Research Papers
arXiv · cs.AI, cs.LG, cs.CL · 50 papers
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Yaxin Luo, Haobin Jiang, Jialv Zou +11
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system. While an ideal harness system should align with human design priors
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Bobo Li, Hao Fei, Tianjie Ju +2
Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
Dairu Liu, Zekun Qi, Jiayu Zeng +11
Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors average per-frame pose differences but miss the physical artifacts that matter most, p
Defensive Boosting for Online Probabilistic Forecasting
Georgy Noarov, Aaron Roth
We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class $H$, we would like to efficiently obtain two incomparable guarantees that existing online boo
Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure
Mingyuan Zhang
The per-instance Jaccard score, or intersection over union (IoU), is standard in multi-label classification and binary segmentation. With $s$ labels, its loss matrix has $2^s$ outcomes and reports. Under the convention $\mathrm{Jac}(\varnothing,\varn
QuoteBench: How Matched Scores Can Hide Command-Path Failures
Shangao Li, Yao Zhang, Volker Tresp +1
LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures th
LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
Fanfei Li, Jana Zeller, Manuel Prada-Corral +4
Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LIT
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
Weihan Meng, Hongzhu Guo, Yi Jing +5
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferr
DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
Tianyi Li, Yaxin Luo, Xinyi Shang +1
Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency by predicting an entire token block in parallel, but their position-wi
Vero: Can AI Agents Build Formally Verified Software Repositories?
Zhe Ye, Hantao Lou, Yuechun Sun +8
AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offe
Exponential quantum advantage for learning signals with a single qubit
Ishaan Kannan, Sridhar Prabhu, Saeed A. Khan +7
Quantum technology has the potential to transform scientific discovery, but quantum advantages often require processing capabilities well beyond the reach of experimental platforms. We show that coupling a single controllable qubit to an otherwise co
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
Martin J. Wainwright
We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its local increments directly control Kullback--Leibler (KL) discretization
Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology
Yunsung Chung, Yingshuo Liu, Abboud F. Hassan +4
Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication ch
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
Peter Schneider-Kamp, Jacob Nielsen, Gianluca Barmina +2
Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced data. We introduce Mimir v1, a 1-billion-parameter language model based
Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining
Yuto Nishida, Hirokazu Kiyomaru, Yusuke Oda +6
Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validation sets representative of a model's general capabilities, and reliance on task performance at inter
Bagging Robustly Learns VC Classes with Linear Sample Complexity
Omar Montasser
We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample complexity linear in the VC dimension $d$, providing an exponential improvement over
TabSOM: A tabular-to-image encoding method based on self-organizing maps
David Chushig-Muzo, María Ángeles Rodríguez de Cara, Eva Milara +3
Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They convert tabular data into image representations, mapping each feature at a fixed pixe
On the Structural Limits of Machine Learning Decision Systems: An Information-Theoretic, Interaction-Based, and Stochastic-Dynamical Perspective
Nestor R. Barraza, Gabriel Pena
Machine learning procedures are commonly evaluated in terms of predictive accuracy and computational efficiency. However, their achievable performance is fundamentally constrained by structural properties of the underlying data-generating process, wh
Equivariant learning of a transferable three-dimensional classical density functional
Bingqing Cheng
Liquids exhibit collective behavior that depends sensitively on thermodynamic conditions, interfaces and confinement, yet predicting each new state commonly requires a separate atomistic simulation. Classical density functional theory offers a reusab
Intern-S2-Preview: Scientific Agentic Foundation Model
Lei Bai, Jiaqi Cao, Chiyu Chen +122
Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons. We present Intern-S2-Preview,
Sparse Orthogonal Regression Technique: A Spectral Framework for Equation Discovery, Approximation, and Integration
Sabin Roman, Ljupco Todorovski, Saso Dzeroski
We develop the Sparse Orthogonal Regression Technique (SORT), a sparse spectral framework for learning orthonormal-basis expansions from noisy and irregularly sampled data. SORT estimates expansion coefficients directly from observations using L1-reg
TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval
Yi-Chung Chen, Philip Jacobson, Tom Lampo +6
Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis. Structured and rule-based retrieval systems can explicitly target driving events, but typically require expert
AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
AlayaWorld Team, Kaipeng Zhang, Chuanhao Li +15
This report presents an improved version of AlayaWorld. While the backbone architecture, chunk-wise autoregressive generation scheme, and training data remain unchanged from the previous release, we substantially revise how conditioning signals are r
Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
Dananjay Srinivas, Saksham Khatwani, Maria Pacheco
When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We frame this failure through a Gricean lens: a cooperative speaker who is uncertai
Synthetic Persona Pretraining: Alignment from Token Zero
Julian Minder, Viktor Moskvoretskii, Raghav Singhal +12
As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant identity itself, are typically introduced only after pretraining, onc
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
Saisha Shetty, Satvik Tripathi, Austin Lin +6
We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration for clinical reasoning. MARC coordinates role-specialized agents for extraction, re
AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
Mohammed Ayman Habib, Rylan Hart, Morteza Fayazi
Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition. Among recent developments, LLMs have introduced a promising approach by bringing natural language r
Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
Yuchen Xin, Zhihua Zhang
We study the Moreau--Yosida unadjusted Langevin algorithm (MYULA) for the nonsmooth composite target \[ π(dx)\propto \exp\{-f(x)-g(x)\}\,dx, \qquad x\in\mathbb R^d, \] where \(f\) is \(m\)-strongly convex with \(L_f\)-Lipschitz gradient and \(g\) is
Concept Drift Detection and Adaptive Retraining of Malware Classification Models
Christofer Washington Berruz Chungata, Martin Jurecek, Katerina Potika +2
Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models for malware detection or classification are particularly susceptible to performa
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
Daniel Perkins, John Squires, Janou Milligan +2
Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty levels. We propose ARMDIL, an Adaptive Router for Multi-Domain Image classification with LLMs. ARMDI
Doubly Robust Estimation of Causal Effect on CVR with Targeted Regularization
Jiayi Dan, Bo Li, Lu Deng +1
Post-click conversion rate (CVR) is a key metric in various scenarios including e-commerce and advertising, reflecting the efficiency and user experience in the second stage of the conversion process. Estimating the causal effect on CVR is therefore
CAPRI: Contract-Aware Proof Repair for Isabelle
Jim Woodcock, Gabriel Leite, Augusto Sampaio +1
We address the use of large language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accepted, but not that an LLM changed only what the developer authorised. We present CAPRI, a contract-awa
Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion
Van Khoa Nguyen, Alexandros Kalousis
Generating crystals has recently attracted significant interest due to their broad applications in materials science. However, existing generative models struggle to produce complete crystallographic specifications, limiting their ability to capture
A Unifying Perspective on Causal World Models: From Observations to Representations to Structure
Avinash Kori, Fabrizio Russo
World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study WMs from a causal perspective across multiple levels of abstraction, ranging fr
UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
Yukun Dai, Mingzhe Dai, Tianshi Wang +3
Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks. However, their direct control over embodied agents also exposes them
LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles
Md Wasiul Haque, Sagar Dasgupta, Mizanur Rahman +1
Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking, or other control decisions. Static analysis can identify candidate sites, but dynamically confirming
Academic League of Artificial Intelligence - An Integrative Perspective of Teaching, Research, and Extension
Alison R. Panisson, Maria Eduarda W. M. Vianna, Italo Firmino da Silva +9
Academic leagues have become important mechanisms for promoting extracurricular education and strengthening the integration between universities and society. This paper presents the organizational framework adopted by the Academic League of Artificia
ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
Gehan Zheng, Matthew Johnson-Roberson, Weiming Zhi
Contact-rich manipulation failures are often detected only after the robot has committed to contact. This is especially limiting in wrist-camera setups: close gripper--object views help observe contact, but a poor approach may already push, miss, sli
Algebraic Decomposition Theory for Transformer Length Generalization
Andy Yang, Blerta Veseli, Corentin Barloy +5
Transformer-based language models are known to sometimes generalize to sequences longer than seen during training, but we lack a precise characterization of which tasks admit length generalization. It is not even known which regular languages transfo
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
Irina Proskurina, Mayank Kumar, Oyindolapo O. Komolafe
Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence. In question answering, verbalized model overconfidence may be associated with the
RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level
Juan Irving Vasquez, Juan Terven, Laura-Ivoone Garay-Jimenez
Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring, yet the available readiness frameworks are heterogeneous and difficult to apply automatically: the adapta
Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference
Zixuan Lan, Yanhong Li, Jiawei Zhou
Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose Reduced Matrix Multiplication (RMM), a training-free, input-adaptive inference metho
Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease Detection
Serli Kopar, Sam Gijsen, Abner Hernandez +2
Self-supervised learning (SSL) speech representations achieve strong performance for Parkinson's disease (PD) detection within individual corpora. However, it remains unclear whether these models capture disease-related characteristics or exploit dat
Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
Aimilios Hadjiliasi, Louis Nisiotis
Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse worlds. However, implementing cognitively capable agents in such environments is conceptually and tec
Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning
Yikai Xu, Zhao Chen, Jian Huang
Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution. To this end, we propose Wasserstein Filtering (WF), a novel sample selection framework that discards a fraction of s
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Yiwei Li, Wanli Yang, Hexiang Tan +10
Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation. To understand the current state of this capability, however, evaluation must go beyond final scores, which ne
Deliberate Practice: Learning Robot Skills under a Budget
Shivam Vats, Sudarshan Harithas, Mete Tuluhan Akbulut +2
We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learning algorithm, \emph{Deliberate Practice (DP)}, that computes a provably \emph{budget-optimal} allocat
Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
Mirko Tritella, Riccardo Pozzi, Matteo Palmonari
Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens, journalists, and researchers. Applying Retrieval-Augmented Generation (RAG) to parliam
Jointly Predicting Courses and Grades Using a Transformer-Based Model
Paul Savala
Existing predictive models in learning analytics often treat student academic history as a simple sequence, overlooking the concurrent nature of courses taken within a semester. This simplification can lead to inaccurate performance predictions, part
Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks
Muhammad Hannan Akram, Muhammad Abubakar Rashid, Wassi Haider Kabir +3
6G networks will not be serving as communication infrastructures only; rather, they are expected to evolve into intelligent systems, where thousands of autonomous artificial intelligence (AI) agents are interconnected. The agents are deployed across