# Research Papers — 2026-02 · bundle page 89 of 210 > Full-text markdown of papers #4401–4450 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/89 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/88.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/90.md) ### Named Entity Recognition for Payment Data Using NLP Authors: Srikumar Nayak Published: 2026-02-15 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.14009v1 Named Entity Recognition (NER) has emerged as a critical component in automating financial transaction processing, particularly in extracting structured information from unstructured payment data. This paper presents a comprehensive analysis of state-of-the-art NER algorithms specifically designed for payment data extraction, including Conditional Random Fields (CRF), Bidirectional Long Short-Term Memory with CRF (BiLSTM-CRF), and transformer-based models such as BERT and FinBERT. We conduct extensive experiments on a dataset of 50,000 annotated payment transactions across multiple payment formats including SWIFT MT103, ISO 20022, and domestic payment systems. Our experimental results demonstrate that fine-tuned BERT models achieve an F1-score of 94.2% for entity extraction, outperforming traditional CRF-based approaches by 12.8 percentage points. Furthermore, we introduce PaymentBERT, a novel hybrid architecture combining domain-specific financial embeddings with contextual representations, achieving state-of-the-art performance with 95.7% F1-score while maintaining real-time processing capabilities. We provide detailed analysis of cross-format generalization, ablation studies, and deployment considerations. This research provides practical insights for financial institutions implementing automated sanctions screening, anti-money laundering (AML) compliance, and payment processing systems. --- ### Prompt-Driven Low-Altitude Edge Intelligence: Modular Agents and Generative Reasoning Authors: Jiahao You, Ziye Jia, Chao Dong, Qihui Wu Published: 2026-02-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14003v1 The large artificial intelligence models (LAMs) show strong capabilities in perception, reasoning, and multi-modal understanding, and can enable advanced capabilities in low-altitude edge intelligence. However, the deployment of LAMs at the edge remains constrained by some fundamental limitations. First, tasks are rigidly tied to specific models, limiting the flexibility. Besides, the computational and memory demands of full-scale LAMs exceed the capacity of most edge devices. Moreover, the current inference pipelines are typically static, making it difficult to respond to real-time changes of tasks. To address these challenges, we propose a prompt-to-agent edge cognition framework (P2AECF), enabling the flexible, efficient, and adaptive edge intelligence. Specifically, P2AECF transforms high-level semantic prompts into executable reasoning workflows through three key mechanisms. First, the prompt-defined cognition parses task intent into abstract and model-agnostic representations. Second, the agent-based modular execution instantiates these tasks using lightweight and reusable cognitive agents dynamically selected based on current resource conditions. Third, the diffusion-controlled inference planning adaptively constructs and refines execution strategies by incorporating runtime feedback and system context. In addition, we illustrate the framework through a representative low-altitude intelligent network use case, showing its ability to deliver adaptive, modular, and scalable edge intelligence for real-time low-altitude aerial collaborations. --- ### The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective Authors: Ali Zahedzadeh, Behnam Bahrak Published: 2026-02-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.14002v1 Large Language Models increasingly rely on self-explanations, such as chain of thought reasoning, to improve performance on multi step question answering. While these explanations enhance accuracy, they are often verbose and costly to generate, raising the question of how much explanation is truly necessary. In this paper, we examine the trade-off between sufficiency, defined as the ability of an explanation to justify the correct answer, and conciseness, defined as the reduction in explanation length. Building on the information bottleneck principle, we conceptualize explanations as compressed representations that retain only the information essential for producing correct answers.To operationalize this view, we introduce an evaluation pipeline that constrains explanation length and assesses sufficiency using multiple language models on the ARC Challenge dataset. To broaden the scope, we conduct experiments in both English, using the original dataset, and Persian, as a resource-limited language through translation. Our experiments show that more concise explanations often remain sufficient, preserving accuracy while substantially reducing explanation length, whereas excessive compression leads to performance degradation. --- ### Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization Authors: Guandong Li, Mengxia Ye Published: 2026-02-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13994v1 Personalized text-to-image generation aims to integrate specific identities into arbitrary contexts. However, existing tuning-free methods typically employ Spatially Uniform Visual Injection, causing identity features to contaminate non-facial regions (e.g., backgrounds and lighting) and degrading text adherence. To address this without expensive fine-tuning, we propose SpatialID, a training-free spatially-adaptive identity modulation framework. SpatialID fundamentally decouples identity injection into face-relevant and context-free regions using a Spatial Mask Extractor derived from cross-attention responses. Furthermore, we introduce a Temporal-Spatial Scheduling strategy that dynamically adjusts spatial constraints - transitioning from Gaussian priors to attention-based masks and adaptive relaxation - to align with the diffusion generation dynamics. Extensive experiments on IBench demonstrate that SpatialID achieves state-of-the-art performance in text adherence (CLIP-T: 0.281), visual consistency (CLIP-I: 0.827), and image quality (IQ: 0.523), significantly eliminating background contamination while maintaining robust identity preservation. --- ### Elastic Diffusion Transformer Authors: Jiangshan Wang, Zeqiang Lai, Jiarui Chen, Jiayi Guo, Hang Guo, Xiu Li, Xiangyu Yue, Chunchao Guo Published: 2026-02-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13993v1 Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and distillation, typically rely on a fixed computational capacity, leading to insufficient acceleration and degraded generation quality. To address this limitation, we propose \textbf{Elastic Diffusion Transformer (E-DiT)}, an adaptive acceleration framework for DiT that effectively improves efficiency while maintaining generation quality. Specifically, we observe that the generative process of DiT exhibits substantial sparsity (i.e., some computations can be skipped with minimal impact on quality), and this sparsity varies significantly across samples. Motivated by this observation, E-DiT equips each DiT block with a lightweight router that dynamically identifies sample-dependent sparsity from the input latent. Each router adaptively determines whether the corresponding block can be skipped. If the block is not skipped, the router then predicts the optimal MLP width reduction ratio within the block. During inference, we further introduce a block-level feature caching mechanism that leverages router predictions to eliminate redundant computations in a training-free manner. Extensive experiments across 2D image (Qwen-Image and FLUX) and 3D asset (Hunyuan3D-3.0) demonstrate the effectiveness of E-DiT, achieving up to $\sim$2$\times$ speedup with negligible loss in generation quality. Code will be available at https://github.com/wangjiangshan0725/Elastic-DiT. --- ### Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms Authors: Belona Sonna, Alban Grastien Published: 2026-02-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13985v2 Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of human experts. A key challenge, however, is that AI reasoning frequently diverges from structured clinical frameworks, limiting trust, interpretability, and adoption. Critical symptoms, pivotal for rapid and accurate decision-making, may be overlooked by AI models even when predictions are correct. Existing post hoc explanation methods provide limited transparency and lack formal guarantees. To address this, we leverage formal abductive explanations, which offer consistent, guaranteed reasoning over minimal sufficient feature sets. This enables a clear understanding of AI decision-making and allows alignment with clinical reasoning. Our approach preserves predictive accuracy while providing clinically actionable insights, establishing a robust framework for trustworthy AI in medical diagnosis. --- ### Cognitive Chunking for Soft Prompts: Accelerating Compressor Learning via Block-wise Causal Masking Authors: Guojie Liu, Yiqi Wang, Yanfeng Yang, Wenqi Fan, Songlei Jian, Jianfeng Zhang, Jie Yu Published: 2026-02-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13980v1 Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows quadratically with sequence length. To mitigate this issue, context compression-particularly soft prompt compressio-has emerged as a widely studied solution, which converts long contexts into shorter memory embeddings via a trained compressor. Existing methods typically compress the entire context indiscriminately into a set of memory tokens, requiring the compressor to capture global dependencies and necessitating extensive pre-training data to learn effective patterns. Inspired by the chunking mechanism in human working memory and empirical observations of the spatial specialization of memory embeddings relative to original tokens, we propose Parallelized Iterative Compression (PIC). By simply modifying the Transformer's attention mask, PIC explicitly restricts the receptive field of memory tokens to sequential local chunks, thereby lowering the difficulty of compressor training. Experiments across multiple downstream tasks demonstrate that PIC consistently outperforms competitive baselines, with superiority being particularly pronounced in high compression scenarios (e.g., achieving relative improvements of 29.8\% in F1 score and 40.7\% in EM score on QA tasks at the $64\times$ compression ratio). Furthermore, PIC significantly expedites the training process. Specifically, when training the 16$\times$ compressor, it surpasses the peak performance of the competitive baseline while effectively reducing the training time by approximately 40\%. --- ### Chain-of-Thought Reasoning with Large Language Models for Clinical Alzheimer's Disease Assessment and Diagnosis Authors: Tongze Zhang, Jun-En Ding, Melik Ozolcer, Fang-Ming Hung, Albert Chih-Chieh Yang, Feng Liu, Yi-Rou Ji, Sang Won Bae Published: 2026-02-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.13979v1 Alzheimer's disease (AD) has become a prevalent neurodegenerative disease worldwide. Traditional diagnosis still relies heavily on medical imaging and clinical assessment by physicians, which is often time-consuming and resource-intensive in terms of both human expertise and healthcare resources. In recent years, large language models (LLMs) have been increasingly applied to the medical field using electronic health records (EHRs), yet their application in Alzheimer's disease assessment remains limited, particularly given that AD involves complex multifactorial etiologies that are difficult to observe directly through imaging modalities. In this work, we propose leveraging LLMs to perform Chain-of-Thought (CoT) reasoning on patients' clinical EHRs. Unlike direct fine-tuning of LLMs on EHR data for AD classification, our approach utilizes LLM-generated CoT reasoning paths to provide the model with explicit diagnostic rationale for AD assessment, followed by structured CoT-based predictions. This pipeline not only enhances the model's ability to diagnose intrinsically complex factors but also improves the interpretability of the prediction process across different stages of AD progression. Experimental results demonstrate that the proposed CoT-based diagnostic framework significantly enhances stability and diagnostic performance across multiple CDR grading tasks, achieving up to a 15% improvement in F1 score compared to the zero-shot baseline method. --- ### WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL Authors: Zhennan Jiang, Shangqing Zhou, Yutong Jiang, Zefang Huang, Mingjie Wei, Yuhui Chen, Tianxing Zhou, Zhen Guo, Hao Lin, Quanlu Zhang, Yu Wang, Haoran Li et al. Published: 2026-02-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.13977v2 Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots. Recent work attempts to use learned world models as simulators for policy optimization, yet closed-loop imagined rollouts inevitably suffer from hallucination and long-horizon error accumulation. Such errors not only degrade visual fidelity, but also mislead policy optimization by providing unreliable learning signals. We propose WoVR, a reliable world-model-based RL framework for post-training VLA policies. Instead of assuming a faithful world model, WoVR explicitly regulates how RL interacts with imperfect imagined dynamics. It improves rollout stability through a controllable action-conditioned video world model, reshapes imagined interaction to reduce effective error depth via Keyframe-Initialized Rollouts, and maintains policy--simulator alignment through World Model-Policy co-evolution. Extensive experiments demonstrate that WoVR enables stable long-horizon imagined rollouts and effective policy optimization, achieving superior LIBERO performance and consistent real-world gains across multiple robotic platforms. These results show that world models can serve as practical simulators for RL when hallucination is explicitly controlled. Additional visualization results are available at https://wovr-corl.github.io. --- ### DAIAN: Deep Adaptive Intent-Aware Network for CTR Prediction in Trigger-Induced Recommendation Authors: Zhihao Lv, Longtao Zhang, Ailong He, Shuzhi Cao, Shuguang Han, Jufeng Chen Published: 2026-02-15 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.13971v1 Recommendation systems are essential for personalizing e-commerce shopping experiences. Among these, Trigger-Induced Recommendation (TIR) has emerged as a key scenario, which utilizes a trigger item (explicitly represents a user's instantaneous interest), enabling precise, real-time recommendations. Although several trigger-based techniques have been proposed, most of them struggle to address the intent myopia issue, that is, a recommendation system overemphasizes the role of trigger items and narrowly focuses on suggesting commodities that are highly relevant to trigger items. Meanwhile, existing methods rely on collaborative behavior patterns between trigger and recommended items to identify the user's preferences, yet the sparsity of ID-based interaction restricts their effectiveness. To this end, we propose the Deep Adaptive Intent-Aware Network (DAIAN) that dynamically adapts to users' intent preferences. In general, we first extract the users' personalized intent representations by analyzing the correlation between a user's click and the trigger item, and accordingly retrieve the user's related historical behaviors to mine the user's diverse intent. Besides, sparse collaborative behaviors constrain the performance in capturing items associated with user intent. Hence, we reinforce similarity by leveraging a hybrid enhancer with ID and semantic information, followed by adaptive selection based on varying intents. Experimental results on public datasets and our industrial e-commerce datasets demonstrate the effectiveness of DAIAN. --- ### Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMs Authors: Ruicheng Zhang, Xinyi Li, Tianyi Xu, Shuhao Zhang, Xiaofei Liao, Hai Jin Published: 2026-02-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13967v1 Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state. In practice, memory is streaming: new facts arrive continuously, insertions interleave with retrievals, and the memory state evolves while the model is serving queries. In this regime, accuracy and cost are governed by the full memory lifecycle, which encompasses the ingestion, maintenance, retrieval, and integration of information into generation. We present Neuromem, a scalable testbed that benchmarks External Memory Modules under an interleaved insertion-and-retrieval protocol and decomposes its lifecycle into five dimensions including memory data structure, normalization strategy, consolidation policy, query formulation strategy, and context integration mechanism. Using three representative datasets LOCOMO, LONGMEMEVAL, and MEMORYAGENTBENCH, Neuromem evaluates interchangeable variants within a shared serving stack, reporting token-level F1 and insertion/retrieval latency. Overall, we observe that performance typically degrades as memory grows across rounds, and time-related queries remain the most challenging category. The memory data structure largely determines the attainable quality frontier, while aggressive compression and generative integration mechanisms mostly shift cost between insertion and retrieval with limited accuracy gain. --- ### HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam Authors: Weiqi Zhai, Zhihai Wang, Jinghang Wang, Boyu Yang, Xiaogang Li, Xander Xu, Bohan Wang, Peng Wang, Xingzhe Wu, Anfeng Li, Qiyuan Feng, Yuhao Zhou et al. Published: 2026-02-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.13964v4 Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions. However, community-led analyses have raised concerns that HLE contains a non-trivial number of noisy items, which can bias evaluation results and distort cross-model comparisons. To address this challenge, we introduce HLE-Verified, a verified and revised version of HLE with a transparent verification protocol and fine-grained error taxonomy. Our construction follows a two-stage validation-and-repair workflow resulting in a certified benchmark. In Stage I, each item undergoes binary validation of the problem and final answer through domain-expert review and model-based cross-checks, yielding 668 verified items. In Stage II, flawed but fixable items are revised under strict constraints preserving the original evaluation intent, through dual independent expert repairs, model-assisted auditing, and final adjudication, resulting in 1,143 revised-and-certified items. The remaining 689 items are released as a documented uncertain set with explicit uncertainty sources and expertise tags for future refinement. We evaluate eight state-of-the-art language models on HLE and HLE-Verified, observing an average absolute accuracy gain of 7--10 percentage points on HLE-Verified. The improvement is particularly pronounced on items where the original problem statement and/or reference answer is erroneous, with gains of 30--40 percentage points. Our analyses further reveal a strong association between model confidence and the presence of errors in the problem statement or reference answer, supporting the effectiveness of our revisions. Overall, HLE-Verified improves HLE-style evaluations by reducing annotation noise and enabling more faithful measurement of model capabilities. Data is available at: https://huggingface.co/datasets/skylenage/HLE-Verified --- ### HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam Authors: Weiqi Zhai, Zhihai Wang, Jinghang Wang, Boyu Yang, Xiaogang Li, Xander Xu, Bohan Wang, Peng Wang, Xingzhe Wu, Anfeng Li, Qiyuan Feng, Yuhao Zhou et al. Published: 2026-02-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.13964v3 Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions. However, community-led analyses have raised concerns that HLE contains a non-trivial number of noisy items, which can bias evaluation results and distort cross-model comparisons. To address this challenge, we introduce HLE-Verified, a verified and revised version of HLE with a transparent verification protocol and fine-grained error taxonomy. Our construction follows a two-stage validation-and-repair workflow resulting in a certified benchmark. In Stage I, each item undergoes binary validation of the problem and final answer through domain-expert review and model-based cross-checks, yielding 668 verified items. In Stage II, flawed but fixable items are revised under strict constraints preserving the original evaluation intent, through dual independent expert repairs, model-assisted auditing, and final adjudication, resulting in 1,143 revised-and-certified items. The remaining 689 items are released as a documented uncertain set with explicit uncertainty sources and expertise tags for future refinement. We evaluate eight state-of-the-art language models on HLE and HLE-Verified, observing an average absolute accuracy gain of 7--10 percentage points on HLE-Verified. The improvement is particularly pronounced on items where the original problem statement and/or reference answer is erroneous, with gains of 30--40 percentage points. Our analyses further reveal a strong association between model confidence and the presence of errors in the problem statement or reference answer, supporting the effectiveness of our revisions. Overall, HLE-Verified improves HLE-style evaluations by reducing annotation noise and enabling more faithful measurement of model capabilities. Data is available at: https://huggingface.co/datasets/skylenage/HLE-Verified --- ### MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars Authors: Shuoyuan Wang, Yiran Wang, Hongxin Wei Published: 2026-02-15 Categories: cs.CV, astro-ph.IM, cs.CL arXiv: https://arxiv.org/abs/2602.13961v1 Data-driven approaches like deep learning are rapidly advancing planetary science, particularly in Mars exploration. Despite recent progress, most existing benchmarks remain confined to closed-set supervised visual tasks and do not support text-guided retrieval for geospatial discovery. We introduce MarsRetrieval, a retrieval benchmark for evaluating vision-language models for Martian geospatial discovery. MarsRetrieval includes three tasks: (1) paired image-text retrieval, (2) landform retrieval, and (3) global geo-localization, covering multiple spatial scales and diverse geomorphic origins. We propose a unified retrieval-centric protocol to benchmark multimodal embedding architectures, including contrastive dual-tower encoders and generative vision-language models. Our evaluation shows MarsRetrieval is challenging: even strong foundation models often fail to capture domain-specific geomorphic distinctions. We further show that domain-specific fine-tuning is critical for generalizable geospatial discovery in planetary settings. Our code is available at https://github.com/ml-stat-Sustech/MarsRetrieval --- ### Constant-Stepsize Stochastic Approximation: Finite-Time Convergence, Gaussian Approximation, and Tail Bounds Authors: Zedong Wang, Yuyang Wang, Ijay Narang, Felix Wang, Yuzhou Wang, Siva Theja Maguluri Published: 2026-02-15 Categories: cs.LG, math.PR arXiv: https://arxiv.org/abs/2602.13960v2 Constant-stepsize stochastic approximation (SA) is widely used in learning for computational efficiency, yet the distribution of the iterates is typically intractable. Classical asymptotics results give $X_k^{(α)} \approx X^{(α)} \approx x^\star+\sqrtαY$, where $X^{(α)}$ is the steady state and $Y$ is an appropriate Gaussian limit, by progressively taking the time $k\uparrow\infty$ and stepsize $α\downarrow0$. Such limit results, however, do not quantify finite-time, finite-stepsize errors. We develop an explicit pre-limit characterization for SA with i.i.d.\ and Markovian noise. We establish existence and uniqueness of the stationary law, a geometric Wasserstein convergence to stationarity, and almost-sure and $L^3$ convergence of the steady state to the root $x^\star$, identifying the scale $\sqrtα$ as first-order fluctuation. At this scale, we derive a higher-order quantitative Gaussian approximation with a Wasserstein error, using Stein's method and Poisson equation techniques. We further obtain non-uniform Berry--Esseen-type tail bounds, incorporating both steady-state approximation and finite-time convergence errors. We instantiate the theory for strongly convex smooth SGD, linear SA, and nonlinear contractive SA. Beyond strong convexity, for general convex SGD, we identify a Gibbs limiting law and prove a pre-limit Wasserstein approximation error under stability and Stein-equation hypothesis, which are validated numerically. --- ### Steady-State Behavior of Constant-Stepsize Stochastic Approximation: Gaussian Approximation and Tail Bounds Authors: Zedong Wang, Yuyang Wang, Ijay Narang, Felix Wang, Yuzhou Wang, Siva Theja Maguluri Published: 2026-02-15 Categories: cs.LG, math.PR arXiv: https://arxiv.org/abs/2602.13960v1 Constant-stepsize stochastic approximation (SA) is widely used in learning for computational efficiency. For a fixed stepsize, the iterates typically admit a stationary distribution that is rarely tractable. Prior work shows that as the stepsize $α\downarrow 0$, the centered-and-scaled steady state converges weakly to a Gaussian random vector. However, for fixed $α$, this weak convergence offers no usable error bound for approximating the steady-state by its Gaussian limit. This paper provides explicit, non-asymptotic error bounds for fixed $α$. We first prove general-purpose theorems that bound the Wasserstein distance between the centered-scaled steady state and an appropriate Gaussian distribution, under regularity conditions for drift and moment conditions for noise. To ensure broad applicability, we cover both i.i.d. and Markovian noise models. We then instantiate these theorems for three representative SA settings: (1) stochastic gradient descent (SGD) for smooth strongly convex objectives, (2) linear SA, and (3) contractive nonlinear SA. We obtain dimension- and stepsize-dependent, explicit bounds in Wasserstein distance of order $α^{1/2}\log(1/α)$ for small $α$. Building on the Wasserstein approximation error, we further derive non-uniform Berry--Esseen-type tail bounds that compare the steady-state tail probability to Gaussian tails. We achieve an explicit error term that decays in both the deviation level and stepsize $α$. We adapt the same analysis for SGD beyond strongly convexity and study general convex objectives. We identify a non-Gaussian (Gibbs) limiting law under the correct scaling, which is validated numerically, and provide a corresponding pre-limit Wasserstein error bound. --- ### Chemical Language Models for Natural Products: A State-Space Model Approach Authors: Ho-Hsuan Wang, Afnan Sultan, Andrea Volkamer, Dietrich Klakow Published: 2026-02-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13958v1 Language models are widely used in chemistry for molecular property prediction and small-molecule generation, yet Natural Products (NPs) remain underexplored despite their importance in drug discovery. To address this gap, we develop NP-specific chemical language models (NPCLMs) by pre-training state-space models (Mamba and Mamba-2) and comparing them with transformer baselines (GPT). Using a dataset of about 1M NPs, we present the first systematic comparison of selective state-space models and transformers for NP-focused tasks, together with eight tokenization strategies including character-level, Atom-in-SMILES (AIS), byte-pair encoding (BPE), and NP-specific BPE. We evaluate molecule generation (validity, uniqueness, novelty) and property prediction (membrane permeability, taste, anti-cancer activity) using MCC and AUC-ROC. Mamba generates 1-2 percent more valid and unique molecules than Mamba-2 and GPT, with fewer long-range dependency errors, while GPT yields slightly more novel structures. For property prediction, Mamba variants outperform GPT by 0.02-0.04 MCC under random splits, while scaffold splits show comparable performance. Results demonstrate that domain-specific pre-training on about 1M NPs can match models trained on datasets over 100 times larger. --- ### Eureka-Audio: Triggering Audio Intelligence in Compact Language Models Authors: Dan Zhang, Yishu Lei, Jing Hu, Shuwei He, Songhe Deng, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou He, Yu Sun, Hua Wu et al. Published: 2026-02-15 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2602.13954v1 We present Eureka-Audio, a compact yet high-performance audio language model that achieves competitive performance against models that are 4 to 18 times larger across a broad range of audio understanding benchmarks. Despite containing only 1.7B parameters, Eureka-Audio demonstrates strong performance on automatic speech recognition (ASR), audio understanding, and dense audio captioning, matching or surpassing multiple 7B to 30B audio and omni-modal baselines. The model adopts a unified end-to-end architecture composed of a lightweight language backbone, a Whisper-based audio encoder, and a sparsely activated Mixture-of-Experts (MoE) adapter that explicitly accounts for audio heterogeneity and alleviates cross-modal optimization conflicts under limited capacity. To further enhance paralinguistic reasoning, we introduce DataFlux, a closed loop audio instruction data synthesis and verification pipeline that constructs high quality, logically consistent supervision from raw audio. Extensive evaluations across ASR, knowledge reasoning, safety, instruction following, and paralinguistic benchmarks, demonstrate that Eureka-Audio achieves an efficient balance between computational cost and performance. These results establish Eureka Audio as a strong and practical baseline for lightweight audio understanding models. --- ### QuRL: Efficient Reinforcement Learning with Quantized Rollout Authors: Yuhang Li, Reena Elangovan, Xin Dong, Priyadarshini Panda, Brucek Khailany Published: 2026-02-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13953v1 Reinforcement learning with verifiable rewards (RLVR) has become a trending paradigm for training reasoning large language models (LLMs). However, due to the autoregressive decoding nature of LLMs, the rollout process becomes the efficiency bottleneck of RL training, consisting of up to 70\% of the total training time. In this work, we propose Quantized Reinforcement Learning (QuRL) that uses a quantized actor for accelerating the rollout. We address two challenges in QuRL. First, we propose Adaptive Clipping Range (ACR) that dynamically adjusts the clipping ratio based on the policy ratio between the full-precision actor and the quantized actor, which is essential for mitigating long-term training collapse. Second, we identify the weight update problem, where weight changes between RL steps are extremely small, making it difficult for the quantization operation to capture them effectively. We mitigate this problem through the invariant scaling technique that reduces quantization noise and increases weight update. We evaluate our method with INT8 and FP8 quantization experiments on DeepScaleR and DAPO, and achieve 20% to 80% faster rollout during training. --- ### Experiential Reinforcement Learning Authors: Taiwei Shi, Sihao Chen, Bowen Jiang, Linxin Song, Longqi Yang, Jieyu Zhao Published: 2026-02-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13949v1 Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is challenging, as LMs must implicitly infer how observed failures should translate into behavioral changes for future iterations. We introduce Experiential Reinforcement Learning (ERL), a training paradigm that embeds an explicit experience-reflection-consolidation loop into the reinforcement learning process. Given a task, the model generates an initial attempt, receives environmental feedback, and produces a reflection that guides a refined second attempt, whose success is reinforced and internalized into the base policy. This process converts feedback into structured behavioral revision, improving exploration and stabilizing optimization while preserving gains at deployment without additional inference cost. Across sparse-reward control environments and agentic reasoning benchmarks, ERL consistently improves learning efficiency and final performance over strong reinforcement learning baselines, achieving gains of up to +81% in complex multi-step environments and up to +11% in tool-using reasoning tasks. These results suggest that integrating explicit self-reflection into policy training provides a practical mechanism for transforming feedback into durable behavioral improvement. --- ### Fusing Pixels and Genes: Spatially-Aware Learning in Computational Pathology Authors: Minghao Han, Dingkang Yang, Linhao Qu, Zizhi Chen, Gang Li, Han Wang, Jiacong Wang, Lihua Zhang Published: 2026-02-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13944v1 Recent years have witnessed remarkable progress in multimodal learning within computational pathology. Existing models primarily rely on vision and language modalities; however, language alone lacks molecular specificity and offers limited pathological supervision, leading to representational bottlenecks. In this paper, we propose STAMP, a Spatial Transcriptomics-Augmented Multimodal Pathology representation learning framework that integrates spatially-resolved gene expression profiles to enable molecule-guided joint embedding of pathology images and transcriptomic data. Our study shows that self-supervised, gene-guided training provides a robust and task-agnostic signal for learning pathology image representations. Incorporating spatial context and multi-scale information further enhances model performance and generalizability. To support this, we constructed SpaVis-6M, the largest Visium-based spatial transcriptomics dataset to date, and trained a spatially-aware gene encoder on this resource. Leveraging hierarchical multi-scale contrastive alignment and cross-scale patch localization mechanisms, STAMP effectively aligns spatial transcriptomics with pathology images, capturing spatial structure and molecular variation. We validate STAMP across six datasets and four downstream tasks, where it consistently achieves strong performance. These results highlight the value and necessity of integrating spatially resolved molecular supervision for advancing multimodal learning in computational pathology. The code is included in the supplementary materials. The pretrained weights and SpaVis-6M are available at: https://github.com/Hanminghao/STAMP. --- ### A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization Authors: Zexuan Sun, Garvesh Raskutti Published: 2026-02-15 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.13942v1 In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is why only a few epochs of fine-tuning are typically sufficient to achieve strong performance on many different tasks. In this work, we approach this question by developing a statistical framework, combining rigorous early stopping theory with the attention-based Neural Tangent Kernel (NTK) for LLMs, offering new theoretical insights on fine-tuning practices. Specifically, we formally extend classical NTK theory (Jacot et al., 2018) to non-random (i.e., pretrained) initializations and provide a convergence guarantee for attention-based fine-tuning. One key insight provided by the theory is that the convergence rate with respect to sample size is closely linked to the eigenvalue decay rate of the empirical kernel matrix induced by the NTK. We also demonstrate how the framework can be used to explain task vectors for multiple tasks in LLMs. Finally, experiments with modern language models on real-world datasets provide empirical evidence supporting our theoretical insights. --- ### You Can Learn Tokenization End-to-End with Reinforcement Learning Authors: Sam Dauncey, Roger Wattenhofer Published: 2026-02-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13940v4 Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at scale in bringing this compression step inside the LLMs' architecture with heuristics to draw token boundaries, and also attempts to learn these token boundaries with straight-through estimates, which treat the problem of drawing discrete token boundaries as a continuous one. We show that these token boundaries can instead be learned using score function estimates, which have tighter theoretical guarantees due to directly optimizing the problem of drawing discrete token boundaries to minimize loss. We observe that techniques from reinforcement learning, such as time discounting, are necessary to reduce the variance of this score function sufficiently to make it practicable. We demonstrate that the resultant method outperforms prior proposed straight-through estimates, both qualitatively and quantitatively at the $100$ million parameter scale. --- ### You Can Learn Tokenization End-to-End with Reinforcement Learning Authors: Sam Dauncey, Roger Wattenhofer Published: 2026-02-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13940v2 Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at scale in bringing this compression step inside the LLMs' architecture with heuristics to draw token boundaries, and also attempts to learn these token boundaries with straight-through estimates, which treat the problem of drawing discrete token boundaries as a continuous one. We show that these token boundaries can instead be learned using score function estimates, which have tighter theoretical guarantees due to directly optimizing the problem of drawing discrete token boundaries to minimize loss. We observe that techniques from reinforcement learning, such as time discounting, are necessary to reduce the variance of this score function sufficiently to make it practicable. We demonstrate that the resultant method outperforms prior proposed straight-through estimates, both qualitatively and quantitatively at the $100$ million parameter scale. --- ### Adaptive Automatic Model Selection for Demand Forecasting under Heterogeneous Demand Patterns Authors: Adolfo González, Víctor Parada Published: 2026-02-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13939v7 Demand forecasting is critical for inventory planning, procurement, replenishment, production, and capacity decisions in heterogeneous supply chains. However, selecting the most appropriate model for each demand series remains challenging because performance varies across datasets, demand structures, horizons, and evaluation metrics. This study proposes the Adaptive Hybrid Selector (AHS), an automatic model-selection rule that combines observed predictive performance with structural demand information. AHS uses demand frequency and series variability to activate a hierarchical logic based on RMSSE, MAE, sMAPE, and BIAS. The proposed selector is compared with Overall Weighted Average (OWA), a benchmark-relative criterion based on sMAPE and MASE, and Equilibrium Ranking Aggregation (ERA), a comparator based on MAE, RMSE, and R^2 rankings. The empirical evaluation uses the Walmart, M3, M4, and M5 datasets, three training-testing partitions, 22 forecasting models, and horizons of up to 12 cycles. Selector performance is assessed ex post using Global Relative Accuracy (GRA), interpreted as an indicator of volumetric coherence between accumulated forecasted demand and observed demand. Results show that AHS provides the most robust overall behavior, especially in M5, while OWA remains competitive in more regular datasets. ERA shows lower volumetric coherence in most configurations. These findings suggest that automatic model selection should account for demand structure and be evaluated using ex post indicators of volumetric coherence. --- ### iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML Authors: Dat Le, Duc-Cuong Le, Anh-Son Nguyen, Tuan-Dung Bui, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo Published: 2026-02-15 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2602.13937v2 Automated Machine Learning (AutoML) has improved access to machine learning, yet existing techniques often remain limited in flexibility, transparency, and execution reliability. Code-driven AutoML offers a promising direction by synthesizing executable code for preprocessing, model training, and evaluation. However, current LLM-based approaches frequently generate code that is plausible in text yet brittle in execution, insufficiently grounded in the actual dataset, or restricted to narrow solution paths. In this paper, we introduce iML, a multi-agent code-driven AutoML framework designed around three requirements: executability, problem grounding, and broad exploration of valid solutions. iML first analyzes the task and profiles the data, then synthesizes a structured blueprint that guides modular code generation across multiple implementation tracks, including traditional ML,pretrained adaptation, and custom neural architectures. To improve reliability, iML enforces interface checking, dynamic execution, and iterative debugging during integration. We evaluate iML on MLE-BENCH and the newly introduced iML-BENCH, covering diverse Kaggle-style tasks. On MLE-BENCH, iML attains a 90% valid submission rate and a 45% medal rate, and an APS of 0.82, improving the average standardized performance score (APS) over the LLM-based baselines by 52%-273%. On iML-BENCH, it achieves the highest APS and demonstrates robust performance even when task descriptions are substantially stripped. These results establish iML as a reliable and competitive framework for code-driven AutoML. --- ### A Generalizable Physics-guided Causal Model for Trajectory Prediction in Autonomous Driving Authors: Zhenyu Zong, Yuchen Wang, Haohong Lin, Lu Gan, Huajie Shao Published: 2026-02-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13936v1 Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consistent nature of kinematics across diverse domains, we aim to incorporate domain-invariant knowledge to enhance zero-shot trajectory prediction capabilities. The key challenges include: 1) effectively extracting domain-invariant scene representations, and 2) integrating invariant features with kinematic models to enable generalized predictions. To address these challenges, we propose a novel generalizable Physics-guided Causal Model (PCM), which comprises two core components: a Disentangled Scene Encoder, which adopts intervention-based disentanglement to extract domain-invariant features from scenes, and a CausalODE Decoder, which employs a causal attention mechanism to effectively integrate kinematic models with meaningful contextual information. Extensive experiments on real-world autonomous driving datasets demonstrate our method's superior zero-shot generalization performance in unseen cities, significantly outperforming competitive baselines. The source code is released at https://github.com/ZY-Zong/Physics-guided-Causal-Model. --- ### Statistical Early Stopping for Reasoning Models Authors: Yangxinyu Xie, Tao Wang, Soham Mallick, Yan Sun, Georgy Noarov, Mengxin Yu, Tanwi Mallick, Edgar Dobriban Published: 2026-02-15 Categories: cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.13935v3 While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically principled early stopping methods that monitor uncertainty signals during generation to mitigate this issue. Our first approach is parametric: it models inter-arrival times of uncertainty keywords as a renewal process and applies sequential testing for stopping. Our second approach is nonparametric and provides finite-sample guarantees on the probability of halting too early on well-posed queries. We conduct empirical evaluations on reasoning tasks across several domains and models. Our results indicate that uncertainty-aware early stopping can improve both efficiency and reliability in LLM reasoning, and we observe especially significant gains for math reasoning. --- ### Why Code, Why Now: An Information-Theoretic Perspective on the Limits of Machine Learning Authors: Zhimin Zhao Published: 2026-02-15 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.13934v4 This paper offers a new perspective on the limits of machine learning: the ceiling on progress is set not by model size or algorithm choice but by the information structure of the task itself. Code generation has progressed more reliably than reinforcement learning, largely because code provides dense, local, verifiable feedback at every token, whereas most reinforcement learning problems do not. This difference in feedback quality is not binary but graded. We propose a five-level hierarchy of learnability based on information structure and argue that diagnosing a task's position in this hierarchy is more predictive of scaling outcomes than any property of the model. The hierarchy rests on a formal distinction among three properties of computational problems (expressibility, computability, and learnability). We establish their pairwise relationships, including where implications hold and where they fail, and present a unified template that makes the structural differences explicit. The analysis suggests why supervised learning on code scales predictably while reinforcement learning does not, and why the common assumption that scaling alone will solve remaining ML challenges warrants scrutiny. --- ### HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling Authors: Xiaochen Zhao, Kaikai Wang, Xiaowen Zhang, Chen Yao, Aili Wang Published: 2026-02-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13933v2 Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to inefficient memory management. Existing approaches face a fundamental trade-off between efficiency and effectiveness: memory compression risks losing critical details required for complex reasoning, while retaining raw text introduces unnecessary computational overhead for simple queries. The crux lies in the limitations of monolithic memory representations and static retrieval mechanisms, which fail to emulate the flexible and proactive memory scheduling capabilities observed in humans, thus struggling to adapt to diverse problem scenarios. Inspired by the principle of cognitive economy, we propose HyMem, a hybrid memory architecture that enables dynamic on-demand scheduling through multi-granular memory representations. HyMem adopts a dual-granular storage scheme paired with a dynamic two-tier retrieval system: a lightweight module constructs summary-level context for efficient response generation, while an LLM-based deep module is selectively activated only for complex queries, augmented by a reflection mechanism for iterative reasoning refinement. Experiments show that HyMem achieves strong performance on both the LOCOMO and LongMemEval benchmarks, outperforming full-context while reducing computational cost by 92.6\%, establishing a state-of-the-art balance between efficiency and performance in long-term memory management. --- ### LCM: Lossless Context Management Authors: Clint Ehrlich, Theodore Blackman Published: 2026-02-14 Categories: cs.AI, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2605.04050v1 We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented coding agent, Volt, achieves higher scores than Claude Code on the OOLONG long-context eval, including at every context length between 32K and 1M tokens. LCM may be considered both a vindication and extension of the recursive paradigm pioneered by Recursive Language Models (RLMs). Our results demonstrate that recursive context manipulation can outperform not just conventional LLMs, but frontier coding agents with native file-system access. LCM departs from RLM by decomposing symbolic recursion into two deterministic, engine-managed mechanisms: recursive context compression, in which a hierarchical summary DAG automatically compacts older messages while retaining lossless pointers to every original; and recursive task partitioning, in which engine-managed parallel primitives like LLM-Map replace model-written loops. This trade-off, analogous to the move from GOTO to structured control flow in program-ming language design, sacrifices maximal flexibility for termination guarantees, zero-cost continuity on short tasks, and lossless retrievability of all prior state. --- ### ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness Authors: Wenxing Zhu, Simeng Qi, Junkui Chen, Yan Xie, Min Huang, Jingkan He, Xiao Wang, Cheng Chen, Sijing Meng, Tianqi Zhang Published: 2026-02-14 Categories: cs.DC, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.09564v1 We present ACE-Bench (Azure SDK Coding Evaluation Benchmark), an execution-free benchmark that provides fast, reproducible pass or fail signals for whether large language model (LLM)-based coding agents use Azure SDKs correctly-without provisioning cloud resources or maintaining fragile end-to-end test environments. ACE-Bench turns official Azure SDK documentation examples into self-contained coding tasks and validates solutions with task-specific atomic criteria: deterministic regex checks that enforce required API usage patterns and reference-based LLM-judge checks that capture semantic workflow constraints. This design makes SDK-centric evaluation practical in day-to-day development and CI: it reduces evaluation cost, improves repeatability, and scales to new SDKs and languages as documentation evolves. Using a lightweight coding agent, we benchmark multiple state-of-the-art LLMs and quantify the benefit of retrieval in an MCP-enabled augmented setting, showing consistent gains from documentation access while highlighting substantial cross-model differences. --- ### Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya Authors: Sharath Sathish Published: 2026-02-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.04937v1 Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple researchers added irrelevant context to mathematical problems, LLM performance degraded by 65% Apple Machine Learning Research, exposing brittle pattern-matching beneath apparent reasoning. This epistemic gap, the inability to ground claims in traceable evidence, limits AI reliability in domains requiring justification. We introduce Pramana, a novel approach that teaches LLMs explicit epistemological methodology by fine-tuning on Navya-Nyaya logic, a 2,500-year-old Indian reasoning framework. Unlike generic chain-of-thought prompting, Navya-Nyaya enforces structured 6-phase reasoning: SAMSHAYA (doubt analysis), PRAMANA (evidence source identification), PANCHA AVAYAVA (5-member syllogism with universal rules), TARKA (counterfactual verification), HETVABHASA (fallacy detection), and NIRNAYA (ascertainment distinguishing knowledge from hypothesis). This integration of logic and epistemology provides cognitive scaffolding absent from standard reasoning approaches. We fine-tune Llama 3.2-3B and DeepSeek-R1-Distill-Llama-8B on 55 Nyaya-structured logical problems (constraint satisfaction, Boolean SAT, multi-step deduction). Stage 1 achieves 100% semantic correctness on held-out evaluation despite only 40% strict format adherence revealing that models internalize reasoning content even when structural enforcement is imperfect. Ablation studies show format prompting and temperature critically affect performance, with optimal configurations differing by stage. We release all models, datasets, and training infrastructure on Hugging Face to enable further research on epistemic frameworks for AI reasoning. --- ### Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives Authors: Ruchira Dhar, Qiwei Peng, Anders Søgaard Published: 2026-02-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.09994v2 Compositionality is considered central to language abilities. As performant language systems, how do large language models (LLMs) do on compositional tasks? We evaluate adjective-noun compositionality in LLMs using two complementary setups: prompt-based functional assessment and a representational analysis of internal model states. Our results reveal a striking divergence between task performance and internal states. While LLMs reliably develop compositional representations, they fail to translate consistently into functional task success across model variants. Consequently, we highlight the importance of contrastive evaluation for obtaining a more complete understanding of model capabilities. --- ### CEI: A Benchmark for Evaluating Pragmatic Reasoning in Language Models Authors: Jon Chun, Hannah Sussman, Adrian Mangine, Murathan Kocaman, Kirill Sidorko, Abhigya Koirala, Andre McCloud, Gwen Eisenbeis, Wisdom Akanwe, Moustapha Gassama, Eliezer Gonzalez Chirinos, Anne-Duncan Enright et al. Published: 2026-02-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.09993v1 Pragmatic reasoning, inferring intended meaning beyond literal semantics, underpins everyday communication yet remains difficult for large language models. We present the Contextual Emotional Inference (CEI) Benchmark: 300 human-validated scenarios for evaluating how well LLMs disambiguate pragmatically complex utterances. Each scenario pairs a situational context and speaker-listener roles (with explicit power relations) against an ambiguous utterance. The dataset covers five pragmatic subtypes (sarcasm/irony, mixed signals, strategic politeness, passive aggression, deflection/misdirection) drawn from workplace, family, social, and service settings, with three power configurations (peer, higher-to-lower, lower-to-higher). Three trained annotators independently labeled every scenario. Inter-annotator agreement (Fleiss' kappa = 0.06-0.25 by subtype) is low but expected: pragmatic inference admits multiple valid readings, and the disagreement itself is informative. We describe our annotation methodology, including a 4-level quality control pipeline that combines automated statistical checks with expert adjudication. CEI is released under CC-BY-4.0. --- ### TAMUSA-Chat: A Domain-Adapted Large Language Model Conversational System for Research and Responsible Deployment Authors: Izzat Alsmadi, Anas Alsobeh Published: 2026-02-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.09992v1 This paper presents TAMUSA-Chat, a research-oriented framework for building domain-adapted large language model conversational systems. The work addresses critical challenges in adapting general-purpose foundation models to institutional contexts through supervised fine-tuning, retrieval-augmented generation, and systematic evaluation methodologies. We describe the complete architecture encompassing data acquisition from institutional sources, preprocessing pipelines, embedding construction, model training workflows, and deployment strategies. The system integrates modular components enabling reproducible experimentation with training configurations, hyper-parameters, and evaluation protocols. Our implementation demonstrates how academic institutions can develop contextually grounded conversational agents while maintaining transparency, governance compliance, and responsible AI practices. Through empirical analysis of fine-tuning behavior across model sizes and training iterations, we provide insights into domain adaptation efficiency, computational resource requirements, and quality-cost trade-offs. The publicly available codebase at https://github.com/alsmadi/TAMUSA_LLM_Based_Chat_app supports continued research into institutional LLM deployment, evaluation methodologies, and ethical considerations for educational AI systems. --- ### PoultryLeX-Net: Domain-Adaptive Dual-Stream Transformer Architecture for Large-Scale Poultry Stakeholder Modeling Authors: Stephen Afrifa, Biswash Khatiwada, Kapalik Khanal, Sanjay Shah, Lingjuan Wang-Li, Ramesh Bahadur Bist Published: 2026-02-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.09991v1 The rapid growth of the global poultry industry, driven by rising demand for affordable animal protein, has intensified public discourse surrounding production practices, housing, management, animal welfare, and supply-chain transparency. Social media platforms such as X (formerly Twitter) generate large volumes of unstructured textual data that capture stakeholder sentiment across the poultry industry. Extracting accurate sentiment signals from this domain-specific discourse remains challenging due to contextual ambiguity, linguistic variability, and limited domain awareness in general-purpose language models. This study presents PoultryLeX-Net, a lexicon-enhanced, domain-adaptive dual-stream transformer framework for fine-grained sentiment analysis in poultry-related text. The proposed architecture integrates sentiment classification, topic modeling, and contextual representation learning through domain-specific embeddings and gated cross-attention mechanisms. A lexicon-guided stream captures poultry-specific terminology and sentiment cues, while contextual stream models long-range semantic dependencies. Latent Dirichlet Allocation is employed to identify dominant thematic structures associated with production management and welfare-related discussions, providing complementary interpretability to sentiment predictions. PoultryLeX-Net was evaluated against multiple baseline models, including convolutional neural network and pre-trained transformer architectures such as DistilBERT and RoBERTa. PoultryLeX-Net consistently outperformed all baselines, achieving an accuracy of 97.35%, an F1 score of 96.67%, and an area under the receiver operating characteristic curve (AUC-ROC) of 99.61% across sentiment classification tasks. Overall, domain adaptation and dual-stream attention markedly improve sentiment classification, enabling scalable intelligence for poultry production decision support. --- ### Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis? Authors: Grace Chang Yuan, Xiaoman Zhang, Sung Eun Kim, Pranav Rajpurkar Published: 2026-02-14 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.04421v2 Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis, leveraging collaboration among agents to refine medical reasoning. However, most existing frameworks rely on single-vendor teams (e.g., multiple agents from the same model family), which risk correlated failure modes that reinforce shared biases rather than correcting them. We investigate the impact of vendor diversity by comparing Single-LLM, Single-Vendor, and Mixed-Vendor Multi-Agent Conversation (MAC) frameworks. Using three doctor agents instantiated with o4-mini, Gemini-2.5-Pro, and Claude-4.5-Sonnet, we evaluate performance on RareBench and DiagnosisArena. Mixed-vendor configurations consistently outperform single-vendor counterparts, achieving state-of-the-art recall and accuracy. Overlap analysis reveals the underlying mechanism: mixed-vendor teams pool complementary inductive biases, surfacing correct diagnoses that individual models or homogeneous teams collectively miss. These results highlight vendor diversity as a key design principle for robust clinical diagnostic systems. --- ### Machine Learning for Complex Systems Dynamics: Detecting Bifurcations in Dynamical Systems with Deep Neural Networks Authors: Swadesh Pal, Roderick Melnik Published: 2026-02-14 Categories: cs.LG, math.DS, q-bio.NC, stat.ML arXiv: https://arxiv.org/abs/2603.04420v1 Critical transitions are the abrupt shifts between qualitatively different states of a system, and they are crucial to understanding tipping points in complex dynamical systems across ecology, climate science, and biology. Detecting these shifts typically involves extensive forward simulations or bifurcation analyses, which are often computationally intensive and limited by parameter sampling. In this study, we propose a novel machine learning approach based on deep neural networks (DNNs) called equilibrium-informed neural networks (EINNs) to identify critical thresholds associated with catastrophic regime shifts. Rather than fixing parameters and searching for solutions, the EINN method reverses this process by using candidate equilibrium states as inputs and training a DNN to infer the corresponding system parameters that satisfy the equilibrium condition. By analyzing the learned parameter landscape and observing abrupt changes in the feasibility or continuity of equilibrium mappings, critical thresholds can be effectively detected. We demonstrate this capability on nonlinear systems exhibiting saddle-node bifurcations and multi-stability, showing that EINNs can recover the parameter regions associated with impending transitions. This method provides a flexible alternative to traditional techniques, offering new insights into the early detection and structure of critical shifts in high-dimensional and nonlinear systems. --- ### Context-Dependent Affordance Reports in Vision-Language Models Authors: Murad Farzulla Published: 2026-02-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.04419v3 Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify an affordance effect. We audit an earlier seven-prompt study and add matched-question controls. In the historical Qwen pilot, 363 of 3,213 parsed responses contain empty object lists. These affect 2,037 of 9,244 comparisons, with the implementation assigning zero lexical overlap to every affected pair. Conditioning on nonempty reports raises pooled word Jaccard from 0.095 to 0.121 and sentence cosine from 0.415 to 0.511. A previously named chef-specific Tucker factor loses its concentrated loading under missing-cell and complete-nonempty analyses. We withdraw the functional-manifold interpretation and the conversion of similarity scores into percentages of meaning. A new experiment uses 48 images absent from the original pilot, four personas, a shared three-object task, two wordings, and two requested seeds in each of two model configurations. Qwen3.5-9B's persona-minus-wording cosine-distance contrast is 0.0146 (95% CI (-0.0003, 0.0295); 37 complete images). Ollama llava:13b's persona-minus-wording cosine-distance contrast is -0.0266 (95% CI (-0.0412, -0.0121); 32 complete images). Persona-associated variation does not uniformly exceed wording or sampling variation. The study provides a reproducible analysis of context-conditioned reports while separating response availability, content similarity, and the limits of inference from linguistic outputs. --- ### Context-Dependent Affordance Computation in Vision-Language Models Authors: Murad Farzulla Published: 2026-02-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.04419v2 We characterize the phenomenon of context-dependent affordance computation in vision-language models (VLMs). Our primary study uses Qwen3-VL-30B-A3B ($n = 3{,}213$ scene-context pairs from COCO-2017: 479 images under 7 agentic personas), with a cross-model replication on LLaVA-1.5-13B. We demonstrate substantial affordance drift: mean Jaccard similarity between context conditions is $0.095$ (95% CI $(0.092, 0.097)$ across $N = 479$ images; $9{,}244$ prime pairs; $p < 0.0001$), indicating that more than 90% of lexical scene description is context-dependent; the LLaVA replication reproduces the effect (mean $J = 0.160$, 84% context-dependent). Sentence-level cosine similarity confirms drift at the semantic level (mean $= 0.415$, 58.5% context-dependent). Stochastic baseline experiments ($2{,}384$ inference runs across 4 temperatures and 5 seeds) confirm this reflects genuine context effects rather than generation noise: within-prime variance is substantially lower than cross-prime variance across all conditions. Tucker decomposition with bootstrap stability analysis ($n = 1{,}000$ resamples) reveals stable orthogonal latent factors: a "Culinary Manifold" isolated to chef contexts and an "Access Axis" spanning child-mobility contrasts. The gap between lexical (90%) and semantic (58.5%) measures indicates that surface vocabulary changes more than underlying meaning under context shifts. These findings suggest a direction for robotics: dynamic, query-dependent ontological projection (JIT Ontology) rather than static world modeling. We do not claim to establish processing order or architectural primacy; such claims require internal representational analysis beyond output behavior. --- ### Arapai: An Offline-First LLM Architecture for Adaptive Learning in Low-Connectivity Environments Authors: Joseph Walusimbi, Ann Move Oguti, Joshua Benjamin Ssentongo, Keith Ainebyona Published: 2026-02-14 Categories: cs.CY, cs.AR, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2603.03339v7 Artificial intelligence and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalised explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents Arapai, an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aware model selection to enable deployment on low-specification, CPU-only devices. By removing dependence on cloud infrastructure, the system provides curriculum-aligned explanations and structured academic support through natural-language interaction. To support learners at different educational stages, the system includes adaptive response levels that generate explanations at varying levels of complexity: Simple English, Lower Secondary, Upper Secondary, and Technical. The system was evaluated with 120 students and 9 instructors from secondary and tertiary institutions under limited-connectivity conditions. Results indicate stable operation on legacy hardware, acceptable response times of 1-3 seconds for typical queries, and positive user perceptions of its effectiveness in supporting self-directed learning. --- ### DeepXiv-SDK: An Agentic Data Interface for Scientific Literature Authors: Hongjin Qian, Ziyi Xia, Ze Liu, Jianlyu Chen, Kun Luo, Minghao Qin, Chaofan Li, Lei Xiong, Junwei Lan, Sen Wang, Zhengyang Liang, Yingxia Shao et al. Published: 2026-02-14 Categories: cs.DL, cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2603.00084v2 LLM-agents are increasingly used to accelerate the progress of scientific research. Yet a persistent bottleneck is data access: agents not only lack readily available tools for retrieval, but also have to work with unstrcutured, human-centric data on the Internet, such as HTML web-pages and PDF files, leading to excessive token consumption, limit working efficiency, and brittle evidence look-up. This gap motivates the development of \textit{an agentic data interface}, which is designed to enable agents to access and utilize scientific literature in a more effective, efficient, and cost-aware manner. In this paper, we introduce DeepXiv-SDK, which offers a three-layer agentic data interface for scientific literature. 1) Data Layer, which transforms unstructured, human-centric data into normalized and structured representations in JSON format, improving data usability and enabling progressive accessibility of the data. 2) Service Layer, which presents readily available tools for data access and ad-hoc retrieval. It also enables a rich form of agent usage, including CLI, MCP, and Python SDK. 3) Application Layer, which creates a built-in agent, packaging basic tools from the service layer to support complex data access demands. DeepXiv-SDK currently supports the complete ArXiv corpus, and is synchronized daily to incorporate new releases. It is designed to extend to all common open-access corpora, such as PubMed Central, bioRxiv, medRxiv, and chemRxiv. We release RESTful APIs, an open-source Python SDK, and a web demo showcasing deep search and deep research workflows. DeepXiv-SDK is free to use with registration. --- ### Linguistic Uncertainty and Engagement in Arabic-Language X (formerly Twitter) Discourse Authors: Mohamed Soufan Published: 2026-02-14 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2603.00082v1 Linguistic uncertainty is a common feature of social media discourse, yet its relationship with user engagement remains underexplored, particularly in non-English contexts. Using a dataset of 16,695 Arabic-language tweets about Lebanon posted over a 35-day period, we examine whether tweets expressing linguistic uncertainty receive different levels and forms of engagement compared to certainty-marked tweets. We develop a lexicon-based, context-sensitive classifier to identify uncertainty markers and classify 29.9% of tweets as uncertain. Descriptive analyses indicate that uncertain tweets exhibit 51.5% higher mean total engagement (likes, retweets, and replies). Regression models controlling for tweet length, URL presence, and account verification status confirm a positive association between uncertainty and engagement (\b{eta} = 0.221, SE = 0.044, p < 0.001), corresponding to approximately 25% higher expected engagement. The association is strongest for replies, followed by retweets and likes, suggesting a shift toward more conversational forms of engagement. Results are robust to alternative model specifications and adjustments for within-account correlation. These findings suggest that linguistic uncertainty may function as an interactional cue that encourages participatory engagement in Arabic-language social media discourse. The study contributes computational approaches for modeling linguistic features in large-scale, non-English digital communication. --- ### An Adaptive Multichain Blockchain: A Multiobjective Optimization Approach Authors: Nimrod Talmon, Haim Zysberg Published: 2026-02-14 Categories: cs.CR, cs.GT, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2602.22230v1 Blockchains are widely used for secure transaction processing, but their scalability remains limited, and existing multichain designs are typically static even as demand and capacity shift. We cast blockchain configuration as a multiagent resource-allocation problem: applications and operators declare demand, capacity, and price bounds; an optimizer groups them into ephemeral chains each epoch and sets a chain-level clearing price. The objective maximizes a governance-weighted combination of normalized utilities for applications, operators, and the system. The model is modular -- accommodating capability compatibility, application-type diversity, and epoch-to-epoch stability -- and can be solved off-chain with outcomes verifiable on-chain. We analyze fairness and incentive issues and present simulations that highlight trade-offs among throughput, decentralization, operator yield, and service stability. --- ### RDBLearn: Simple In-Context Prediction Over Relational Databases Authors: Yanlin Zhang, Linjie Xu, Quan Gan, David Wipf, Minjie Wang Published: 2026-02-14 Categories: cs.DB, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18495v1 Recent advances in tabular in-context learning (ICL) show that a single pretrained model can adapt to new prediction tasks from a small set of labeled examples, avoiding per-task training and heavy tuning. However, many real-world tasks live in relational databases, where predictive signal is spread across multiple linked tables rather than a single flat table. We show that tabular ICL can be extended to relational prediction with a simple recipe: automatically featurize each target row using relational aggregations over its linked records, materialize the resulting augmented table, and run an off-the-shelf tabular foundation model on it. We package this approach in \textit{RDBLearn} (https://github.com/HKUSHXLab/rdblearn), an easy-to-use toolkit with a scikit-learn-style estimator interface that makes it straightforward to swap different tabular ICL backends; a complementary agent-specific interface is provided as well. Across a broad collection of RelBench and 4DBInfer datasets, RDBLearn is the best-performing foundation model approach we evaluate, at times even outperforming strong supervised baselines trained or fine-tuned on each dataset. --- ### On the Dynamics of Observation and Semantics Authors: Xiu Li Published: 2026-02-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18494v1 A dominant paradigm in visual intelligence treats semantics as a static property of latent representations, assuming that meaning can be discovered through geometric proximity in high dimensional embedding spaces. In this work, we argue that this view is physically incomplete. We propose that intelligence is not a passive mirror of reality but a property of a physically realizable agent, a system bounded by finite memory, finite compute, and finite energy interacting with a high entropy environment. We formalize this interaction through the kinematic structure of an Observation Semantics Fiber Bundle, where raw sensory observation data (the fiber) is projected onto a low entropy causal semantic manifold (the base). We prove that for any bounded agent, the thermodynamic cost of information processing (Landauer's Principle) imposes a strict limit on the complexity of internal state transitions. We term this limit the Semantic Constant B. From these physical constraints, we derive the necessity of symbolic structure. We show that to model a combinatorial world within the bound B, the semantic manifold must undergo a phase transition, it must crystallize into a discrete, compositional, and factorized form. Thus, language and logic are not cultural artifacts but ontological necessities the solid state of information required to prevent thermal collapse. We conclude that understanding is not the recovery of a hidden latent variable, but the construction of a causal quotient that renders the world algorithmically compressible and causally predictable. --- ### Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment Authors: Jingwei Li, Jiaxin Tong, Pengfei Wu Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15903v1 The proliferation of highly realistic facial forgeries necessitates robust detection methods. However, existing approaches often suffer from limited accuracy and poor generalization due to significant distribution shifts among samples generated by diverse forgery techniques. To address these challenges, we propose a novel Multivariate and Soft Blending Augmentation with CLIP-guided Forgery Intensity Estimation (MSBA-CLIP) framework. Our method leverages the multimodal alignment capabilities of CLIP to capture subtle forgery traces. We introduce a Multivariate and Soft Blending Augmentation (MSBA) strategy that synthesizes images by blending forgeries from multiple methods with random weights, forcing the model to learn generalizable patterns. Furthermore, a dedicated Multivariate Forgery Intensity Estimation (MFIE) module is designed to explicitly guide the model in learning features related to varied forgery modes and intensities. Extensive experiments demonstrate state-of-the-art performance. On in-domain tests, our method improves Accuracy and AUC by 3.32\% and 4.02\%, respectively, over the best baseline. In cross-domain evaluations across five datasets, it achieves an average AUC gain of 3.27\%. Ablation studies confirm the efficacy of both proposed components. While the reliance on a large vision-language model entails higher computational cost, our work presents a significant step towards more generalizable and robust deepfake detection. --- ### Attention-gated U-Net model for semantic segmentation of brain tumors and feature extraction for survival prognosis Authors: Rut Pate, Snehal Rajput, Mehul S. Raval, Rupal A. Kapdi, Mohendra Roy Published: 2026-02-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15067v1 Gliomas, among the most common primary brain tumors, vary widely in aggressiveness, prognosis, and histology, making treatment challenging due to complex and time-intensive surgical interventions. This study presents an Attention-Gated Recurrent Residual U-Net (R2U-Net) based Triplanar (2.5D) model for improved brain tumor segmentation. The proposed model enhances feature representation and segmentation accuracy by integrating residual, recurrent, and triplanar architectures while maintaining computational efficiency, potentially aiding in better treatment planning. The proposed method achieves a Dice Similarity Score (DSC) of 0.900 for Whole Tumor (WT) segmentation on the BraTS2021 validation set, demonstrating performance comparable to leading models. Additionally, the triplanar network extracts 64 features per planar model for survival days prediction, which are reduced to 28 using an Artificial Neural Network (ANN). This approach achieves an accuracy of 45.71%, a Mean Squared Error (MSE) of 108,318.128, and a Spearman Rank Correlation Coefficient (SRC) of 0.338 on the test dataset. --- ### MamaDino: A Hybrid Vision Model for Breast Cancer 3-Year Risk Prediction Authors: Ruggiero Santeramo, Igor Zubarev, Florian Jug Published: 2026-02-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.13930v1 Breast cancer screening programmes increasingly seek to move from one-size-fits-all interval to risk-adapted and personalized strategies. Deep learning (DL) has enabled image-based risk models with stronger 1- to 5-year prediction than traditional clinical models, but leading systems (e.g., Mirai) typically use convolutional backbones, very high-resolution inputs (>1M pixels) and simple multi-view fusion, with limited explicit modelling of contralateral asymmetry. We hypothesised that combining complementary inductive biases (convolutional and transformer-based) with explicit contralateral asymmetry modelling would allow us to match state-of-the-art 3-year risk prediction performance even when operating on substantially lower-resolution mammograms, indicating that using less detailed images in a more structured way can recover state-of-the-art accuracy. We present MamaDino, a mammography-aware multi-view attentional DINO model. MamaDino fuses frozen self-supervised DINOv3 ViT-S features with a trainable CNN encoder at 512x512 resolution, and aggregates bilateral breast information via a BilateralMixer to output a 3-year breast cancer risk score. We train on 53,883 women from OPTIMAM (UK) and evaluate on matched 3-year case-control cohorts: an in-distribution test set from four screening sites and an external out-of-distribution cohort from an unseen site. At breast-level, MamaDino matches Mirai on both internal and external tests while using ~13x fewer input pixels. Adding the BilateralMixer improves discrimination to AUC 0.736 (vs 0.713) in-distribution and 0.677 (vs 0.666) out-of-distribution, with consistent performance across age, ethnicity, scanner, tumour type and grade. These findings demonstrate that explicit contralateral modelling and complementary inductive biases enable predictions that match Mirai, despite operating on substantially lower-resolution mammograms. ---