Linearized string representations serve as the foundation of scalable autoregressive molecular generation; however, they introduce a fundamental modality mismatch where a single molecular graph maps to multiple distinct sequences. This ambiguity leads to \textit{trajectory divergence}, where the latent representations of structurally equivalent partial graphs drift apart due to differences in linearization history. To resolve this without abandoning the efficient string formulation, we propose Structure-Invariant Generative Molecular Alignment (SIGMA). Rather than altering the linear representation, SIGMA enables the model to strictly recognize geometric symmetries via a token-level contrastive objective, which explicitly aligns the latent states of prefixes that share identical suffixes. Furthermore, we introduce Isomorphic Beam Search (IsoBeam) to eliminate isomorphic redundancy during inference by dynamically pruning equivalent paths. Empirical evaluations on standard benchmarks demonstrate that SIGMA bridges the gap between sequence scalability and graph fidelity, yielding superior sample efficiency and structural diversity in multi-parameter optimization compared to strong baselines.
Evaluating large language models at scale remains a practical bottleneck for many organizations. While existing evaluation frameworks work well for thousands of examples, they struggle when datasets grow to hundreds of thousands or millions of samples. This scale is common when assessing model behavior across diverse domains or conducting comprehensive regression testing. We present Spark-LLM-Eval, a distributed evaluation framework built natively on Apache Spark. The system treats evaluation as a data-parallel problem, partitioningexamplesacrossexecutorsandaggregatingresultswithproperstatistical accounting. Beyond raw throughput, we emphasize statistical rigor: every reported metric includes bootstrap confidence intervals, and model comparisons come with appropriate significance tests (paired t-tests, McNemar's test, or Wilcoxon signed-rank, depending on the metric type). The framework also addresses the cost problem inherent in LLM evaluation through content-addressable response caching backed by Delta Lake, which allows iterating on metric definitions without re-running inference. We describe the system architecture, the statistical methodology, and report benchmark results showing linear scaling with cluster size. The framework and all evaluation code are available as open source.
Compared to theoretical frameworks that assume equal sensitivity to deviations in all features of data, the theory of anomaly detection allowing for variable sensitivity across features is less developed. To the best of our knowledge, this issue has not yet been addressed in the context of isolation-based methods, and this paper represents the first attempt to do so. This paper introduces an Extended Isolation Forest with feature sensitivities, which we refer to as the Anisotropic Isolation Forest (AIF). In contrast to the standard EIF, the AIF enables anomaly detection with controllable sensitivity to deviations in different features or directions in the feature space. The paper also introduces novel measures of directional sensitivity, which allow quantification of AIF's sensitivity in different directions in the feature space. These measures enable adjustment of the AIF's sensitivity to task-specific requirements. We demonstrate the performance of the algorithm by applying it to synthetic and real-world datasets. The results show that the AIF enables anomaly detection that focuses on directions in the feature space where deviations from typical behavior are more important.
Large language models are often described as capable of reflective reasoning, yet recursive self-evaluation without external feedback frequently yields reformulation rather than progress. We test this prediction in a cross-provider study of 144 reasoning sequences across three models (OpenAI GPT-4o-mini, Anthropic Claude 3 Haiku, and Google Gemini 2.0 Flash) and four task families (arithmetic, code, explanation, reflection), each iterated ten times under two conditions: ungrounded self-critique and a minimal grounding intervention (a single verification step at iteration three). Mean informational change (delta I, measured via normalized edit distance) declined by 55% from early (0.193) to late (0.087) iterations in ungrounded runs, with consistent patterns across all three providers. Grounded runs showed a +28% rebound in informational change immediately after the intervention and sustained non-zero variance thereafter. Complementary measures-n-gram novelty, embedding drift, and character-level entropy-converged on the same pattern: reflection without contact tends toward informational closure. We interpret this as evidence for a structural limit on self-correction in generative reasoning: without an exchange of information with an independent verifier or environment, recursive inference approaches an attractor state of epistemic stasis. Minimal grounding functions as dissipative coupling, reintroducing informational flux. The cross-architecture consistency suggests the mirror loop arises from shared autoregressive training objectives rather than provider-specific alignment schemes. The results delineate when reflection is performative rather than epistemic and motivate design principles for grounded, cooperative reasoning. Materials and code are publicly available.
Fine-tuning large language models (LLMs) with parameter-efficient techniques such as LoRA and QLoRA has enabled adaptation of foundation models on modest hardware. Yet the efficiency of such training on consumer-grade GPUs, especially under strict 8 GB VRAM limits, remains underexplored. We present a controlled profiling study of LoRA/QLoRA fine-tuning using the Qwen2.5-1.5B-Instruct model on a single NVIDIA RTX 4060. Across three representative configurations, we systematically vary batch size, sequence length, optimizer choice (AdamW vs. PagedAdamW), and precision (fp16 vs. bf16). We report throughput (tokens/s), time per 10k tokens, and VRAM footprint, alongside energy estimates derived from GPU board power limits. Our results show that paged optimizers improve throughput by up to 25% (628 tok/s vs. 500 tok/s baseline), while bf16 degrades efficiency relative to fp16. Despite 8 GB constraints, sequence lengths up to 2048 tokens were feasible using parameter-efficient strategies. To our knowledge, this is the first systematic case study of LLM fine- tuning efficiency on consumer GPUs, providing reproducible benchmarks and practical guidelines for resource-constrained researchers and practitioners.
Data driven and autoregressive indoor scene synthesis systems generate indoor scenes automatically by suggesting and then placing objects one at a time. Empirical observations show that current systems tend to produce incomplete next object location distributions. We introduce a system which addresses this problem. We design a Domain Specific Language (DSL) that specifies functional constraints. Programs from our language take as input a partial scene and object to place. Upon execution they predict possible object placements. We design a generative model which writes these programs automatically. Available 3D scene datasets do not contain programs to train on, so we build upon previous work in unsupervised program induction to introduce a new program bootstrapping algorithm. In order to quantify our empirical observations we introduce a new evaluation procedure which captures how well a system models per-object location distributions. We ask human annotators to label all the possible places an object can go in a scene and show that our system produces per-object location distributions more consistent with human annotators. Our system also generates indoor scenes of comparable quality to previous systems and while previous systems degrade in performance when training data is sparse, our system does not degrade to the same degree.
Accurate medium-range precipitation forecasting is crucial for hydrometeorological risk management and disaster mitigation, yet remains challenging for current numerical weather prediction (NWP) systems. Traditional ensemble systems such as the Global Ensemble Forecast System (GEFS) struggle to maintain high skill, especially for moderate and heavy rainfall at extended lead times. This study develops a deep learning-based ensemble framework for multi-step precipitation prediction through joint modeling of a comprehensive set of atmospheric variables. The model is trained on ERA5 reanalysis data at 0.25$^{\circ}$ spatial resolution, with precipitation labels from NASA's Integrated Multi-satellite Retrievals for Global Precipitation Measurement (GPM) constellation (IMERG), incorporating 57 input variables, including upper-air and surface predictors. The architecture employs a patch-based Swin Transformer backbone with periodic convolutions to handle longitudinal continuity and integrates time and noise embeddings through conditional layer normalization. A dual-branch decoder predicts total precipitation and other variables, with targeted freezing of encoder-decoder pathways for specialized training. Training minimizes a hybrid loss combining the Continuous Ranked Probability Score (CRPS) and weighted log1p mean squared error (log1pMSE), balancing probabilistic accuracy and magnitude fidelity. During inference, the model ingests real-time Global Forecast System (GFS) initial conditions to generate 15-day forecasts autoregressively. Evaluation against GEFS using IMERG data demonstrates higher Critical Success Index (CSI) scores at precipitation thresholds of 0.1 mm, 1 mm, 10 mm, and 20 mm, highlighting improved performance for moderate to heavy rainfall.
This project presents an AI-based system for tone replication in music production, focusing on predicting EQ parameter settings directly from audio features. Unlike traditional audio-to-audio methods, our approach outputs interpretable parameter values (e.g., EQ band gains) that musicians can further adjust in their workflow. Using a dataset of piano recordings with systematically varied EQ settings, we evaluate both regression and neural network models. The neural network achieves a mean squared error of 0.0216 on multi-band tasks. The system enables practical, flexible, and automated tone matching for music producers and lays the foundation for extensions to more complex audio effects.
This study presents a validation and extension of a recent methodological framework for medical image classification. While an improved ConvNeXt Tiny architecture, integrating Global Average and Max Pooling fusion (GAGM), lightweight channel attention (SEVector), and Feature Smoothing Loss (FSL), demonstrated promising results on Alzheimer MRI under CPU friendly conditions, our work investigates its transposability to mammography classification. Using a Kaggle dataset that consolidates INbreast, MIAS, and DDSM mammography collections, we compare a baseline CNN, ConvNeXt Tiny, and InceptionV3 backbones enriched with GAGM and SEVector modules. Results confirm the effectiveness of GAGM and SEVector in enhancing feature discriminability and reducing false negatives, particularly for malignant cases. In our experiments, however, the Feature Smoothing Loss did not yield measurable improvements under mammography classification conditions, suggesting that its effectiveness may depend on specific architectural and computational assumptions. Beyond validation, our contribution extends the original framework through multi metric evaluation (macro F1, per class recall variance, ROC/AUC), feature interpretability analysis (Grad CAM), and the development of an interactive dashboard for clinical exploration. As a perspective, we highlight the need to explore alternative approaches to improve intra class compactness and inter class separability, with the specific goal of enhancing the distinction between malignant and benign cases in mammography classification.
Integrating Large AI Models (LAMs) into 6G mobile networks is a key enabler of the AI-Native Air Interface (AI-AI), where protocol intelligence must scale beyond handcrafted logic. This paper presents, to our knowledge, the first standards-compliant emulation of the Radio Resource Control (RRC) layer using a decoder-only LAM (LLAMA-class) fine-tuned with Low-Rank Adaptation (LoRA) on a multi-vendor corpus of real-world traces spanning both 5G and 4G systems. We treat RRC as a domain-specific language and construct a segmentation-safe, question-answer (Question-and-Answer (QA)) dataset that preserves Abstract Syntax Notation (ASN.1) structure through linearization prior to Byte Pair Encoding (BPE) tokenization. The proposed approach combines parameter-efficient adaptation with schema-bounded prompting to ensure syntactic and procedural fidelity. Evaluation introduces a standards-aware triad -- ASN.1 conformance, field-level coverage analysis, and uplink-to-downlink state-machine checks -- alongside semantic similarity and latency profiling across 120 configurations. On 30k 5G request-response pairs plus an additional 4.8k QA turns from 4G sessions, our 8B model achieves a median cosine similarity of 0.97, a 61% relative gain over a zero-shot baseline, while sustaining high conformance rates. These results demonstrate that LAMs, when augmented with protocol-aware reasoning, can directly orchestrate control-plane procedures, laying the foundation for the future Artificial Intelligence (AI)-native Radio Access Network (RAN).
Citations are a key ingredient of scientific research to relate a paper to others published in the community. Recently, it has been noted that there is a citation age bias in the Natural Language Processing (NLP) community, one of the currently fastest growing AI subfields, in that the mean age of the bibliography of NLP papers has become ever younger in the last few years, leading to `citation amnesia' in which older knowledge is increasingly forgotten. In this work, we put such claims into perspective by analyzing the bibliography of $\sim$300k papers across 15 different scientific fields submitted to the popular preprint server Arxiv in the time period from 2013 to 2022. We find that all AI subfields (in particular: cs.AI, cs.CL, cs.CV, cs.LG) have similar trends of citation amnesia, in which the age of the bibliography has roughly halved in the last 10 years (from above 12 in 2013 to below 7 in 2022), on average. Rather than diagnosing this as a citation age bias in the NLP community, we believe this pattern is an artefact of the dynamics of these research fields, in which new knowledge is produced in ever shorter time intervals.
University students often spend a considerable amount of time seeking answers to common questions from administrators or teachers. This can become tedious for both parties, leading to a need for a solution. In response, this paper proposes a chatbot model that utilizes natural language processing and deep learning techniques to answer frequently asked questions (FAQs) in the Amharic language. Chatbots are computer programs that simulate human conversation through the use of artificial intelligence (AI), acting as a virtual assistant to handle questions and other tasks. The proposed chatbot program employs tokenization, normalization, stop word removal, and stemming to analyze and categorize Amharic input sentences. Three machine learning model algorithms were used to classify tokens and retrieve appropriate responses: Support Vector Machine (SVM), Multinomial Naïve Bayes, and deep neural networks implemented through TensorFlow, Keras, and NLTK. The deep learning model achieved the best results with 91.55% accuracy and a validation loss of 0.3548 using an Adam optimizer and SoftMax activation function. The chatbot model was integrated with Facebook Messenger and deployed on a Heroku server for 24-hour accessibility. The experimental results demonstrate that the chatbot framework achieved its objectives and effectively addressed challenges such as Amharic Fidel variation, morphological variation, and lexical gaps. Future research could explore the integration of Amharic WordNet to narrow the lexical gap and support more complex questions.
To raise awareness of the environmental impact of deep learning (DL), many studies estimate the energy use of DL systems. However, energy estimates during DL training often rely on unverified assumptions. This work addresses that gap by investigating how model architecture and training environment affect energy consumption. We train a variety of computer vision models and collect energy consumption and accuracy metrics to analyze their trade-offs across configurations. Our results show that selecting the right model-training environment combination can reduce training energy consumption by up to 80.68% with less than 2% loss in $F_1$ score. We find a significant interaction effect between model and training environment: energy efficiency improves when GPU computational power scales with model complexity. Moreover, we demonstrate that common estimation practices, such as using FLOPs or GPU TDP, fail to capture these dynamics and can lead to substantial errors. To address these shortcomings, we propose the Stable Training Epoch Projection (STEP) and the Pre-training Regression-based Estimation (PRE) methods. Across evaluations, our methods outperform existing tools by a factor of two or more in estimation accuracy.
We describe a method for approximating a single-variable function $f$ using persistence diagrams of sublevel sets of $f$ from height functions in different directions. We provide algorithms for the piecewise linear case and for the smooth case. Three directions suffice to locate all local maxima and minima of a piecewise linear continuous function from its collection of directional persistence diagrams, while five directions are needed in the case of smooth functions with non-degenerate critical points. Our approximation of functions by means of persistence diagrams is motivated by a study of importance attribution in machine learning, where one seeks to reduce the number of critical points of signal functions without a significant loss of information for a neural network classifier.
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and self-supervised learning of deep neural networks. We analyze the training dynamics of deep networks on training data that are corrupted by, e.g., random noise and adversarial examples. Our analysis shows that model predictions are able to magnify useful underlying information in data and this phenomenon occurs broadly even in the absence of any label information, highlighting that model predictions could substantially benefit the training processes: self-adaptive training improves the generalization of deep networks under noise and enhances the self-supervised representation learning. The analysis also sheds light on understanding deep learning, e.g., a potential explanation of the recently-discovered double-descent phenomenon in empirical risk minimization and the collapsing issue of the state-of-the-art self-supervised learning algorithms. Experiments on the CIFAR, STL, and ImageNet datasets verify the effectiveness of our approach in three applications: classification with label noise, selective classification, and linear evaluation. To facilitate future research, the code has been made publicly available at https://github.com/LayneH/self-adaptive-training.
We describe a strategy for identifying the universe of research publications relevant to the application and development of artificial intelligence. The approach leverages the arXiv corpus of scientific preprints, in which authors choose subject tags for their papers from a set defined by editors. We compose a functional definition of AI relevance by learning these subjects from paper metadata, and then inferring the arXiv-subject labels of papers in larger corpora: Clarivate Web of Science, Digital Science Dimensions, and Microsoft Academic Graph. This yields predictive classification $F_1$ scores between .75 and .86 for Natural Language Processing (cs.CL), Computer Vision (cs.CV), and Robotics (cs.RO). For a single model that learns these and four other AI-relevant subjects (cs.AI, cs.LG, stat.ML, and cs.MA), we see precision of .83 and recall of .85. We evaluate the out-of-domain performance of our classifiers against other sources of topic information and predictions from alternative methods. We find that a supervised solution can generalize to identify publications that belong to the high-level fields of study represented on arXiv. This offers a method for identifying AI-relevant publications that updates at the pace of research output, without reliance on subject-matter experts for query development or labeling.
We introduce two approaches for combining neural evolution strategy (NES) and proximal policy optimization (PPO): parameter transfer and parameter space noise. Parameter transfer is a PPO agent with parameters transferred from a NES agent. Parameter space noise is to directly add noise to the PPO agent`s parameters. We demonstrate that PPO could benefit from both methods through experimental comparison on discrete action environments as well as continuous control tasks
We analyze the performance of different sentiment classification models on syntactically complex inputs like A-but-B sentences. The first contribution of this analysis addresses reproducible research: to meaningfully compare different models, their accuracies must be averaged over far more random seeds than what has traditionally been reported. With proper averaging in place, we notice that the distillation model described in arXiv:1603.06318v4 [cs.LG], which incorporates explicit logic rules for sentiment classification, is ineffective. In contrast, using contextualized ELMo embeddings (arXiv:1802.05365v2 [cs.CL]) instead of logic rules yields significantly better performance. Additionally, we provide analysis and visualizations that demonstrate ELMo's ability to implicitly learn logic rules. Finally, a crowdsourced analysis reveals how ELMo outperforms baseline models even on sentences with ambiguous sentiment labels.
In this paper, we study the problem of determining a minimum state probabilistic finite state machine capable of generating statistically identical symbol sequences to samples provided. This problem is qualitatively similar to the classical Hidden Markov Model problem and has been studied from a practical point of view in several works beginning with the work presented in: Shalizi, C.R., Shalizi, K.L., Crutchfield, J.P. (2002) \textit{An algorithm for pattern discovery in time series.} Technical Report 02-10-060, Santa Fe Institute. arxiv.org/abs/cs.LG/0210025. We show that the underlying problem is $\mathrm{NP}$-hard and thus all existing polynomial time algorithms must be approximations on finite data sets. Using our $\mathrm{NP}$-hardness proof, we show how to construct a provably correct algorithm for constructing a minimum state probabilistic finite state machine given data and empirically study its running time.