WIP: LLM Odyssey is an open‑source, browser‑based serious gaming platform that offers 13 interactive games to teach Large Language Model engineering concepts such as tokenization, transformer architecture, prompt engineering, RAG, and production deployment. The platform is organized into three learning tiers—Cognitive Core, Systems Forge, and Foundry Arena—aligned with Bloom’s revised taxonomy, and each game employs five pedagogical strategies including immediate feedback, scaffolded hints, progressive difficulty, worked examples, and authentic production scenarios. An initial deployment at a Canadian college in Winter 2026 confirmed functional requirements, highlighted the need for adaptive difficulty, and led to the design of a formal mixed‑methods evaluation protocol for future studies.
By Priyamvada Tripathi
MoRA is a human‑centric geospatial representation learning framework that uses a large mobility graph as its backbone to fuse spatial tokenization, graph neural networks, and asymmetric contrastive learning. It aligns over 100 million points of interest, massive remote sensing imagery, and structured demographic data with a billion‑edge mobility graph, producing compact 128‑dimensional embeddings that capture socio‑economic context and functional roles of locations. On a benchmark of nine downstream social and economic prediction tasks, MoRA outperforms state‑of‑the‑art models by an average of 12.9% and demonstrates scaling behavior analogous to large language models.
By Ya Wen, Jixuan Cai, Qiyao Ma, Linyan Li, Xinhua Chen, Chris Webster, Yulun Zhou
The paper argues that language operates with two parameters: amplitude, which measures how often words co‑occur, and phase, a signed relational factor that determines how co‑activated meanings combine and can reverse a meaning’s contribution. Unlike amplitude, phase is not captured by standard word embeddings or transformer attention weights and is indexed to individuals and dyadic interactions. The authors propose six empirical predictions to test phase’s role and suggest that future language models should incorporate agent‑indexed, phase‑bearing semantic states.
The paper explores using a small language model (SBERT) for invoice categorisation, a task that requires nuanced accounting judgement. By analysing the embedding geometry of SBERT and DeBERTa, the authors find that the sentence‑embedding space is globally anisotropic but contains locally isotropic clusters tied to vendor identity. Fine‑tuned SBERT achieves 0.96 accuracy and 0.9 F1 with only about 100 client‑specific invoices, outperforming zero‑shot LLMs and vendor baselines, and demonstrates that in‑house SLMs can reduce cost, enhance security, and improve interpretability.
The paper introduces a risk‑controlled framework for using large language models (LLMs) as judges in tasks without reference answers. By calibrating uncertainty thresholds on a held‑out set, the method ensures that the false discovery rate of accepted verdicts stays below a user‑specified level α with high probability, using finite‑sample Clopper–Pearson intervals. When the parametric judge lacks confidence, the instance is routed to a retrieval‑augmented mode with a second calibrated threshold, preserving the error guarantee while achieving higher coverage than single‑mode baselines.
Authorship verification (AV) assumes that an author's writing style remains sufficiently stable to distinguish it from that of other writers. In practice, however, this assumption is challenged by dis...
The paper investigates whether reader-specific differences in retrieval‑augmented generation (RAG) reflect reusable structure or merely input‑local interactions. By fixing query, evidence, task, scoring, and intervention, the authors find that nine readers disagree on the effect sign in 33% of cases, with reader×query interactions explaining 29.8% of utility variance. They further decompose heterogeneity into evidence activity, ordinal preference, and conditional signed direction, discovering that ordinal reader geometry is stable across multiple settings while signed geometry is task‑bounded, yet stable ordinal similarity does not predict cross‑reader intervention transfer.
Reflex-Guard is a lightweight, locally running guardrail for large language models that uses jailbreak-aware preprocessing, compact sentence‑transformer embeddings, and seven fast binary classifiers to filter unsafe prompts. It achieves 95.9% recall on harmful prompts with an end‑to‑end latency of 37.6 ms, far faster than existing solutions such as Llama Guard 2 (255 ms) and SafeDecoding (723 ms). The system can detect all GCG suffix attacks and Base64‑encoded prompts at the default threshold, and it attains a Reflex Efficiency Score up to 16.79, outperforming its competitors.
The paper introduces Action-Contrastive Masked Transition Modeling (AC‑MTM), a method that stabilizes Joint‑Embedding Predictive Architectures (JEPAs) without relying on Gaussian regularization. AC‑MTM adds a training‑only inverse‑dynamics head that uses Action‑NCE to force each latent transition to identify its generating action, thereby preventing encoder collapse. Experiments on pixel‑control and multi‑object visual tasks show that AC‑MTM trains stably from scratch and matches or surpasses the performance of SIGReg, achieving up to a 24‑point improvement on the OGBench Visual Scene benchmark.
BrainNorm is a normative foundation model trained on about 66,000 T1-weighted structural MRI scans. It uses language‑image style contrastive pretraining to create a Semantic Atlas Latent space (SAL), where each scan is encoded as atlas‑parcel embeddings that capture healthy aging trajectories. The model supports age‑consistent template matching, localized deviation scoring, and zero‑shot disease prediction, outperforming nine baselines across multiple downstream tasks and aligning its deviation patterns with known neurodegeneration pathology.
The paper introduces a spatio‑temporal traffic forecasting framework that fuses Graph Neural Networks with embeddings derived from a general‑purpose knowledge graph such as Wikidata. By creating semantic subgraphs around traffic sensors, the approach captures relationships like nearby points of interest, administrative hierarchies, and functional roles of locations, which are then integrated as additional adjacency matrices for the GNN. Experiments demonstrate that this external knowledge improves prediction accuracy beyond what street‑network data alone can achieve, while also offering a path toward better interpretability.
arXiv:2608. 15438v1 Announce Type: cross Abstract: Building approximate nearest neighbor (ANN) indexes at billion scale is often dominated by expensive global clustering or graph construction, making time-to-index a first-order systems concern.
By Xingqiao Wang, Zi Wang, Xiaowei Xu
OGX (Open GenAI Stack) is an open‑source AI application server and Python library that implements the APIs of major frontier labs such as OpenAI, Anthropic, and Google, allowing developers to build agentic AI applications against a single API surface. It supports a wide range of inference providers, vector store backends, and safety backends, and includes a Kubernetes Operator for production deployment. OGX is used as the self‑hosted, model‑agnostic backend for AI‑powered developer tools like Claude Code, Codex CLI, OpenCode, and OpenHands, and has garnered significant community engagement with over 8,400 GitHub stars, 242 contributors, and 4,000 commits.
By Francisco Javier Arceo, S\'ebastien Han, Matthew Farrellee, Charlie Doern, Yuan Tang, Derek Higgins, Varsha Prasad Narsing, Gordon Sim, Sumanth Kamenani, Ben Browning, Raghotham Murthy
arXiv:2608. 14666v1 Announce Type: new Abstract: Unsupervised fault detection in industrial systems is dominated by reconstruction based methods that monitor individual sensor marginal distributions.
By Dhiraj Neupane, Mohamed Reda Bouadjenek, Richard Dazeley, Sunil Aryal
arXiv:2608. 14697v1 Announce Type: new Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text.
By Andrew Rufail, Aadi Dash, Onir Narahari, Ethan Mui, Mahi Gajare, Prakhar Tiwari, Shrija Makapothula, Nick Cui
arXiv:2608. 15082v1 Announce Type: new Abstract: Cold chain logistics has advanced technologically, yet most deployed systems remain reactive monitors, not decision-making agents: thresholds trigger alerts, but nothing relates violations to cumulative product degradation or converts degradation signals into logistics decisions.
By Aashna Sofat, Balwinder Sodhi
arXiv:2608. 15165v1 Announce Type: new Abstract: Large language model (LLM) agents can continually improve without parameter updates by converting historical experience into reusable procedural knowledge.
By Yu He, Weikai Yang
arXiv:2608. 16621v1 Announce Type: new Abstract: Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time.
By Yusuke Takahashi, Kyle Wild, Asako Uraki
arXiv:2608. 16628v1 Announce Type: new Abstract: Modern Multimodal Retrieval-Augmented Generation (M-RAG) systems are fundamentally limited by the binary connectivity paradigm of traditional simple graphs, which fails to capture the intricate, high-order correlations among heterogeneous entities, such as the N-ary relationships between a visual chart, its scattered textual descriptions, and underlying numerical data.
By Shenao Chen, Yidan Xu, Xiangmin Han, Rundong Xue, Duanpo Wu, Yuhan Gao, Chenggang Yan, Yue Gao
arXiv:2608. 15424v1 Announce Type: cross Abstract: The rapid adoption of large language models has enabled the development of clinical multi-agent systems (MAS) capable of integrating multimodal patient data and supporting increasingly complex clinical decision-making.
By Rakesh Sharma, Sydney Pugh, Cameron Beeche, Pankhuri Singhal, Rachel Wu, Margaret Eby, Jeffrey Duda, James Gee, Kyra O'Brien, Hersh Sagreiya, Marina Serper, Victoria Gershuni, Angela Bradbury, Anurag Verma, Eric Eaton, Kevin B. Johnson, Walter Witschey