arXiv:2512.15209v1 Announce Type: cross Abstract: Coupling within-host infection dynamics with population-level transmission remains a major challenge in infectious disease modeling, especially for airborne pathogens with potential to spread indoor. The frequent emergence of such diseases highlight the need for integrated frameworks that capture both individual-level infection kinetics and between-host transmission. While analytical models for each […]
RFKG-CoT: Relation-Driven Adaptive Hop-count Selection and Few-Shot Path Guidance for Knowledge-Aware QA
arXiv:2512.15219v1 Announce Type: cross Abstract: Large language models (LLMs) often generate hallucinations in knowledge-intensive QA due to parametric knowledge limitations. While existing methods like KG-CoT improve reliability by integrating knowledge graph (KG) paths, they suffer from rigid hop-count selection (solely question-driven) and underutilization of reasoning paths (lack of guidance). To address this, we propose RFKG-CoT: […]
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
arXiv:2512.02826v2 Announce Type: replace-cross Abstract: Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memorization-generalization behavior remains poorly understood. In this work, we revisit the flow matching (FM) objective and study its marginal velocity field, which admits a closed-form expression, allowing exact computation of the […]
Yes-MT’s Submission to the Low-Resource Indic Language Translation Shared Task in WMT 2024
arXiv:2512.15226v1 Announce Type: cross Abstract: This paper presents the systems submitted by the Yes-MT team for the Low-Resource Indic Language Translation Shared Task at WMT 2024 (Pakray et al., 2024), focusing on translating between English and the Assamese, Mizo, Khasi, and Manipuri languages. The experiments explored various approaches, including fine-tuning pre-trained models like mT5 (Xue […]
Explaining the Reasoning of Large Language Models Using Attribution Graphs
arXiv:2512.15663v1 Announce Type: new Abstract: Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have proven effective for explaining the decision making of computer vision models. From these, context attributions have emerged as a promising approach for explaining the […]
Governing rapid technological change: Policy Delphi on the future of European AI governance
arXiv:2512.15196v1 Announce Type: cross Abstract: The rapid advancements in artificial intelligence (AI) present unique challenges for policymakers that seek to govern the technology. In this context, the Delphi method has become an established way to identify consensus and disagreement on emerging technological issues among experts in the field of futures studies and foresight. The aim […]
Artism: AI-Driven Dual-Engine System for Art Generation and Critique
arXiv:2512.15710v1 Announce Type: new Abstract: This paper proposes a dual-engine AI architectural method designed to address the complex problem of exploring potential trajectories in the evolution of art. We present two interconnected components: AIDA (an artificial artist social network) and the Ismism Machine, a system for critical analysis. The core innovation lies in leveraging deep […]
DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
arXiv:2510.12691v2 Announce Type: replace-cross Abstract: Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains challenging. In this work, we propose a new method for training diffusion models with Expectation-Maximization (EM) from corrupted data. Our proposed method, DiffEM, utilizes conditional diffusion […]
LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts
arXiv:2512.14706v1 Announce Type: cross Abstract: Neural architecture search (NAS) traditionally requires significant human expertise or automated trial-and-error to design deep learning models. We present NN-Caption, an LLM-guided neural architecture search pipeline that generates runnable image-captioning models by composing CNN encoders from LEMUR’s classification backbones with sequence decoders (LSTM/GRU/Transformer) under a strict Net API. Using DeepSeek-R1-0528-Qwen3-8B […]
DEER: Draft with Diffusion, Verify with Autoregressive Models
arXiv:2512.15176v1 Announce Type: cross Abstract: Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost through a draft-verify scheme, yet existing approaches rely on AR draft models (a.k.a., drafters), which introduce two fundamental issues: (1) step-wise uncertainty […]