knowledge, is the first application of quantum machine learnin…

arXiv → PDF
cs.MMcs.AI

Can LLMs Design Video Coding Tools? A Case Study on Planar Mode

Yingwen Zhang, Meng Wang, Liqiang He, Shiqi Wang

This paper explores whether large language models (LLMs) can design video coding tools, a highly challenging task due to the intricate algorithmic coupling of tool modifications. In particular, we present an empirical case study on the Planar mode, a long-standing intra prediction tool in video coding standards. Our experiments operate within a generation-and-evaluation loop, with the LLM generating new Planar predictors, encoder trials evaluating their coding performance, and the LLM re-generat…

arXiv → PDF
cs.CL

Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall

Jacqueline He, Howard Yen, Shuyue Stella Li, Margaret Li, Hanqing Zeng, Yinglong Xia, Benyu Zhang, Zhuokai Zhao et al.

Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across training stages remains unclear. Through controlled experiments, we find that forward Kullback-Leibler (KL) distillation--the standard KD formulation--with post-trained teachers behaves fundamentally differently during mid-training, an intermediate phase of self-supervised learning on curated corpora. Surprisingly, while for…

arXiv → PDF
cs.CV

Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison

Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit

Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the reference view provides little information for reconstructing non-co-visible patches, implicitly yielding a monocular training signal in these regions. We introduce Gekko, which turns this limitation into a useful signal. The relative improvement of the cross-view reconstruction error over a masked-autoencoder error is a self-supervised proxy for co-vis…

arXiv → PDF
cs.CGcs.LG

Sierpiński--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation

Sebastien Tchitchek, Julien Tierny

This paper introduces the Sierpiński-Knopp (SK) Wasserstein distance, a fast metric between persistence diagrams. The SK-Wasserstein distance, denoted $d_{\mathrm{SK}}$, maps diagram points and their diagonal projections to the unit interval via the Sierpiński-Knopp space-filling curve on the upper diagonal triangle. The encoded point sets are then efficiently matched via one-dimensional optimal assignment, in \(O(N\log N)\) steps, yielding an explicit diagonal-aware point assignment between the…

arXiv → PDF
cs.AI

EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation

Qing Zhao, Haowei Li, Weijian Deng, Pengxu Wei, Liang Lin

Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in free-form text, leaving their beliefs implicit and difficult to test or revise. We introduce EvoSCM, which equips scientific agents with explicit structural causal models that evolve as new experimental evidence is collected. EvoSCM maintains a population of competing SCM hypotheses, each encoding a candidate causal explanation of the environment,…

arXiv → PDF
cs.DBcs.AIcs.PL

Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data

Gene Zhang

A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data. We argue the opposite for the workloads enterprises actually run. A columnar relational engine fronted by a graph query language matches or exceeds native graph engines on analytical graph queries, and - decisively - scales past the point where in-memory graph engines fail. We further argue that the node/edge property graph is not a more faithful mo…

arXiv → PDF
cs.AI

When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation

Peiying Zhu, Sidi Chang

Interactive simulations increasingly evaluate policies in markets populated by language-model agents. Their outputs can look economic---prices, profits, consumer surplus, and welfare---without instantiating the behavior named in the claim. We audit this risk in a multi-turn buyer--seller testbed for configurable hotel transactions. An initial implementation reported welfare gains from two marketplace guardrails of +87.4, +35.0, and +28.8 across a Qwen2.5 1.5B--14B ladder. It also gave guarded an…

arXiv → PDF
cs.CV

DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting

Qian Wang, Yu Wang, Weiqi Li, Xinhua Cheng, Xiandong Meng, Ronggang Wang, Jian Zhang

While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor reconstruction quality and artifacts in rendered novel views. Recent efforts attempt to utilize powerful diffusion priors, yet they typically process rendered and reference views concatenated along an additional dimension in a single network. These methods overlook an inherent nature that different views should maintain appearance similarity but…

arXiv → PDF
cs.CVcs.AI

TempCloze: Can Video-LLMs Identify the Missing Middle?

Wenqi Pei, Henry Hengyuan Zhao, Yilai Liu, Jiahao Meng, Han Chen, Ziyu Wang, Hongyang Du

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidates. TempCloze contains 1,521 carefully filtered videos from seven sources, mainly…

arXiv → PDF
physics.ao-phcs.CVstat.AP

A Sensor-Adaptive Incremental Learning Framework for Artifact Detection in Satellite Precipitation Data

Andres F. Monsalve, Hernan A. Moreno, Christian D. Kummerow

Historically, retrieving rainfall data from satellite imagery has been the domain of space agencies. However, in recent years, the development of cheaper, more compact satellites (SmallSats) capable of detecting rainfall proxies has led to a significant increase in private-sector initiatives for satellite launch and surface precipitation products. This rapid growth has yet to be matched by data validation efforts. Consequently, the need for a robust tool to detect anomalies in near-real-time dat…

arXiv → PDF
cs.CV

Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic Degradation

Lucas Cunha, Lucas Sotomaior, Lucas Gasperin, Beatriz Caldas, Eduardo Pianovski, Rayson Laroca

Face forgery detectors often achieve strong results on controlled benchmarks, but their reliability under realistic image degradations remains limited. This paper presents a standardized benchmark for face forgery detection using the Multi-Dimensional Face Forgery Image (MFFI) dataset and evaluates performance on both clean and degraded test partitions. We compare six model families, including convolutional networks, transformer-based models, and a frozen self-supervised DINOv3 backbone, across…

arXiv → PDF
cs.LGcs.AI

LatentPress: Context Compression Beyond Text and Vision

Zhengze Zhou, Hejian Sang

Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference. A small reader-matched writer compresses $4$-$16\times$ while training only an adapter (4.2M-26.…

arXiv → PDF
cs.LGcs.AI

Optimizing Byzantine Node Placement in Decentralized Federated Learning

Edoardo Gabrielli, Gabriele Tolomei

Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a communication graph, the placement of Byzantine nodes determines how malicious influence propagates through the network. We therefore treat Byzantine placement as an explicit adversarial decision and formulate the attacker's objective as selecting, under a fixed compromise…

arXiv → PDF
cs.LGcs.AIcs.NE

Rethinking Learnability in Offline Data-driven Optimization

Chao Qian, Chen-Guang Wang, Rong-Xi Tan, Ke Xue

Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization improves the efficiency of BBO algorithms by learning from data. Offline data-driven optimization seeks high-quality solutions using only a fixed set of previous evaluations, attracting substantial attention because it requires no additional online evaluations. Many offline optimi…

arXiv → PDF
cs.CLcs.AIcs.MA

GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions

Elias Stengel-Eskin, Newton Sander, Carlos Bonetti, Sasha Boguraev, James Bowler, Hale Sirin, Simon Kirby

The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implications for safety and monitorability as well as for linguistic accounts of LLMs. To address these questions, we introduce GlossoGen, a novel platform for studying multi-agent language evolution in complex scenarios. Within GlossoGen, we build the SaveVeyru scenario, which requires agents with partial information to communicate under pressure. We fin…

arXiv → PDF
cs.CRcs.AI

Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents

Xiaofang Yang, Ziqi Miao, Dianbo Sui, Jing Shao, Lijun Li

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense…

arXiv → PDF
cs.AI

Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

Haoyang Yan, Min-le Su, Hangfan Zhang, Zhanhao Li, Chen Zhang, Shao Zhang, Yang Chen, Lei Bai et al.

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across l…

arXiv → PDF
cs.CV

CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modeling

Xin Shen, Chengyou Jia, Keshuo Xing, Zifeng Zhu, Changliang Xia, Bowen Ping, Zhuohang Dang, Hangwei Qian et al.

Beyond semantic content, camera parameters play a pivotal role in dictating the geometric perspective and appearance of any given image. While recent image editing models excel at semantic and stylistic manipulation, they struggle with explicit camera parameter control. When handling large perspective shifts, instruction-driven models face a dilemma: they either suffer from structural tearing or generate conservative outputs that ignore geometric instructions. To address this, we introduce Camer…

arXiv → PDF
cs.CV

RadMatch: Auditable Radiology Report Evaluation via Finding-Level Matching

Charles Corbière, Léo Machado, Aubin Charley, Baptiste Callard, Pierre Manceron, Corentin Dancette

As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language model (LLM)-based metrics are now the best-correlated with radiologist judgment, yet they output a single opaque score that neither a clinician nor a model builder can easily interpret or audit. We introduce RadMatch, a multi-stage, LLM-based metric that decomposes report comparison into a structured finding-level matching with significance-aware…

arXiv → PDF
cs.AI

Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers

Egor Pakhomov, Erik Nijkamp

A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into. We present a live trace model, an append-only event ledger folded incrementally into typed run state and compiled into per-consumer views, and evaluate it for both consumers against deterministic ground truth. For the observer side, evaluated with an LLM reader as proxy, the compiled view answers monitoring questions u…

arXiv → PDF
cs.IRcs.CL

AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval

Tianyu Wang, Tianjiao Wu

Composed image retrieval (CIR) retrieves a target image from a reference image and a text modification. This paper studies metadata-available CIR reranking, where a fixed CIR model first returns a candidate pool and gallery metadata is then used for second-stage concept-guided scoring. We introduce AutoConcept, a training-free reranker that converts concept evidence into an interpretable memory. AutoConcept filters noisy concepts, activates query-relevant positive constraints with an auxiliary n…

arXiv → PDF
cs.CRcs.AI

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

Yitong Guo, Xiaoyi Chen, Siyuan Zhang, Xiaofeng Wang, Haixu Tang

Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior work often attributes this failure to gradient conflict, we propose a fundamentally different Fisher-geometric explanation: safety Fisher is low-rank, and alignment makes the safety geometry flatter while preserving an output-routing pathway. After 100 benign fine-tuning examples, this pathway is selectively re-sharpened in output-side MLP modules,…

arXiv → PDF
cs.ROcs.LG

Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds

Clinton Enwerem, John S. Baras, Calin Belta

Dexterous manipulation policies learned by imitation are typically evaluated for robustness to variation in scenes, objects, or instructions, but their performance across task execution speeds is less often examined. This leaves open how much temporal robustness a learner retains relative to the expert it imitates. We compare an expert and learner under the same task conditions, initial-condition draws, and speedup factors. We instantiate the evaluation in ParcelStow, a contact-rich task in whic…

arXiv → PDF
cs.LG

Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning

Mariia Drozdova, Aidan Sirbu, Pietro Miotti, Robert Obryk, Mayalen Etcheverry, Eyvind Niklasson, Blake Richards

Diffusion models and recursive reasoners are both iterative, but they carry information across iterations differently. We add a persistent hidden state to a diffusion denoiser and remove its timestep conditioning, leaving a single shared update that can be run to arbitrary depth. The result is an anytime solver: accuracy keeps improving with inference depth far beyond the rollout lengths and backpropagation window used in training, reaching 99.90% exact solve on Sudoku-Extreme. We also obtain 98…

arXiv → PDF
cs.LG

Edge-Girth as a Structural Edge Feature for Graph Neural Networks

Lilian Marey, Charlotte Laclau

Graph neural networks (GNN) based on message passing are provably no more powerful than the one-dimensional Weisfeiler--Leman colour-refinement test (1-WL): two graphs it cannot tell apart receive identical representations, however deep or wide the network. A common remedy augments node or edge features with precomputed structural descriptors, most often counts of a fixed small subgraph such as triangles or longer cycles, but such counts require committing in advance to the size of the substruct…

arXiv → PDF
cs.SEcs.CL

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Yuhao Wu, Jingyuan Zhang, Jiajun Shi, Xinping Lei, Qingshui Gu, Yuxuan Zhang, Zexuan Wang, Chen He et al.

As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly termed the agent harness. Changing this harness while holding model weights fixed can substantially alter task performance. Current agent evaluations typically report downstream performance under a chosen harness, leaving a model's ability to develop the harness itself comparatively underexplored. We introduce HarnessDev, a benchmark that shifts th…

arXiv → PDF
cs.CV

Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept Erasure

Qinghui Gong, Xunlei Chen, Yu-Xuan Zhang, Hua Meng, Zhengchun Zhou

Concept erasure aims to suppress unsafe, privacy-sensitive, or undesirable generations in text-to-image diffusion models while preserving benign semantics, visual quality, and deployment efficiency. Existing adapter-based methods, such as Low-Rank Adaptation (LoRA), typically freeze the diffusion backbone and learn lightweight parameter updates to steer generation away from target semantics. However, these methods usually assign a static semantic erasure direction to each target concept. This as…

arXiv → PDF
cs.DLcs.CLcs.CYcs.SI

Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation

Yixuan Liu, Lin Chen, Zhuoqi Liu, Jianglin Lu, Dakota Murray

Scientific citations carry rhetorical intent. Scholars may cite prior work positively (supporting), negatively (contrasting), or neutrally (mentioning). As large language models (LLMs) increasingly assist scientific writing, whether they reproduce citations with the same rhetorical intent as humans remains unclear. We introduce a masked-citation task to compare human and LLM-generated citation behavior. For each citation context, an LLM generates a replacement citation sentence, producing a coun…

arXiv → PDF
cs.LGcs.AI

Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search

Zhiliang Chen, Sebastian Ament, David Eriksson, Maximilian Balandat, Eytan Bakshy, Jihao Andreas Lin

Optimal hyperparameter scaling laws describe how the best hyperparameters for large language model (LLM) training change with model and data scale, enabling practitioners to predict optimal configurations at production scales without expensive large-scale tuning. However, estimating these scaling laws conventionally requires exhaustive grid searches over thousands of training runs, consuming enormous computational resources. We introduce Power-Law Entropy Search (PLES), a computational cost-awar…

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 →