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.AIcs.NE2026年10月16日

Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence

Jian Yao, Zhiyao Zhang, Yichen Li, Xingyu Wu, Kay Chen Tan

Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new paradigm that turns iterative algorithms into trainable models. Its central idea is to regard algorithm execution trajectories as computational experience: by learning how algorithmic states evolve over iterations, a model can internalize the knowledge embodied in existing algorithms, reproduce their computational behaviors, and fur…

arXiv → PDF

cs.LG2026年10月16日

Nearly Linear Private Learning of Littlestone Classes

Shay Moran, Chao Yan

Differentially private learning aims to learn from data while protecting individual training examples. For binary classification, finite Littlestone dimension characterizes approximate private PAC learnability (Alon et al., JACM 2022). Understanding how this dimension controls private sample complexity remains a central question. For classes of Littlestone dimension $d$, the first general upper bound was doubly exponential in $d$ (Bun, Livni, and Moran, FOCS 2020). Subsequent work improved this…

arXiv → PDF

cs.CL2026年10月16日

Cross-Centaur: Modeling Individual Decision-Making Across Psychological Tasks with Language Models

Hikaru Asano, Hidezo Suganuma, Ryutaro Mori, Yukino Baba

Large language models (LLMs) are increasingly used as computational models of human behavior. Recent models such as Centaur have advanced this goal by fine-tuning LLMs on trial-by-trial decisions from psychological experiments. However, existing large-scale behavioral datasets do not link the same participants across different tasks, so these models learn population-level regularities but are not trained to model individual-level regularities across tasks. We introduce Cross-Psych-101, a dataset…

arXiv → PDF

cs.AIcs.HC2026年10月16日

QuAD: Quantitative Assessment via Distribution-Alignment for Qualitative Data Quality Enabled by a Content-Aware Multi-Agent System

Wenshuo Zhang, Leixian Shen, Qiqi Zhou, Shuchang Xu, Feiyang Hao, Huamin Qu, Haobo Li, Zhao Chen et al.

Assessing whether qualitative responses collected from semi-structured questions are ready for a particular analysis goal is a persistent challenge. Manual qualitative analysis is interpretive and labor-intensive, while existing automated methods often lack a dataset-level perspective for deciding whether a response set supports a researcher-selected analytical lens. We introduce QuAD, a framework for quantitative pre-analysis assessment of qualitative response datasets. QuAD compares a reconstr…

arXiv → PDF

cs.AIcs.LG2026年10月16日

CIIR - Class-Indexed Interface Representation Learning

Doo Yon Kim, Christian Wallraven

Multimodal learning commonly assumes paired or synchronized observations, yet independently collected datasets rarely provide such correspondence. We introduce CIIR, a modular encoder--decoder framework that connects heterogeneous datasets through a class-indexed address space while preserving each dataset's native input format and output module. A known local index selects address $k$, and an input-dependent 128-dimensional address representation Z_k(x) is written to that address. To demonstrat…

arXiv → PDF

cs.CYcs.CLcs.HC2026年10月16日

Can AI interview? Comparing AI-led to Human-led Chat Interviews

Semra Guven, Tobias Gårdhus, Andreas Bjerre-Nielsen, Anna Rogers, Hjalmar Bang Carlsen

Large language model chatbots have been proposed as AI-interviewers for collecting qualitative interview data at scale, potentially bridging social science's longstanding divide between the breadth of surveys and the depth of qualitative interviews. This paper provides the first direct empirical comparison of data quality in AI-led and human-led interviews. In a randomized experiment (N = 41), university students were interviewed via synchronous text chat by either trained non-expert interviewer…

arXiv → PDF

cs.LG2026年10月16日

Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents

Qirui Liu, Hao Chen, Yi Wen, Weijie Shi, Yao Zhao, Xianhe Chen, Hao Zhao, Xing Tang et al.

Outcome-reward reinforcement learning such as GRPO gives every token of a search-agent rollout the same advantage, although the rollout exercises two capabilities: finding evidence and using it. We show that accuracy improves without grounding: Search-R1 raises accuracy on all seven QA benchmarks, yet on Bamboogle the evidence-supported share of correct answers falls from 84.0% to 42.9%. We attribute this to GRPO's credit assignment: rollouts that retrieve answer-bearing evidence are favoured in…

arXiv → PDF

cs.LGcs.AI2026年10月16日

Local proxies for memory-efficient training

Wu S. Zihan, Brian A. Yuan, Guillaume Bellec

Local learning algorithms can reshape resource requirements of artificial intelligence. The memory bottleneck of standard end-to-end backpropagation lies in the need to store all network activations until the loss gradient has been propagated back through. Local learning avoids this, but typically at a cost in accuracy. We study how to achieve accurate and memory efficient local learning in transformers. For each transformer block, we train a local proxy network to predict the global network out…

arXiv → PDF

cs.CVcs.CRcs.HC2026年10月16日

From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images

Zhiqing Guo, Lixin Jia, Luning Sun, Xiaowei Chen, Guofeng Yu, Liejun Wang, Gaobo Yang, David Stillwell et al.

Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal large language models (MLLMs). However, empirical research on human performance in detecting deepfake face images has not kept pace. It remains unclear if (and how) detection performance varies across generative models and whether model-specific training improves detection more effectively than general-purpose training. In this paper, we propose the \emph{Deepfake Face Artifact Ta…

arXiv → PDF

cs.AI2026年10月16日

LexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case Consultation

Wenbin Zhang, ShangZhan Li, Bingxiang He, Ye He, Yuxin Zhou, Muzhen Cai, Qi Shi, Wanxiang Che et al.

Large Language Models (LLMs) have greatly assisted legal professionals. However, our empirical studies reveal that, when faced with underspecified consultations from non-experts, current LLMs often produce irresponsible responses with limited utility despite lacking sufficient case details for definitive conclusions. To better assist laypeople, legal LLMs must identify focal points of dispute and proactively elicit crucial context from users. Unfortunately, existing data resources often focus on…

arXiv → PDF