The paper introduces proFILL, a method that transforms the existing rule-based advising chatbot hoBIT into a profile-aware retrieval-augmented generation system. Instead of needing a full student profile at the start, proFILL incrementally gathers only the attributes required for each query, using both the query intent and initially retrieved evidence to guide retrieval from a profile-aware index. Experiments and a human preference study demonstrate that proFILL outperforms various RAG baselines, is favored by users, and remains effective when deployed with open-weight models for cost-efficient on‑premise use.
By Yoonseo Kim, Seongmin Lee, Joongheon Kim, SeongKu Kang
The paper introduces a compositional graph embedding framework based on Aitchison geometry, where nodes are represented as simplex-valued mixtures over latent archetypal factors. By embedding these mixtures using isometric log-ratio coordinates, the method preserves Aitchison distances while allowing unconstrained optimization in Euclidean space, yielding intrinsically interpretable embeddings. The approach achieves competitive performance on node classification and link prediction tasks and enables principled component restriction through subcompositional coherence, allowing analysis of how archetype groups influence representations and predictions.
By Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos
The paper introduces Successive Capacity Growth (SCG), a method that starts with a minimal Vision Transformer encoder and incrementally expands its width or depth based on a task‑agnostic test‑and‑verify mechanism. SCG uses function‑preserving expansion and a Sketched Isotropic Gaussian Regularizer (SIGReg) to ensure independent semantic dimensions and prevent collapse. Experiments on multi‑object dynamics and 2D navigation tasks show that SCG achieves significant prediction loss reductions while being far more parameter‑efficient than fixed large models, with no false‑positive expansions and exact function preservation.
The paper explores how AI can develop its own aesthetic categorization of art across text, audio, image, and video without explicit labels. Using a self‑supervised framework, the authors embed these modalities into a shared 256‑dimensional space and iteratively cluster the data to uncover aesthetic structure. They compare the AI’s cluster assignments with human affective labels, highlighting divergences and discussing implications for cross‑modal similarity, media organization, and automated labeling.
GraphMemix introduces a combinatorial‑optimization graph memory framework that organizes long‑term multimodal agent memory as query‑aware evidence forests. It constructs candidate graphs by expanding seed memories through schema and semantic relations, then decouples evidence utility from anchor‑conditioned relation verification to reduce redundancy, and finally optimizes a forest‑format memory context within a maximum evidence budget. Experiments on four benchmarks show significant accuracy gains and a new Pareto frontier between accuracy and lifecycle cost.
The paper introduces a composite metric for quantizing small language models that balances information retention and throughput gains. By profiling Gemma 3 1B, it identifies Feed‑Forward Network blocks and the embedding matrix as key acceleration targets, estimating quality and speed scores without actual execution. The metric, validated across architectures with ~4% prediction error, enables predictable, resource‑efficient quantization compared to evolutionary or Shapley‑based methods.
We present TabuLM, the first language model pre-trained on Kinyarwanda tabular data. Kinyarwanda is a morphologically rich Bantu language spoken by over 12 million people in Rwanda, yet lacks any dedi...
The paper introduces SymbolLKG, a neuro-symbolic framework that combines a Logical Knowledge Graph (LKG) with dynamic solver routing to improve logical reasoning in large language models. The LKG represents logical rules and constraints as topological nodes, allowing explicit modeling of dependencies extracted from text. A Logic Router dispatches tasks to the most suitable symbolic engine, supported by a topology-aware hybrid retrieval mechanism, and the approach outperforms existing prompting and RAG baselines on logical reasoning benchmarks.
The paper introduces the Multi-Instruction Multi-Shot Long-Video Editing (MMLVE) task, aiming to edit long videos with multiple instructions while maintaining consistency across shots, decoupling instructions, and preserving spatiotemporal structure. It proposes an agentic editing framework that combines Large Language Models and Vision‑Language Models for shot-level decoupling and precise instruction parsing. A new dataset, MMLVE‑Bench, and three evaluation metrics are created to benchmark this task, and experiments show the proposed MMLVE‑Agent outperforms existing closed‑source state‑of‑the‑art methods by eliminating hallucinations and ensuring seamless transitions.
Data lakes rely on metadata to remain usable, yet this meta data is often limited or weakly informative for column relationship discovery, especially in ERP-derived datasets with coded or abbreviated...
The paper investigates whether placing class prototypes on a hyperbolic manifold (Poincaré ball) rather than a Euclidean space improves the satisfaction of a tree‑structured regularizer in hierarchical classification. Experiments on WikiArt show that hyperbolic prototypes better preserve nearest‑neighbor topology (higher sibling and cousin recall) across multiple tree definitions, while Euclidean prototypes perform similarly to logistic regression on raw features and only hyperbolic models improve local retrieval. The study provides empirical evidence that the choice of latent geometry can affect the fidelity of tree‑structured regularization in real data.
By Peter Flo, Luca Grossmann
The paper investigates whether retrieval‑augmented generation (RAG) can uniformly correct factual errors in large language models (LLMs) by testing six LLMs on a benchmark of about 2,000 public companies. In a controlled factual QA setting, the authors evaluate the models under four conditions—no‑context, perfect context, misleading context, and distraction context—across four atomic attributes. Results show significant geographic disparities in baseline accuracy, and while perfect context improves performance, it does not eliminate these gaps; misleading context often leads models to copy incorrect information, and larger models only marginally reduce structural biases.
By Abhinav Havaldar, Enrico Santus
The paper introduces a model‑agnostic open‑set detection framework for air‑to‑air visual object detection on UAVs, addressing the limitations of closed‑set detectors under domain shifts and flight data corruption. It estimates semantic uncertainty through entropy modeling in the embedding space and employs spectral normalization and temperature scaling to improve open‑set discrimination. Experiments on the AOT aerial benchmark and real‑world flight tests show up to a 10% relative AUROC improvement over standard YOLO detectors, with background rejection further enhancing robustness without sacrificing accuracy.
By Spyridon Loukovitis, Anastasios Arsenos, Vasileios Karampinis, Athanasios Voulodimos
MMEmb-R1 is a multimodal embedding framework that enhances reasoning by treating it as a latent variable and selecting beneficial reasoning paths through pair-aware selection and counterfactual intervention. It uses reinforcement learning to invoke reasoning only when necessary, reducing unnecessary computation and latency. On the MMEB-V2 benchmark, MMEmb-R1 achieves a state‑of‑the‑art score of 71.2 with just 4 B parameters.
By Yuchi Wang, Dingkang Yang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang, Chao Feng, Hongsheng Li
The paper reports a new phenomenon in CLIP embeddings where human and AI‑generated paintings naturally separate along dominant principal directions without any supervised training. The authors investigate this separation by linking embedding directions back to image features using interpretable representations and gradient‑based inversion, finding that the separation is driven by distributed multiscale image structure rather than simple global or local statistics. They also show that small, imperceptible image perturbations can cause large displacements along these directions, highlighting a mismatch between CLIP’s visual evidence and human perception.
By Andrea Asperti
The paper introduces a three‑layer security framework designed to protect retrieval‑augmented generation (RAG) chatbots from both direct and indirect prompt injection attacks. Layer 1 filters user input with rule‑based patterns and a semantic anomaly classifier; Layer 2 enforces a provenance‑based instruction hierarchy during context assembly; Layer 3 audits model output with a policy rule engine and semantic drift detector. Evaluations on GPT‑4o, Llama 3, and Mistral 7B demonstrate a reduction in attack success rate from 71.4 % to 11.3 %, outperforming existing single‑layer defenses while keeping false positives low and latency acceptable.
By Gulshan Saleem, Nisar Ahmed, Muhammad Imran Zaman, Ali Hassan, Umar Mujahid
The paper introduces RoMem, a temporal knowledge graph module that treats time as continuous phase rotation rather than discrete labels. RoMem uses a Semantic Speed Gate to assign volatility scores to relations, allowing evolving facts to rotate quickly while persistent facts remain stable, thereby preventing the need for deletion or costly LLM calls. The method achieves state‑of‑the‑art performance on ICEWS05‑15 and improves temporal reasoning in agentic memory benchmarks such as MultiTQ, LoCoMo, and FinTMMBench.
By Weixian Waylon Li, Jiaxin Zhang, Xianan Jim Yang, Tiejun Ma, Yiwen Guo
ReliableRAG is a new framework for Retrieval-Augmented Generation that tackles misinformation in multi‑hop question answering. It extracts structured triples from retrieved documents, evaluates each triple’s reliability by combining semantic relevance to the query with credibility, and keeps only the top‑K reliable, non‑redundant triples. Using these refined triples, the system builds robust reasoning chains that filter out deceptive misinformation and produce accurate, trustworthy answers.
By Jinpu Jiang, Xuan Wu, Wenhao Song, Bo Yang, You Zhou, Hongwei Ge, Heow Pueh Lee, Yanchun Liang, Chunguo Wu
arXiv:2602. 04795v3 Announce Type: replace Abstract: Nonnegative matrix factorization (NMF) is a popular data embedding technique.
By Olivier Vu Thanh, Nicolas Gillis
The paper introduces Hessian-free high-resolution (HFHR) dynamics, an extension of underdamped Langevin dynamics that incorporates reversible position diffusion for sampling in machine learning. It provides an explicit quantitative contraction rate under a position Poincaré inequality, weighted Hessian and Laplacian bounds, and a compact Sobolev embedding, even when the potential is non‑convex. For the HFHR Monte Carlo algorithm, a path‑space Girsanov argument yields a non‑asymptotic convergence bound and an explicit iteration complexity in total variation distance, improving on previous HFHR results and demonstrating benefits of a positive diffusion parameter through numerical experiments.
By Wujun Lv, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu