The study benchmarks tokenization choices for generative medical event models, evaluating quantization granularity, reference-range anchoring, code–value fusion, numeric and temporal encodings, and native versus harmonized event representations. Using Llama and Qwen architectures, 156 models were trained and assessed on early hospitalization data, showing that fusing codes with value deciles and using event-order or admission-relative RoPE embeddings improved predictive performance. The Common Longitudinal Intensive Care Unit Data Format (CLIF) reduced token count by 30.8% while enhancing outcomes in most families.
By Inhyeok Lee, Luke Solo, Michael C. Burkhart, Bashar Ramadan, Sahil Sethi, Sarah Jabbour, William F. Parker, Brett K. Beaulieu-Jones
The paper introduces a general machine learning framework called the localization method, built on localization kernels and local means that underpin self‑attention. It formally defines the framework through a local‑ized model and a localization trick, and systematically connects it to a wide array of existing models such as kernel methods, MeanShift, Hopfield networks, LLE, fuzzy inference, and denoising autoencoders. The authors also extend the framework with adaptive kernels, hierarchical local models, and non‑local models, showing that the Transformer can be constructed using hierarchical local models, thereby unifying and generalizing state‑of‑the‑art architectures.
By Congwei Song
arXiv:2609.12898v1 Announce Type: new
Abstract: Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized b...
By Xinqiang Yu, Zekun qi, Jiawei He, Wenyao Zhang, Xuchuan Chen, Guaocai Yao, Li Yi, Zhaoxiang Zhang, He Wang
The paper introduces MMD-FUSE, a two-sample test that remains effective on small datasets by fusing classical and quantum kernels. By combining the inductive biases of classical kernels with the expressive power of quantum kernels, the hybrid approach achieves higher test power, especially for small, high‑dimensional data. Experiments on synthetic and real clinical datasets confirm that the method consistently outperforms purely classical counterparts and adapts robustly to varied data characteristics.
By Yu Terada, Yugo Ogio, Ken Arai, Hiroyuki Tezuka, Yu Tanaka
The paper investigates whether retrieval-time signals add value to Adaptive Retrieval-Augmented Generation (RAG) routing when the query is already known. Experiments across document, audio, and video RAG compare routers that use only the query versus those that also incorporate retrieval signals, keeping all other factors constant. The results show that adding retrieval signals does not reliably improve routing decisions over a query-only baseline, suggesting that any routing benefit must be explicitly demonstrated rather than presumed.
By Qiaomu Li, Qiuyuan Zhang, Nong Ming
arXiv:2503.00612v2 Announce Type: replace-cross
Abstract: The basic problem of semantic compression is to minimize the length of a message while preserving its meaning. This differs from classical no...
By Tankut Can
MOSAIC is a training‑free framework that adapts Graph Retrieval‑Augmented Generation (GraphRAG) to each query by converting query‑specific evidence needs into a bounded policy over seed selection, traversal, stopping, and evidence selection. It keeps the corpus graph, indexes, scoring, grounding, and answer generation shared, while an LLM analyzer tailors the exploration strategy per query. On GraphRAG‑Bench, MOSAIC improves answer correctness by over 5 points on Medical and 4 points on Novel, achieves high evidence recall and context relevancy, and reduces path and evidence evaluations compared to fixed policies.
By EunKyeong Lee, Kyeong-Jin Oh, Jinwon Kim, Hye Woo Lee, Minsang Song, Hyeongjun Jang, Junyoung Youn
The paper introduces a method for measuring accent differences that balances interpretability and practicality. It proposes using articulatory representations obtained via articulatory inversion as an interpretable basis for accent comparison, while employing optimal transport to compare accents across any type of recording. This approach aims to overcome the limitations of traditional phonetic analyses and embedding‑based methods, which are either time‑consuming or non‑interpretable.
By Charles McGhee, Mark J. F. Gales, Kate M. Knill
The paper introduces Agent-Integrated Software (AIS), a pattern that embeds an intelligent agent within an existing application to address persistent coordination challenges. It defines Intent-Level Interaction Abstraction (IIA) as the task semantics for user inspection and control, and presents interaction contracts that constrain the relationship between AIS execution and IIA states. The authors provide a transition-system model, a compact disclosure contract, and conditional propositions to illustrate how local component validity is insufficient and how admission invariants can be separated from planning, concluding with a research agenda for making agent integration a maintainable software engineering discipline.
By Shengcheng Yu, Chunrong Fang, Zhenyu Chen
ActMap is a new white‑box representation that compresses the entire hidden‑state trajectory of a language model during generation into a fixed 12 × 32 × 128 tensor. This compact 96 KiB map can be captured with no overhead and is read by a lightweight Vision Transformer to estimate answer correctness in a fraction of a millisecond. In experiments on short‑answer QA, math, and summarization, ActMap outperforms sampling, token‑probability, attention, and embedding baselines and matches a larger ACT‑ViT detector while achieving lower calibration error on most test pairs.
By Jacopo Dardini (University of Bologna), Roberta Calegari (University of Bologna)
X-AuT is a progressive framework for compressing the audio encoder of speech large language models. It selects layer combinations via short behavioral probes and restores performance through representation alignment, cross‑scale distillation, scheduled student‑policy supervision, and LoRA finetuning, while keeping the language‑model backbone frozen. On ten Chinese–English benchmarks, reducing Qwen3‑ASR‑0.6B’s encoder from 18 to 16 layers lowers macro‑average error from 5.61% to 5.27%, and a 14‑layer model achieves 5.75% error with 20.7% fewer parameters.
By Haojun Zhang, Yi Zou, Min Chen, Qize Yu, Lianrui Fan, Xini Ding, Hao Li, Shuchang Zhou, Xianming Liu, Shiyu Huang
VeriSim is a configurable patient simulation framework that injects controllable noise across six clinically grounded communication dimensions while preserving patient medical records. It uses a verifier that extracts atomic claims from utterances and checks them against a UMLS‑grounded vector index built with BioLORD embeddings, relying on structured clinical metadata rather than surface‑text similarity. Stress‑testing seven open‑weight LLMs shows realistic noise reduces diagnostic accuracy by 15‑25 percentage points and lengthens conversations by 34‑55%, with smaller models degrading more than larger ones; expert ratings confirm VeriSim’s high truth, realism, clinical utility, and noise fidelity.
By Sina Mansouri, Mohit Marvania, Vibhavari Ashok Shihorkar, Han Ngoc Tran, Kazhal Shafiei, Mehrdad Fazli, Yikuan Li, Ziwei Zhu
The paper proposes a neurosymbolic defense architecture for AI-enhanced Security Operations Centers (AI‑SOCs) that protects against indirect prompt injection via log poisoning. It combines deterministic SIEM decoders as a pre‑filter with NeMo Guardrails for semantic validation, and adds a closed‑loop telemetry system for Human‑in‑the‑Loop visibility. Experimental results mapped to the MITRE ATLAS taxonomy show the approach effectively dismantles promptware kill chains and delivers a resilient, observable defense for next‑generation AI‑SOCs.
By Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros, Nikolaos Kekatos, Grigorios Tsoumakas, Georgios Koutidis
The paper introduces Warrant, a method that locates and controls the contributions of attention mechanisms to model metrics. Warrant exposes the item‑wise contribution path to the reported metric and applies query‑conditioned permission on that path. Experiments on multiple datasets show that Warrant improves primary metrics in most comparisons, reveals a weak correlation between attention and prediction utility, and demonstrates that learned permission can recover evidence ranking while suppressing distractors.
By Minwoo Yu, Young-guk Ha
The paper reviews how voice authentication has evolved from handcrafted acoustic features to deep learning speaker embeddings, expanding its use in finance, smart devices, and law enforcement. It surveys modern threats—including data poisoning, adversarial, deepfake, and adversarial spoofing attacks—tracing their development alongside technological advances. For each attack type, the authors summarize methods, datasets, performance, and limitations, and organize the literature using accepted taxonomies to highlight emerging risks and open challenges.
By Kamel Kamel, Keshav Sood, Hridoy Sankar Dutta, Sunil Aryal
The paper introduces Autopoietic Game Theory, a computational model where social interactions, replication mechanisms, and computational costs co-evolve within a substrate of randomly initialized Z80 machine code programs. By embedding a social dilemma directly into the physics of computation, the authors demonstrate that scarcity of resources can make defection self-limiting, leading to the emergence of self-replicating, cooperative strategies. Empirical results show evolved programs suppress stealing, and spatial assortment enhances structural complexity and task performance, while the framework can also incorporate exogenous pressures such as math tasks tied to computation budgets.
By Kunal Jha, Francesco Cicala, Blaise Ag\"uera y Arcas, Blake Aaron Richards, Natasha Jaques, Max Kleiman-Weiner, Eyvind Niklasson
The paper introduces a modular agentic-AI platform that transforms heterogeneous CMC process-development documents into a dual-layer knowledge graph. The base layer creates a lexical Document‑Section‑Chunk hierarchy, while the intelligence layer extracts ontology‑aligned entities and links cross‑document concepts, all anchored by provenance. LLM agents navigate these layers to answer queries, and a novel three‑tier evaluation protocol demonstrates high retrieval‑augmented generation performance on proprietary data from a Sanofi program.
By Reza Amirmoshiri, Faryad Sahneh, Yasser Jangjou
The paper revisits the continuous diffusion language model Plaid and introduces RePlaid, aligning its architecture with modern discrete diffusion models. RePlaid achieves a compute gap of only 20× compared to autoregressive models, surpasses Duo with fewer parameters, and outperforms MDLM in over‑trained settings. On OpenWebText, RePlaid sets a new state‑of‑the‑art continuous diffusion perplexity of 22.1 and demonstrates superior generation quality, while theoretical analysis links likelihood‑based training to linear cross‑entropy over time and structured embedding geometries.
By Zhihan Yang, Wei Guo, Shuibai Zhang, Subham Sekhar Sahoo, Yongxin Chen, Arash Vahdat, Morteza Mardani, John Thickstun
The paper introduces Prototype-Mediated Process Supervision (PMPS), a method that uses learnable reasoning prototypes to provide structural supervision for latent chain-of-thought embeddings, addressing representation collapse and uneven information distribution. PMPS aligns latent and explicit CoT embeddings in a shared prototype space via many-to-many soft assignment and employs a Progressive Sequential Alignment module to guide training from positional priors to adaptive matching. Experiments show PMPS reduces output token length to under 50% of explicit CoT on GSM8K-Aug and improves accuracy by 2.08% over SIM-CoT, even surpassing CoT-SFT on GPT-2 and achieving the highest accuracy among latent reasoning methods on larger models and harder tasks.
By Yiqi Li, Xu Chen, Chen Ju, Jiangchao Yao, Zhaoyang Li, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Yu Wang
The paper explores using a large language model (LLM) to generate background context for social media posts and tests four ways to integrate this context into a Sentence-BERT (SBERT) hate‑speech detection classifier. The methods include text concatenation, embedding concatenation, hierarchical transformer fusion, and LLM‑driven text enhancement. Experiments on the Latent Hatred dataset of implicitly hateful tweets and the MAMI dataset of misogynous memes show that adding generated context can raise F1 scores by up to 3 points in textual and 6 points in multimodal settings compared to a zero‑context baseline, with embedding concatenation yielding the best results.
By Joshua Wolfe Brook, Ilia Markov