The paper introduces DSRec, a dual‑interest sequential recommendation model that separates item representations into long‑term and short‑term semantic contexts. Long‑term embeddings capture stable preferences through historical aggregation, while short‑term embeddings focus on local session intent modulated by inter‑click time intervals. Each branch is processed by a distinct State Space Model— a full‑sequence Mamba for long‑term modeling and a time‑modulated SSM for short‑term dynamics— and a residual cross‑fusion mechanism aligns the two granularities while preserving their independence. Experiments on public benchmarks show that DSRec outperforms state‑of‑the‑art methods.
By Shuiying Liao, P. Y. Mok
The paper introduces Beacon, a course‑specific Retrieval‑Augmented Generation (RAG) system that offers private, module‑aligned academic support to students. By grounding responses in approved teaching materials, Beacon aims to lower barriers to help‑seeking and encourage independent learning, especially in computing education where tasks are cumulative and demanding. Evaluation through questionnaires and interviews showed students found Beacon’s responses trustworthy and closely aligned with course content, viewing it as a useful first point of support before consulting lecturers or official resources.
By Andy Gray, Jake Hobbs
AutoRecLab is a Python-based autonomous laboratory for recommender‑system research that transforms natural‑language prompts into executable experiments. It automatically derives experiment requirements, builds and validates prototypes, and iteratively expands them into full studies using retrieval‑augmented generation, static type verification, and execution‑steered tree search. In a demonstration, AutoRecLab autonomously conducted an explicit‑to‑implicit feedback conversion study, achieving 8 of 9 successful runs at an average cost of about $1 per run with GPT‑5.4‑mini.
By Moritz Baumgart, Philipp Meister, Justus Krell, Michael Schmidt, Bela Gipp, Joeran Beel
arXiv:2609. 21362v1 Announce Type: new Abstract: Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and often requiring large vocabularies.
By Nghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le, Phu Gia Hoang, Dat Tien Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
Rhamba is a region‑aware pretraining framework for resting‑state fMRI that combines anatomically guided masking with hybrid Attention‑Mamba architectures. The study pretrained models on the ABIDE dataset using three masking strategies (Any, Majority, Pure) and evaluated four architectural variants, finding that the Mamba‑Attention (MA) hybrid achieved the best average AUROC on downstream schizophrenia and ADHD classification tasks. Explainable AI via Integrated Gradients highlighted that performance depends on the interaction between masking strategy and architecture rather than a single dominant configuration.
By Pankaj Pandey, Ruthwik Reddy Doodipala, Pratheek Eranki, Carolina Torres-Rojas, Manob Jyoti Saikia, Ranganatha Sitaram
The paper introduces a training‑free proactive defense for detecting partial deepfake speech by using self‑embedding steganography. It embeds a compressed version of the clean audio within itself, allowing post‑hoc extraction of reference content and enabling detection of spoofed segments via codec‑based restoration. Experiments on a benchmark dataset show that this method complements passive detectors and operates without any training, offering a robust, data‑efficient alternative for partial deepfake detection.
By Yigitcan \"Ozer, Zhe Zhang, Wanying Ge, Xin Wang, Junichi Yamagishi
MIRCID is a framework that enhances drug mechanism-of-action modeling by integrating inferred microRNA (miRNA) activity with gene expression data. It identifies 414 pan‑cancer hub miRNAs (HubmiRs) from L1000 landmark genes, achieving high correlation with actual miRNA measurements and outperforming existing methods in full‑miRNA prediction tasks. The approach consistently improves pathway classification and MoA retrieval, with miRNA augmentation yielding more reliable gains than transcription factor activity alone.
By Xin Cao, Yigang Chen, Jiatong Xu, Ziyue Zhang, Xiang Cheng, Shenyu Wang, Yangyi Zhang, Xiaoxuan Cai, Shidong Cui, Zihao Zhu, Xiang Ji, Hsi-Yuan Huang, Yang-Chi-Dung Lin, Hsien-Da Huang
arXiv:2609.21789v1 Announce Type: new
Abstract: Most multilingual dysarthria-severity systems either train on a single aetiology-language pair or pool heterogeneous aetiologies into one label space....
By Bernard Muller, Antonio Armando Ortiz Barra\~n\'on, LaVonne Roberts
Fact Grounded Attention (FGA) is a new architectural change that injects verifiable knowledge directly into the transformer’s pre‑softmax attention scores, turning large language models into deterministic truth‑tellers. By modifying the attention mechanism itself, FGA prevents hallucinations for facts that exist in its knowledge base, unlike prior methods that patch output or prepend retrieved text. Experiments on 1,107 technical queries show accuracy rising from 6.3% with vanilla Llama 3.2 to 99.7% with FGA, and knowledge updates can be applied in under one second without retraining.
By Aayush Gupta, Manish Choudhary
The paper extends the analysis of Joint-Embedding Predictive Architectures (JEPAs) beyond Euclidean latent spaces to Riemannian manifolds. It shows that when latent variables lie on a sphere and the target distribution matches this spherical geometry, every optimal representation recovers the latent state up to an orthogonal transformation, demonstrating that Gaussian uniqueness is not universal. Experiments confirm that geometrically compatible targets improve linear recovery, especially in high-dimensional toroidal settings.
By L\'eo Nicollier (CB, ATT), Enric Meinhardt-Llopis (CB), Marc Pic (ATT), Pablo Mus\'e (CB, IFUMI), Gabriele Facciolo (CB)
arXiv:2609.21573v1 Announce Type: cross
Abstract: Retrieval-Augmented Generation (RAG) improves large language models by grounding outputs in external knowledge sources, but this dependency also crea...
By Pedro Pereira, Eva Maia, Isabel Pra\c{c}a
arXiv:2603.16086v2 Announce Type: replace-cross
Abstract: While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts...
By Chang Nie, Tianchen Deng, Guangming Wang, Zhe Liu, Hesheng Wang
arXiv:2609.21457v1 Announce Type: new
Abstract: Deep neural architectures are widely used for signal processing in automated pain assessment systems. However, architecture design has remained largely...
By Heinke Hihn, Friedhelm Schwenker
arXiv:2609.21281v1 Announce Type: cross
Abstract: Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, exp...
By Hao Fu, Jichao Sun, Baiting Zhu, Qiaoling Liu, Yan Shi, Cheng Lu, Liu Liu, Yubo Wang, Xin Yao, Xiangyu Niu, Xu Dong, Wenhan Lyu, Chiyao Shen, Yinjie Huang, Minglei Chen, Shuai Ding, Li Fan, Xiao Kong
arXiv:2601.11719v4 Announce Type: replace
Abstract: Self-supervised learning, in the context of foundation model training, is a powerful pre-training method for learning feature representations witho...
By Ho Fung Tsoi, Dylan Rankin
arXiv:2609.20849v1 Announce Type: new
Abstract: Large Audio Language Models (LALMs) perform well on complex question answering but often show a reasoning gap, where explicit Chain-of-Thought (CoT) re...
By Francesco Bonzi, Pooneh Mousavi, Cem Subakan, Mirco Ravanelli
arXiv:2505.10202v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...
By Jintian Shao, Hongyi Huang, Jiayi Wu, YiMing Cheng, ZhiYu Wu, You Shan, MingKai Zheng
arXiv:2609.21018v1 Announce Type: new
Abstract: Recent visual document retrieval (VDR) systems such as ColPali use multi-vector page embeddings, in which patch-level vectors enable fine-grained evide...
By Xu Yuan, Hua Liu, Wenqi Fan, Qing Li
arXiv:2609.21844v1 Announce Type: new
Abstract: Long transcripts are costly inputs for downstream NLP systems and often contain irrelevant context. We study query-conditioned topic localization: pred...
By Steffen Freisinger, Philipp Seeberger, Thomas Ranzenberger, Tobias Bocklet, Korbinian Riedhammer
arXiv:2609.21058v1 Announce Type: cross
Abstract: Language models can now write GPU kernels that outperform PyTorch. We evaluate five model configurations on KernelBench level 1 and find that a front...
By Gaurav Agarwal, Ashish Garg, Isha Singhal