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.AI

Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research

Gihan Panapitiya

Most retrieval-augmented systems treat literature search as a single retrieval step followed by summarization. Real literature research works differently: the investigator's understanding of the question changes as they read, new subquestions appear, and evidence is weighed, not just collected. We present Optimist Deep Research, an open-source agent that runs literature research as an iterative evidence-acquisition process over an explicit, mutable research state. A research question is broken i…

arXiv → PDF
physics.flu-dyncs.LG

How the elastic axis folds the transonic flutter boundary: shock energy transfer and conformally calibrated active learning

Ashray Saxena, Sharad Shrivastava

Isogai's case A, a pitch-plunge aerofoil whose elastic axis lies half a chord ahead of the leading edge, has a folded transonic flutter boundary in inviscid flow: near the bottom of the transonic dip several flutter speeds coexist at one Mach number. We map this boundary, and the family obtained by moving the elastic axis, with coupled unsteady Euler simulations, a Gaussian-process surrogate of the damping coefficient trained by batch active learning, and split conformal prediction on independen…

arXiv → PDF
cs.CVcs.AIeess.IV

FlashReFocus: Interactive Image Refocusing in Seconds

Ching-Heng Cheng, Chia-Ming Lee, Ming-Ching Chang, Xin Li, Yu-Lun Liu, Chih-Chung Hsu

Single-image refocusing changes the focal plane and depth of field of a photograph after capture. It is inherently interactive: users try many focal points and blur strengths on one image, so each edit should be fast and change only the blur. Recent generative methods, however, rerun large diffusion models for every edit. We observe that the two sub-problems differ in kind: recovering the all-in-focus image is ill-posed and needs a generative prior, whereas rendering blur is largely determined b…

arXiv → PDF
quant-phcs.LG

Learning angles for quantum approximate optimization

Johannes Jakubik, Isabelle Wittmann, Zaheed Gaffoor, Gciniwe Simphiwe Baloyi, Craig Mahlasi, Etienne Vos, Thomas Brunschwiler, Daniel J. Egger et al.

The Quantum Approximate Optimization Algorithm (QAOA) and its variants are leading algorithms to help solve challenging combinatorial optimization problems. QAOA maps these problems to Ising Hamiltonians such that their ground state is the desired solution. Candidate solutions are then drawn from a variational quantum circuit. The performance of QAOA hinges on a set of variational angles. However, finding good angles is an instance-specific and computationally expensive non-convex classical opti…

arXiv → PDF
cs.PFcs.CVcs.LG

The Optimal Ranking Tradeoffs Between Two Ranking Scores in Two-Class Classification

Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck

The accuracy, true negative rate (negative class recall), true positive rate (positive class recall), negative predictive value (negative class precision), positive predictive value (positive class precision), class-specific intersections over unions, class-specific F-scores, Cohen's kappa, and balanced accuracy are scores that one intuitively wants to maximize when developing machine learning methods. However, they lead to different rankings of such methods. So, how can we establish a ranking t…

arXiv → PDF
eess.SYcs.LGmath.OC

Distributed Performance Boosting through Neural Control for Plug-and-Play Networks

Danilo Saccani, Leonardo Massai, Giancarlo Ferrari-Trecate

We address the problem of improving the performance of pre-stabilized networked systems subject to plug-and-play (PnP) operations, namely additions or removals of subsystems. While distributed baseline controllers can preserve stability after a PnP transition, augmenting them with expressive neural policies can invalidate the formal stability guarantees. To overcome this issue, we build on recently proposed Performance Boosting controllers based on the Internal Model Control (IMC) principle, whi…

arXiv → PDF
cs.AI

CoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective

Qiyan Zhao, Xiaofeng Zhang, Xu-Yao Zhang, Shijie Han, Zhepeng Li, Shunzhi Zhu, Da-Han Wang

Diffusion-based multimodal large language models (dMLLMs) decode by iterative denoising with bidirectional attention, which precludes the standard autoregressive key--value cache. Practical deployments therefore rely on approximate caching that reuses intermediate states across denoising steps. Such caching, however, often makes a response repeat one token at adjacent positions in a run that breaks the sentence, a failure we term the \emph{Repeat Curse}. Tracing the context-token information flo…

arXiv → PDF
cs.LG

Data-Efficient Classifier Pretraining Through Diffusion Models

Qinyu Li, Yee Whye Teh, Chris Holmes, Joel Jaskari

Machine learning with limited data is susceptible to overfitting, especially with modern deep neural networks. Prior to the introduction of AlexNet, reconstruction-based pretraining with auto-encoder and denoising auto-encoder were found to be beneficial, partially due to the limited size of the training sets at the time. Motivated by these traditional approaches, we propose DiffPT, a simple diffusion modeling approach to pretrain a given classifier backbone for limited domain-specific training…

arXiv → PDF
cs.CV

I2V-DETACH: Source Grounding Detachment for Unauthorized Image-to-Video Generation

Chanhui Lee, Yeonghwan Song, Yewon Kang, Jeany Son

Recent diffusion models have advanced image-conditioned video generation, but their accessibility raises risks of unauthorized manipulation. Image immunization has emerged as a promising defense for Image-to-Video (I2V) protection, yet existing methods often rely on degrading visual quality or temporal coherence. In this work, we revisit I2V immunization as reducing source-content preservation, shifting the focus from output degradation to weakening source-conditioned content propagation. To thi…

arXiv → PDF
cs.AIcs.CLcs.HCcs.MA

Annotrace: A Workbench for Step-Level Annotation of Agent Traces

Arun Josephraj Arokiaraj, Chenyi Huang, Sahan Bulathwela, Zekun Wu, Bin Wu

Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool. Observability platforms record agent traces but offer no structured labelling; annotation tools label text but have no notion of a step, a delegation or a tool call, leaving it unclear what the smallest unit of execution to label should be. Annotrace reads six trace formats, including OpenTelemetry GenAI, LangSmith and Langfuse, and turns each run into an ordered, nested lis…

arXiv → PDF
cs.CV

Xiaomi-Lens-0 Technical Report

Pei Fu, Yike Liu, Yue Sun, Hanmo Wang, Xiuwen Xi, Ruoceng Zhang, Shaojie Zhang, Chao Jiang et al.

Multimodal large language models (MLLMs) answer questions about whole images well, yet they still struggle with fine-grained region understanding. A key reason is that text-only supervision never specifies which regions support an answer. To close this gap, we present Xiaomi-Lens-0, a 4B MLLM built on Qwen3.5 that predicts masks from its own visual representations. Specifically, a lightweight decoder combines vision-encoder patch features with visual latents, the language model's mask-token stat…

arXiv → PDF
cs.CL

Verbalising Model's Computation for Chain-of-Thought Faithfulness Detection

Yujing Wang, Yulan He, Wenya Wang, Hanqi Yan

Current Chain-of-Thought (CoT) verification methods detect reasoning faithfulness from model outputs or static activations, but are limited in explaining how unfaithfulness develops during generation. We introduce VERITAS to verbalise the model's computation: how different reasoning anchors emerge, transfer across layers, and surface in the output. VERITAS adopts the layer-wise Jacobian projection to produce a verbalised account of the model's internal reasoning evolution at each generated CoT t…

arXiv → PDF
cs.LG

DeDiCa: A Scalable Deconfounding Discrete Causal Generative Model

Kunchangtai Liang, Adrián Javaloy, Antonio Vergari, Isabel Valera

We introduce DeDiCa, a practical framework for efficient causal inference with discrete variables and hidden confounding that revisits classical probabilistic modeling through a tensorized parameterization of causal Bayesian networks, enabling tractable inference. Given a causal graph, DeDiCa is trained once on observational data by maximum likelihood, exactly marginalizing over hidden confounders, and can then estimate any (proxy-)identifiable interventional query. Despite this deliberately sim…

arXiv → PDF
cs.ROcs.LG

NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models

Guodong Du, Wanyu Lin

Vision--Language--Action (VLA) models promise generalist robotic agents, yet consolidating skills learned across heterogeneous tasks and environments remains difficult: training data is fragmented across platforms, joint multi-task training suffers from interference, and model merging tends to introduce parameter conflicts or require architectural changes. We instead advocate a paradigm in which skills are first learned independently and then consolidated post hoc. To this end, we propose Nested…

arXiv → PDF
cs.CV

Agentic Image Generation in the Wild

Yifan Li, Bowen Qin, Kun Zhou, Haochen Zhao, Zikang Liu, Zheng Li, Minsheng Hao, Yuhao Cheng et al.

Agentic image generation pairs an image generator with a search agent that retrieves references from the web, extending generation beyond the generator's training data. Real-world requests, however, often concern entities that appeared only days ago. We call this setting Image Generation in the Wild. In this setting, the web offers limited visual evidence, search results are crowded with easily confused entities, and the target is rarely shown on its own. To study this setting, we build an autom…

arXiv → PDF
cs.LGcs.AI

Beyond Marginal Influence: Interaction-Aware Memory Selection for LLM Agents

BHVSP Subrahmanyam, Neeraj Choudhary

LLM-agent memory selection often uses retrieval rankings based on record relevance or individual influence. Such rankings cannot identify sufficient subsets under redundant or jointly necessary evidence. We study per-decision memory sufficiency: selecting a small subset that preserves full-memory behavior. To separate search error from model error, we introduce JointCoreBench, a benchmark with nine interaction families, six workflow domains, natural-language decisions, and exact sufficient-set o…

arXiv → PDF
cs.LG

ADT: All-Atom Diffusion Tokenizer for 3D Molecular Structures

Xuantuo Huang, Encheng Su, Aoran Wang, Pan Tan, Shengyong Xu, Yizhou Wang, Chen Tang, Shixiang Tang et al.

Discrete structural tokenization provides a promising route to autoregressive 3D molecular generation. Yet, existing tokenizers face a trade-off between compact representation and all-atom reconstruction: atom-level tokens preserve atomic details but produce long sequences, while compact residue-level protein tokens typically omit side-chain geometry. To overcome this limitation, we propose All-atom Diffusion Tokenizer (ADT), which decouples token granularity from reconstruction resolution. ADT…

arXiv → PDF
cs.CV

SCALE: Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood Estimation

Jiwan Hur, Dong-Jae Lee, Dongyeun Lee, Gyojin Han, Junmo Kim

Classifier-free guidance (CFG) is essential for improving sample quality in visual generation, but it incurs substantial sampling overhead. Existing guidance-free approaches halve this cost by approximating the CFG with a single model inference, but their performance is bounded by the CFG and inherits its limitations. In this paper, we propose self-contrastive guidance (SCG), which contrasts the model's prediction on real and self-generated samples to obtain a direct, model-based signal that pus…

arXiv → PDF
cs.ROcs.CV

Expand-and-Prune: Test-Time Candidate-Space Adaptation for End-to-End Autonomous Driving

Fabian Schmidt, Karol Fedurko, Markus Enzweiler, Abhinav Valada

Candidate-based end-to-end driving planners reason over a finite set of trajectory hypotheses. However, for sparse planners, a limited candidate set may provide insufficient support for scene-relevant maneuvers, while fixed downstream candidate budgets do not account for prediction uncertainty. To address these challenges, we introduce Expand-and-Prune, a test-time framework that jointly adapts candidate support and capacity without updating learned parameters. The framework expands the native c…

arXiv → PDF
cs.AIcs.CLcs.LG

Reasoning Models Can Control Their Chains of Thought When They Tell Themselves To

Uriel Dolev, Idan Schwartz, Yoav Goldberg

Chain-of-thought (CoT) controllability, the ability of reasoning models to control properties of their CoT, is consequential for both their usefulness and reliable oversight. Recent work evaluates this capability by measuring whether models follow CoT constraints given in the user prompt, and reports very low controllability across models. We argue that this low controllability may not reflect an inherent inability of reasoning models to control their CoT, but instead result from naively specify…

arXiv → PDF
cs.AI

Beyond Reward Scoring: Online Multi-Agent Preference Learning for Multimodal Response Generation

Ziyun Zou, Jiwoo Hong, Yifan Lu, Shao Tang, Weiyi Wu, Aman Gupta, Jin Tian, Imran Razzak et al.

Multimodal preference alignment often follows a score-based RLHF pipeline: a reward model is first trained to learn human preferences, then used to score on-policy responses and optimize the response model's generation. This turns preference supervision into a scalar signal for generation: a model may learn to produce answers with higher preference scores, but is rarely trained explicitly to learn the reasons underlying human preferences. We therefore ask whether making preference understanding…

arXiv → PDF
cs.LGcs.CL

Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers

Srinivasan Iyengar

A common way to make language models and agents more accurate is to spend more compute at inference time: generate many candidate solutions and submit the one a verifier prefers. Success then requires that some candidate is correct and that the verifier picks it. The first grows predictably with the number of samples; the second does not, because real verifiers (unit tests, majority votes, LLM judges, reward models) accept wrong answers, reject right ones, and make correlated mistakes. With a fi…

arXiv → PDF
cs.CLcs.CR

Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents

Farhan Zarif, Kazi Shahid Ahmed Galib, Synthia Akter Promi, Shabnam Sharmin Tarin, Ariyan Hossain, Sadif Ahmed, Farig Yousuf Sadeque

Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI security by the attack success rate (ASR), which treats every failed attack as a successful defense. To test this assumption, we audit 33,000 trajectories from eleven open-weight agents (2-14B parameters) on InjecAgent and AgentDojo. A label-blind LLM judge shows that most failed attacks are ignored (76-80%) rath…

arXiv → PDF
cs.LG

FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations

BHVSP Subrahmanyam, Neeraj Choudhary

Restoring service after distribution-grid faults requires decisions from incomplete and conflicting information while respecting electrical constraints. Addressing this need, we introduce FLARE (Feeder-Level Agent Restoration Evaluation), a physics-grounded benchmark for post-isolation feeder restoration. FLARE con- tains 800 AC-feasible cases across five observation settings and allows agents to gather evidence, evaluate switches, and perform restoration actions under fixed operational limits.…

arXiv → PDF
cs.CV

LonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian Reconstruction

Zhoufeng Xie, Guanjun Wu, Shuai Zhang, Xinggang Wang, Wenyu Liu

Reconstructing high-quality, renderable 3D scenes from long videos is essential for robotic perception and embodied intelligence. Many feed-forward Gaussian reconstruction methods rapidly predict 3D scenes from a small set of images, but extending them to longer sequences presents two bottlenecks: jointly processing all views increases GPU memory requirements, while accumulating pixel-aligned predictions redundantly represents the same surfaces and increases storage and rendering costs. We prese…

arXiv → PDF
cs.CL

Who Pays for Efficient Inference? Confidence-Based Small-to-Large LLM Routing Across Tasks and Languages

Md Sabbir Hossen, Anichur Rahman, Pabon Shaha, Airin Afroj Aishi, Andrew H. Sung, Md Shohel Rana

Small-to-large language model routing can reduce inference cost by escalating difficult inputs while retaining easier ones on a smaller model. Its success, however, depends on identifying examples that benefit from escalation, and the reliability of confidence across multilingual tasks remains unclear. We present a systematic evaluation of confidence-based routing across three model families, four languages, and three task types, covering 72 model, dataset, language, and scale configurations and…

arXiv → PDF
cs.CVcs.LG

Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD

Yibo Zhou, Yirong Xiang

Relational out-of-distribution errors are easy to describe and hard to evaluate cleanly. An image may be natural, a caption may be fluent, and all mentioned objects may be common, yet the caption may describe the wrong relation in the image. Many evaluations intended to test this behavior can be solved without checking the pairing at all, because negatives differ in caption style, template, length, object frequency, or image statistics. We propose counterfactual pairing cycles, a blocked evaluat…

arXiv → PDF
cs.CLcs.LG

Think More or Read More? A Token-Budget Theory of Reasoning with Shared Context

Manh Nguyen, Sunil Gupta, Hung Le

Reasoning systems increasingly improve answers by incorporating additional context into the model's input, from multi-agent debate, where agents read their peers' responses, to self-refinement, where a model revisits its own drafts. In these systems, communication consumes context as one agent's output becomes another's input. We study the regime where token reading and generation draw on one fixed token window, so every token spent reading is a token that cannot be spent reasoning. We develop a…

arXiv → PDF
cs.CLcs.AI

MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning

Jihao Huang, Guangjia Chai, Zhirui Chen, Lei Wang, Yao Liu, Liu Qi, Pengjie Ding, Xinyang Liu et al.

GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered on four-quadrant (4Q) advantage shaping that combines verified correctness with rollout generation entropy. Correctness determines the sign of an additional correction, while entropy controls its magnitude: lower-entropy successes receive larger bonuses and higher-entropy failures receive larger penalties. An online entropy-bas…

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 →