# Research Papers — 2026-02 · bundle page 23 of 210

> Full-text markdown of papers #1101–1150 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/23
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/22.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/24.md)

### Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents

Authors: Ryan Liu, Dilip Arumugam, Cedegao E. Zhang, Sean Escola, Xaq Pitkow, Thomas L. Griffiths
Published: 2026-02-26
Categories: cs.AI, cs.CL, q-bio.NC
arXiv: https://arxiv.org/abs/2602.22523v1

While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For such tasks, there is still uncertainty about how best to take many LLMs as parts and combine them into a greater whole. This position paper argues that potential blueprints for designing such modular language agents can be found in the existing literature on cognitive models and artificial intelligence (AI) algorithms. To make this point clear, we formalize the idea of an agent template that specifies roles for individual LLMs and how their functionalities should be composed. We then survey a variety of existing language agents in the literature and highlight their underlying templates derived directly from cognitive models or AI algorithms. By highlighting these designs, we aim to call attention to agent templates inspired by cognitive science and AI as a powerful tool for developing effective, interpretable language agents.

---

### Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing

Authors: An-Ci Peng, Kuan-Tang Huang, Tien-Hong Lo, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen
Published: 2026-02-26
Categories: cs.CL, cs.AI, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2602.22522v1

Taiwanese Hakka is a low-resource, endangered language that poses significant challenges for automatic speech recognition (ASR), including high dialectal variability and the presence of two distinct writing systems (Hanzi and Pinyin). Traditional ASR models often encounter difficulties in this context, as they tend to conflate essential linguistic content with dialect-specific variations across both phonological and lexical dimensions. To address these challenges, we propose a unified framework grounded in the Recurrent Neural Network Transducers (RNN-T). Central to our approach is the introduction of dialect-aware modeling strategies designed to disentangle dialectal "style" from linguistic "content", which enhances the model's capacity to learn robust and generalized representations. Additionally, the framework employs parameter-efficient prediction networks to concurrently model ASR (Hanzi and Pinyin). We demonstrate that these tasks create a powerful synergy, wherein the cross-script objective serves as a mutual regularizer to improve the primary ASR tasks. Experiments conducted on the HAT corpus reveal that our model achieves 57.00% and 40.41% relative error rate reduction on Hanzi and Pinyin ASR, respectively. To our knowledge, this is the first systematic investigation into the impact of Hakka dialectal variations on ASR and the first single model capable of jointly addressing these tasks.

---

### TFPS: A Temporal Filtration-enhanced Positive Sample Set Construction Method for Implicit Collaborative Filtering

Authors: Jiayi Wu, Zhengyu Wu, Xunkai Li, Rong-Hua Li, Guoren Wang
Published: 2026-02-26
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.22521v1

The negative sampling strategy can effectively train collaborative filtering (CF) recommendation models based on implicit feedback by constructing positive and negative samples. However, existing methods primarily optimize the negative sampling process while neglecting the exploration of positive samples. Some denoising recommendation methods can be applied to denoise positive samples within negative sampling strategies, but they ignore temporal information. Existing work integrates sequential information during model aggregation but neglects time interval information, hindering accurate capture of users' current preferences. To address this problem, from a data perspective, we propose a novel temporal filtration-enhanced approach to construct a high-quality positive sample set. First, we design a time decay model based on interaction time intervals, transforming the original graph into a weighted user-item bipartite graph. Then, based on predefined filtering operations, the weighted user-item bipartite graph is layered. Finally, we design a layer-enhancement strategy to construct a high-quality positive sample set for the layered subgraphs. We provide theoretical insights into why TFPS can improve Recall@k and NDCG@k, and extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed method. Additionally, TFPS can be integrated with various implicit CF recommenders or negative sampling methods to enhance its performance.

---

### TEFL: Prediction-Residual-Guided Rolling Forecasting for Multi-Horizon Time Series

Authors: Xiannan Huang, Shen Fang, Shuhan Qiu, Chengcheng Yu, Jiayuan Du, Chao Yang
Published: 2026-02-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.22520v1

Time series forecasting plays a critical role in domains such as transportation, energy, and meteorology. Despite their success, modern deep forecasting models are typically trained to minimize point-wise prediction loss without leveraging the rich information contained in past prediction residuals from rolling forecasts - residuals that reflect persistent biases, unmodeled patterns, or evolving dynamics. We propose TEFL (Temporal Error Feedback Learning), a unified learning framework that explicitly incorporates these historical residuals into the forecasting pipeline during both training and evaluation. To make this practical in deep multi-step settings, we address three key challenges: (1) selecting observable multi-step residuals under the partial observability of rolling forecasts, (2) integrating them through a lightweight low-rank adapter to preserve efficiency and prevent overfitting, and (3) designing a two-stage training procedure that jointly optimizes the base forecaster and error module. Extensive experiments across 10 real-world datasets and 5 backbone architectures show that TEFL consistently improves accuracy, reducing MAE by 5-10% on average. Moreover, it demonstrates strong robustness under abrupt changes and distribution shifts, with error reductions exceeding 10% (up to 19.5%) in challenging scenarios. By embedding residual-based feedback directly into the learning process, TEFL offers a simple, general, and effective enhancement to modern deep forecasting systems.

---

### A Mathematical Theory of Agency and Intelligence

Authors: Wael Hafez, Chenan Wei, Rodrigo Pena, Amir Nazeri, Cameron Reid
Published: 2026-02-26
Categories: cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2602.22519v2

To operate reliably under changing conditions, complex systems require feedback on how effectively they use resources, not just whether objectives are met. Current AI systems process vast information to produce sophisticated predictions, yet predictions can appear successful while the underlying interaction with the environment degrades. What is missing is a principled measure of how much of the total information a system deploys is actually shared between its observations, actions, and outcomes. We prove this shared fraction, which we term bipredictability, P, is intrinsic to any interaction, derivable from first principles, and strictly bounded: P can reach unity in quantum systems, P equal to, or smaller than 0.5 in classical systems, and lower once agency (action selection) is introduced. We confirm these bounds in a physical system (double pendulum), reinforcement learning agents, and multi turn LLM conversations. These results distinguish agency from intelligence: agency is the capacity to act on predictions, whereas intelligence additionally requires learning from interaction, self-monitoring of its learning effectiveness, and adapting the scope of observations, actions, and outcomes to restore effective learning. By this definition, current AI systems achieve agency but not intelligence. Inspired by thalamocortical regulation in biological systems, we demonstrate a feedback architecture that monitors P in real time, establishing a prerequisite for adaptive, resilient AI.

---

### SignVLA: A Gloss-Free Vision-Language-Action Framework for Real-Time Sign Language-Guided Robotic Manipulation

Authors: Xinyu Tan, Ningwei Bai, Harry Gardener, Zhengyang Zhong, Luoyu Zhang, Liuhaichen Yang, Zhekai Duan, Monkgogi Galeitsiwe, Zezhi Tang
Published: 2026-02-26
Categories: cs.RO, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2602.22514v1

We present, to our knowledge, the first sign language-driven Vision-Language-Action (VLA) framework for intuitive and inclusive human-robot interaction. Unlike conventional approaches that rely on gloss annotations as intermediate supervision, the proposed system adopts a gloss-free paradigm and directly maps visual sign gestures to semantic instructions. This design reduces annotation cost and avoids the information loss introduced by gloss representations, enabling more natural and scalable multimodal interaction. In this work, we focus on a real-time alphabet-level finger-spelling interface that provides a robust and low-latency communication channel for robotic control. Compared with large-scale continuous sign language recognition, alphabet-level interaction offers improved reliability, interpretability, and deployment feasibility in safety-critical embodied environments. The proposed pipeline transforms continuous gesture streams into coherent language commands through geometric normalization, temporal smoothing, and lexical refinement, ensuring stable and consistent interaction. Furthermore, the framework is designed to support future integration of transformer-based gloss-free sign language models, enabling scalable word-level and sentence-level semantic understanding. Experimental results demonstrate the effectiveness of the proposed system in grounding sign-derived instructions into precise robotic actions under diverse interaction scenarios. These results highlight the potential of the framework to advance accessible, scalable, and multimodal embodied intelligence.

---

### Pix2Key: Controllable Open-Vocabulary Retrieval with Semantic Decomposition and Self-Supervised Visual Dictionary Learning

Authors: Guoyizhe Wei, Yang Jiao, Nan Xi, Zhishen Huang, Jingjing Meng, Rama Chellappa, Yan Gao
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.22510v1

Composed Image Retrieval (CIR) uses a reference image plus a natural-language edit to retrieve images that apply the requested change while preserving other relevant visual content. Classic fusion pipelines typically rely on supervised triplets and can lose fine-grained cues, while recent zero-shot approaches often caption the reference image and merge the caption with the edit, which may miss implicit user intent and return repetitive results. We present Pix2Key, which represents both queries and candidates as open-vocabulary visual dictionaries, enabling intent-aware constraint matching and diversity-aware reranking in a unified embedding space. A self-supervised pretraining component, V-Dict-AE, further improves the dictionary representation using only images, strengthening fine-grained attribute understanding without CIR-specific supervision. On the DFMM-Compose benchmark, Pix2Key improves Recall@10 up to 3.2 points, and adding V-Dict-AE yields an additional 2.3-point gain while improving intent consistency and maintaining high list diversity.

---

### Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering

Authors: Ik-hwan Kim, Hyeongrok Han, Mingi Jung, Sangwon Yu, Jinseok Hong, Sang Hun Kim, Yoonyoung Choi, Sungroh Yoon
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.22508v2

Large Language Models (LLMs) often produce incorrect answers on multi-hop question answering even when the reasoning trace already contains a correct intermediate conclusion. We attribute this gap to weak self-regulation rather than insufficient reasoning capacity. Without explicit regulation, valid intermediate conclusions are overridden by continued exploration or left unrecognized as logically sufficient. We propose Metacognitive Behavioral Tuning (MBT), a post-training framework that injects a five-phase metacognitive structure into reasoning traces. The five phases are understanding and filtering, planning, execution and monitoring, self-correction, and verification. MBT has two formulations. MBT-S synthesizes new metacognitive traces from scratch, while MBT-R rewrites the student's own traces into a metacognitive form. Across HotpotQA, MuSiQue, and 2WikiMultiHopQA, MBT attains the highest Accuracy-Efficiency Score (AES) across model scales. MBT lifts task accuracy while keeping traces short and stable, with mean response length on MuSiQue an order of magnitude shorter than baseline methods and degeneration counts reduced by a similar margin. A matched-control study further confirms that the gain stems from the five-phase structural prior itself. To qualitatively assess the regulatory behavior of reasoning traces, we introduce two new metrics, the Reach-Redundancy Profile (RRP) and the length-aware Metacognitive Quality Index (MQI). RRP captures when the answer is reached and how much of the trace is redundant, and MQI quantifies how richly the five phases appear. Under both metrics, MBT achieves the earliest answer arrival, the lowest redundancy, and the richest phase-level behavior across model scales.

---

### Space Syntax-guided Post-training for Residential Floor Plan Generation

Authors: Zhuoyang Jiang, Dongqing Zhang
Published: 2026-02-26
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.22507v2

Residential floor plan generation requires not only geometric fidelity but also spatial configurational logic: shared living spaces should be integrative, while private spaces should remain segregated. Existing generators increasingly use room-relation graphs as input-side conditions, but generated layouts are rarely evaluated on the output side for configurational quality, and such evaluation is rarely fed back into model optimization. We propose Space Syntax-guided Post-training (SSPT), a framework that turns space-syntax integration from a post-hoc analysis tool into a computable feedback signal for already-trained floor plan generators. SSPT introduces the Space Syntax Integration Oracle (SSIO), which converts generated layouts into rectangle-space graphs and measures public-space dominance and functional hierarchy. SSIO is first applied to real residential data to establish empirical configurational references, then connected to two SSPT strategies: SSPT-Iter, a basic generate-filter-retrain route, and SSPT-PPO, the first RL-based post-training route for floor plan generation. We also introduce SSPT-Bench, a new evaluation system for measuring the output-side spatial configurational quality of post-trained generators under an out-of-distribution setting. Experiments show that both strategies improve public-space dominance and functional-hierarchy alignment over the unpost-trained baseline. SSPT-PPO achieves stronger gains, lower variance, and higher efficiency than iterative retraining. These results show that output-side configurational evaluation can serve as actionable post-training feedback, offering a practical path for injecting architectural theory into existing floor plan generation backbones.

---

### Sharp Convergence Rates for Masked Diffusion Models

Authors: Yuchen Liang, Zhiheng Tan, Ness Shroff, Yingbin Liang
Published: 2026-02-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.22505v1

Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, with masked (absorbing-rate) variants emerging as competitive alternatives to autoregressive models. Among existing samplers, the Euler method remains the standard choice in many applications, and more recently, the First-Hitting Sampler (FHS) has shown considerable promise for masked diffusion models. Despite their practical success, the theoretical understanding of these samplers remains limited. Existing analyses are conducted in Kullback-Leibler (KL) divergence, which often yields loose parameter dependencies and requires strong assumptions on score estimation. Moreover, these guarantees do not cover recently developed high-performance sampler of FHS. In this work, we first develop a direct total-variation (TV) based analysis for the Euler method that overcomes these limitations. Our results relax assumptions on score estimation, improve parameter dependencies, and establish convergence guarantees without requiring any surrogate initialization. Also for this setting, we provide the first convergence lower bound for the Euler sampler, establishing tightness with respect to both the data dimension $d$ and the target accuracy $\varepsilon$. Finally, we analyze the FHS sampler and show that it incurs no sampling error beyond that induced by score estimation, which we show to be tight with a matching lower error bound. Overall, our analysis introduces a direct TV-based error decomposition along the CTMC trajectory and a decoupling-based path-wise analysis for FHS, which may be of independent interest.

---

### Mapping the Landscape of Artificial Intelligence in Life Cycle Assessment Using Large Language Models

Authors: Anastasija Mensikova, Donna M. Rizzo, Kathryn Hinkelman
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.22500v1

Integration of artificial intelligence (AI) into life cycle assessment (LCA) has accelerated in recent years, with numerous studies successfully adapting machine learning algorithms to support various stages of LCA. Despite this rapid development, comprehensive and broad synthesis of AI-LCA research remains limited. To address this gap, this study presents a detailed review of published work at the intersection of AI and LCA, leveraging large language models (LLMs) to identify current trends, emerging themes, and future directions. Our analyses reveal that as LCA research continues to expand, the adoption of AI technologies has grown dramatically, with a noticeable shift toward LLM-driven approaches, continued increases in ML applications, and statistically significant correlations between AI approaches and corresponding LCA stages. By integrating LLM-based text-mining methods with traditional literature review techniques, this study introduces a dynamic and effective framework capable of capturing both high-level research trends and nuanced conceptual patterns (themes) across the field. Collectively, these findings demonstrate the potential of LLM-assisted methodologies to support large-scale, reproducible reviews across broad research domains, while also evaluating pathways for computationally-efficient LCA in the context of rapidly developing AI technologies. In doing so, this work helps LCA practitioners incorporate state-of-the-art tools and timely insights into environmental assessments that can enhance the rigor and quality of sustainability-driven decisions and decision-making processes.

---

### Reinforcement-aware Knowledge Distillation for LLM Reasoning

Authors: Zhaoyang Zhang, Shuli Jiang, Yantao Shen, Yuting Zhang, Dhananjay Ram, Shuo Yang, Zhuowen Tu, Wei Xia, Stefano Soatto
Published: 2026-02-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.22495v3

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most existing knowledge distillation (KD) methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization. When combined with RL, these approaches often suffer from distribution mismatch and objective interference: teacher supervision may not align with the student's evolving rollout distribution, and the KL regularizer can compete with reward maximization and require careful loss balancing. To address these issues, we propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update. Our core component, Trust Region Ratio Distillation (TRRD), replaces the teacher-student KL regularizer with a PPO/GRPO-style likelihood-ratio objective anchored to a teacher--old-policy mixture, yielding advantage-aware, trust-region-bounded distillation on student rollouts and naturally balancing exploration, exploitation, and imitation. Across diverse logic reasoning and math benchmarks, RLAD consistently outperforms offline distillation, standard GRPO, and KL-based on-policy teacher-student knowledge distillation.

---

### From Shallow Bayesian Neural Networks to Gaussian Processes: General Convergence, Identifiability and Scalable Inference

Authors: Gracielle Antunes de Araújo, Flávio B. Gonçalves
Published: 2026-02-26
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.22492v1

In this work, we study scaling limits of shallow Bayesian neural networks (BNNs) via their connection to Gaussian processes (GPs), with an emphasis on statistical modeling, identifiability, and scalable inference. We first establish a general convergence result from BNNs to GPs by relaxing assumptions used in prior formulations, and we compare alternative parameterizations of the limiting GP model. Building on this theory, we propose a new covariance function defined as a convex mixture of components induced by four widely used activation functions, and we characterize key properties including positive definiteness and both strict and practical identifiability under different input designs. For computation, we develop a scalable maximum a posterior (MAP) training and prediction procedure using a Nyström approximation, and we show how the Nyström rank and anchor selection control the cost-accuracy trade-off. Experiments on controlled simulations and real-world tabular datasets demonstrate stable hyperparameter estimates and competitive predictive performance at realistic computational cost.

---

### Factorizing formal contexts from closures of necessity operators

Authors: Roberto G. Aragón, Jesús Medina, Eloísa Ramírez-Poussa
Published: 2026-02-25
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2604.09582v1

Factorizing datasets is an interesting process in a multitude of approaches, but many times it is not possible or efficient the computation of a factorization of the dataset. A method to obtain independent subcontexts of a formal context with Boolean data was proposed in~\cite{dubois:2012}, based on the operators used in possibility theory. In this paper, we will analyze this method and study different properties related to the pairs of sets from which a factorization of a formal context arises. We also inspect how the properties given in the classical case can be extended to the fuzzy framework, which is essential to obtain a mechanism that allows the computation of independent subcontexts of a fuzzy context.

---

### Avenir-UX: Automated UX Evaluation via Simulated Human Web Interaction with GUI Grounding

Authors: Wee Joe Tan, Zi Rui Lucas Lim, Shashank Durgad, Karim Obegi, Aiden Yiliu Li
Published: 2026-02-25
Categories: cs.AI, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2604.09581v2

Evaluating web usability typically requires time-consuming user studies and expert reviews, which often limits iteration speed during product development, especially for small teams and agile workflows. We present Avenir-UX, a user-experience evaluation agent that simulates user behavior on websites and produces standardized usability. Unlike traditional tools that rely on DOM parsing, Avenir-UX grounds actions and observations, enabling it to interact with real web pages end-to-end while maintaining a coherent trace of the user journey. Building on Avenir-Web, our system pairs this robust interaction with simulated user behavior profiles and a structured evaluation protocol that integrates the System Usability Scale (SUS), step-wise Single Ease Questions (SEQ), and concurrent Think Aloud. Subsequently, a comprehensive User Experience (UX) report will be generated. We discuss the architecture of Avenir-UX and illustrate how its multimodal grounding improves robustness for web-based interaction and UX evaluation scenarios, paving the way for a new era of continuous, scalable, and data-driven usability testing that empowers every developer to build web interfaces that are usable. Code is available at: https://github.com/Onflow-AI/Avenir-UX

---

### OOWM: Structuring Embodied Reasoning and Planning via Object-Oriented Programmatic World Modeling

Authors: Hongyu Chen, Liang Lin, Guangrun Wang
Published: 2026-02-25
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.09580v1

Standard Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs) with reasoning capabilities, yet its reliance on linear natural language is inherently insufficient for effective world modeling in embodied tasks. While text offers flexibility, it fails to explicitly represent the state-space, object hierarchies, and causal dependencies required for robust robotic planning. To address these limitations, we propose Object-Oriented World Modeling (OOWM), a novel framework that structures embodied reasoning through the lens of software engineering formalisms. We redefine the world model not as a latent vector space, but as an explicit symbolic tuple $W = \langle S, T \rangle$: a State Abstraction ($G_\text{state}$) instantiating the environmental state $S$, coupled with a Control Policy ($G_\text{control}$) representing the transition logic $T: S \times A \rightarrow S'$. OOWM leverages the Unified Modeling Language (UML) to materialize this definition: it employs Class Diagrams to ground visual perception into rigorous object hierarchies, and Activity Diagrams to operationalize planning into executable control flows. Furthermore, we introduce a three-stage training pipeline combining Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO). Crucially, this method utilizes outcome-based rewards from the final plan to implicitly optimize the underlying object-oriented reasoning structure, enabling effective learning even with sparse annotations. Extensive evaluations on the MRoom-30k benchmark demonstrate that OOWM significantly outperforms unstructured textual baselines in planning coherence, execution success, and structural fidelity, establishing a new paradigm for structured embodied reasoning.

---

### Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement

Authors: Fengrui Liu, Xiao He, Tieying Zhang
Published: 2026-02-25
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2604.09579v1

In large-scale cloud service platforms, thousands of customer tickets are generated daily and are typically handled through on-call dialogues. This high volume of on-call interactions imposes a substantial workload on human support analysts. Recent studies have explored reactive agents that leverage large language models as a first line of support to interact with customers directly and resolve issues. However, when issues remain unresolved and are escalated to human support, these agents are typically disengaged. As a result, they cannot assist with follow-up inquiries, track resolution progress, or learn from the cases they fail to address. In this paper, we introduce Vigil, a novel proactive agent system designed to operate throughout the entire on-call life-cycle. Unlike reactive agents, Vigil focuses on providing assistance during the phase in which human support is already involved. It integrates into the dialogue between the customer and the analyst, proactively offering assistance without explicit user invocation. Moreover, Vigil incorporates a continuous self-improvement mechanism that extracts knowledge from human-resolved cases to autonomously update its capabilities. Vigil has been deployed on Volcano Engine, ByteDance's cloud platform, for over ten months, and comprehensive evaluations based on this deployment demonstrate its effectiveness and practicality. The open source version of this work is publicly available at https://github.com/volcengine/veaiops.

---

### ShobdoSetu: A Data-Centric Framework for Bengali Long-Form Speech Recognition and Speaker Diarization

Authors: Md. Nazmus Sakib, Shafiul Tanvir, Mesbah Uddin Ahamed, H. M. Aktaruzzaman Mukdho
Published: 2026-02-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19256v1

Bengali is spoken by over 230 million people yet remains severely under-served in automatic speech recognition (ASR) and speaker diarization research. In this paper, we present our system for the DL Sprint 4.0 Bengali Long-Form Speech Recognition (Task~1) and Bengali Speaker Diarization Challenge (Task~2). For Task~1, we propose a data-centric pipeline that constructs a high-quality training corpus from Bengali YouTube audiobooks and dramas \cite{tabib2026bengaliloop}, incorporating LLM-assisted language normalization, fuzzy-matching-based chunk boundary validation, and muffled-zone augmentation. Fine-tuning the \texttt{tugstugi/whisper-medium} model on approximately 21,000 data points with beam size 5, we achieve a Word Error Rate (WER) of 16.751 on the public leaderboard and 15.551 on the private test set. For Task~2, we fine-tune the pyannote.audio community-1 segmentation model with targeted hyperparameter optimization under an extreme low-resource setting (10 training files), achieving a Diarization Error Rate (DER) of 0.19974 on the public leaderboard, and .26723 on the private test set. Our results demonstrate that careful data engineering and domain-adaptive fine-tuning can yield competitive performance for Bengali speech processing even without large annotated corpora.

---

### LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models

Authors: Wei Zhang, Lintong Du, Yuanhe Zhang, Zhenhong Zhou, Kun Wang, Li Sun, Sen Su
Published: 2026-02-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.19255v1

Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing methods primarily attempt to enforce length constraints by externally imposing length signals or optimization objectives, while largely overlooking the underlying limitation: the model's intrinsic deficit in length cognition. To address this, we propose LARFT (Length-Aware Reinforcement Fine-Tuning), a training framework that aligns the model's length cognition with its action. Specifically, LARFT integrates length-oriented reinforcement learning with a hindsight length awareness. By transforming on-policy data into hindsight self-awareness tasks where the model learns to identify the actual length of its own generation, LARFT jointly optimizes the model's internal representation of length information and refines its policy to satisfy length constraints, thereby achieving precise and reliable length instruction following. Extensive experiments across four base models demonstrate that LARFT outperforms existing baselines, achieving an average improvement of +20.92 points across three length instruction following benchmarks with only a marginal decline of -1.45 points on four general capability benchmarks.

---

### FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting

Authors: Yiyun Zhu, Yidong Jiang, Ziwen Xu, Yinsheng Yao, Dawei Cheng, Jinru Ding, Jie Xu
Published: 2026-02-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19254v2

Large language models (LLMs) are increasingly deployed in financial research workflows, where their role is evolving from single-model assistance for human analysts toward autonomous collaboration among multiple agents. Yet real-world deployments still expose factual errors, numerical inconsistencies, and shallow analysis, which can distort assessments of corporate fundamentals and trigger severe economic losses. While existing benchmarks have begun to evaluate such failures, they score all aspects of the generated analysis in one pass, failing to distinguish whether a model fails at foundational stages like auditing and correction, or underperforms at generating research-grade insights. Consequently, it obscures capability bottlenecks and the specialized strengths essential for multi-agent role assignment. To address these gaps, we introduce FinReasoning, a hierarchical benchmark that decomposes the core capabilities of financial research into semantic consistency, data alignment, and deep insight. We further propose a fine-grained evaluation framework that strengthens hallucination-correction assessment and incorporates a 12-indicator rubric for core analytical skills. FinReasoning reveals clear capability stratification across model types. Closed-source models (like Doubao-Seed-1.8) perform strongly overall and are better suited for core reasoning agents in multi-agent financial systems; open-source general models (like Qwen3-235B) show clear capability divergence and consistently underperform on Semantic Consistency, making them less suited for quality-sensitive generation tasks; financial-domain models (like Fin-R1) generate moderate insights but lack foundational auditing skills. Our work has already been deployed in pilot tests across several real-world scenarios. The resource is available at https://github.com/TongjiFinLab/FinReasoning.

---

### A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2

Authors: Marcin Pietroń, Filip Gampel, Jakub Gomułka, Andrzej Tomski, Rafał Olszowski
Published: 2026-02-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.19253v1

Argument mining (AM) is an interdisciplinary research field focused on the automatic identification and classification of argumentative components, such as claims and premises, and the relationships between them. Recent advances in large language models (LLMs) have significantly improved the performance of argument classification compared to traditional machine learning approaches. This study presents a comprehensive evaluation of several state-of-the-art LLMs, including GPT-5.2, Llama 4, and DeepSeek, on large publicly available argument classification corpora such as Args.me and UKP. The evaluation incorporates advanced prompting strategies, including Chain-of- Thought prompting, prompt rephrasing, voting, and certainty-based classification. Both quantitative performance metrics and qualitative error analysis are conducted to assess model behavior. The best-performing model in the study (GPT-5.2) achieves a classification accuracy of 78.0% (UKP) and 91.9% (Args.me). The use of prompt rephrasing, multi-prompt voting, and certainty estimation further improves classification performance and robustness. These techniques increase the accuracy and F1 metric of the models by typically a few percentage points (from 2% to 8%). However, qualitative analysis reveals systematic failure modes shared across models, including instabilities with respect to prompt formulation, difficulties in detecting implicit criticism, interpreting complex argument structures, and aligning arguments with specific claims. This work contributes the first comprehensive evaluation that combines quantitative benchmarking and qualitative error analysis on multiple argument mining datasets using advanced LLM prompting strategies.

---

### GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagrams

Authors: Yushun Zhang, Weiping Fu, Zesheng Yang, Bo Zhao, Lingling Zhang, Jian Zhang, Yumeng Fu, Jiaxing Huang, Jun Liu
Published: 2026-02-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.19252v1

Evaluating the symbolic reasoning of large language models (LLMs) calls for geometry benchmarks that require multi-step proofs grounded in both text and diagrams. However, existing benchmarks are often limited in scale and rarely provide visually grounded multiple-choice questions, limiting reliable evaluation of complex reasoning. We introduce GeoChallenge, a dataset of 90K automatically generated multiple-choice geometry proof problems, each requiring multi-step reasoning over aligned textual descriptions and diagrams. GeoChallenge provides fine-grained complexity ratings and formal language annotations to enable controlled evaluation. Experiments on multiple advanced LLMs show a clear performance gap between models and humans (the best-performing model, GPT-5-nano, achieves 75.89 exact match vs. 94.74 for humans). Further analysis also reveals three common failure patterns of LLMs: (1) exact match failures under the multiple-choice setting; (2) weak visual reliance; and (3) overextended reasoning without convergence.

---

### Enhancing Legal LLMs through Metadata-Enriched RAG Pipelines and Direct Preference Optimization

Authors: Suyash Maniyar, Deepali Singh, Rohith Reddy
Published: 2026-02-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19251v1

Large Language Models (LLMs) perform well in short contexts but degrade on long legal documents, often producing hallucinations such as incorrect clauses or precedents. In the legal domain, where precision is critical, such errors undermine reliability and trust. Retrieval Augmented Generation (RAG) helps ground outputs but remains limited in legal settings, especially with small, locally deployed models required for data privacy. We identify two failure modes: retrieval errors due to lexical redundancy in legal corpora, and decoding errors where models generate answers despite insufficient context. To address this, we propose Metadata Enriched Hybrid RAG to improve document level retrieval, and apply Direct Preference Optimization (DPO) to enforce safe refusal when context is inadequate. Together, these methods improve grounding, reliability, and safety in legal language models.

---

### Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams

Authors: Yukyung Lee, Yebin Lim, Woojun Jung, Wonjun Choi, Susik Yoon
Published: 2026-02-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19250v2

Evaluating language models in streaming environments is critical, yet underexplored. Existing benchmarks either focus on single complex events or provide curated inputs for each query, and do not evaluate models under the conflicts that arise when multiple concurrent events are mixed within the same document stream. We introduce StreamBench, a benchmark built from major news stories in 2016 and 2025, comprising 605 events and 15,354 documents across three tasks: Topic Clustering, Temporal Question Answering, and Summarization. To diagnose how models fail, we compare performance with and without structural cues, which organize key facts by event. We find that structural cues improve performance on clustering (up to +4.37%) and temporal QA (up to +9.63%), helping models locate relevant information and separate distinct events. While temporal reasoning remains an open challenge inherent to current LLMs, consistent gains across tasks show that structural cues are a promising direction for future work in massive document streams.

---

### Spelling Correction in Healthcare Query-Answer Systems: Methods, Retrieval Impact, and Empirical Evaluation

Authors: Saurabh K Singh
Published: 2026-02-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19249v1

Healthcare question-answering (QA) systems face a persistent challenge: users submit queries with spelling errors at rates substantially higher than those found in the professional documents they search. This paper presents the first controlled study of spelling correction as a retrieval preprocessing step in healthcare QA using real consumer queries. We conduct an error census across two public datasets -- the TREC 2017 LiveQA Medical track (104 consumer health questions) and HealthSearchQA (4,436 health queries from Google autocomplete) -- finding that 61.5% of real medical queries contain at least one spelling error, with a token-level error rate of 11.0%. We evaluate four correction methods -- conservative edit distance, standard edit distance (Levenshtein), context-aware candidate ranking, and SymSpell -- across three experimental conditions: uncorrected queries against an uncorrected corpus (baseline), uncorrected queries against a corrected corpus, and fully corrected queries against a corrected corpus. Using BM25 and TF-IDF cosine retrieval over 1,935 MedQuAD answer passages with TREC relevance judgments, we find that query correction substantially improves retrieval -- edit distance and context-aware correction achieve MRR improvements of +9.2% and NDCG@10 improvements of +8.3% over the uncorrected baseline. Critically, correcting only the corpus without correcting queries yields minimal improvement (+0.5% MRR), confirming that query-side correction is the key intervention. We complement these results with a 100-sample error analysis categorising correction outcomes per method and provide evidence-based recommendations for practitioners.

---

### DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution

Authors: Xin Shen, Zhishu Jiang, Jiaye Yang, Haibo Liu, Yichen Wan, Jiarui Zhang, Tingzhi Dai, Luodong Xu, Shuchen Wu, Guanqiang QI, Chenxi Miao, Jiahui Liang et al.
Published: 2026-02-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.19248v1

Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightweight turns, but requests involving planning and tool invocation (e.g., search and media generation) produce heavy-tail execution latency that degrades turn-taking, persona consistency, and user trust. To address this challenge, we propose DuCCAE (Conversation while Collaboration with Augmentation and Evolution), a hybrid engine for immersive conversation deployed within Baidu Search, serving millions of users. DuCCAE decouples real-time response generation from asynchronous agentic execution and synchronizes them via a shared state that maintains session context and execution traces, enabling asynchronous results to be integrated back into the ongoing dialogue. The system orchestrates five subsystems-Info, Conversation, Collaboration, Augmentation, and Evolution-to support multi-agent collaboration and continuous improvement. We evaluate DuCCAE through a comprehensive framework that combines offline benchmarking on the Du-Interact dataset and large-scale production evaluation within Baidu Search. Experimental results demonstrate that DuCCAE outperforms strong baselines in agentic execution reliability and dialogue quality while reducing latency to fit strict real-time budgets. Crucially, deployment metrics since June 2025 confirm substantial real-world effectiveness, evidenced by a tripling of Day-7 user retention to 34.2% and a surge in the complex task completion rate to 65.2%. Our hybrid architecture successfully preserves conversational continuity while enabling reliable agentic execution, offering practical guidelines for deploying scalable agentic systems in industrial settings.

---

### BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity

Authors: Harshita Diddee, Gregory Yauney, Swabha Swayamdipta, Daphne Ippolito
Published: 2026-02-25
Categories: cs.CL, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.18019v2

Do language model benchmarks actually measure what practitioners intend them to ? High-level metadata is too coarse to convey the granular reality of benchmarks: a "poetry" benchmark may never test for haikus, while "instruction-following" benchmarks will often test for an arbitrary mix of skills. This opacity makes verifying alignment with practitioner goals a laborious process, risking an illusion of competence even when models fail on untested facets of user interests. We introduce BenchBrowser, a retriever that surfaces evaluation items relevant to natural language use cases over 20 benchmark suites. Validated by a human study confirming high retrieval precision, BenchBrowser generates evidence to help practitioners diagnose low content validity (narrow coverage of a capability's facets) and low convergent validity (lack of stable rankings when measuring the same capability). BenchBrowser, thus, helps quantify a critical gap between practitioner intent and what benchmarks actually test.

---

### An Agentic System for Schema Aware NL2SQL Generation

Authors: David Onyango, Naseef Mansoor
Published: 2026-02-25
Categories: cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2603.18018v1

The natural language to SQL (NL2SQL) task plays a pivotal role in democratizing data access by enabling non-expert users to interact with relational databases through intuitive language. While recent frameworks have enhanced translation accuracy via task specialization, their reliance on Large Language Models (LLMs) raises significant concerns regarding computational overhead, data privacy, and real-world deployability in resource-constrained environments. To address these challenges, we propose a schema based agentic system that strategically employs Small Language Models (SLMs) as primary agents, complemented by a selective LLM fallback mechanism. The LLM is invoked only upon detection of errors in SLM-generated output, the proposed system significantly minimizes computational expenditure. Experimental results on the BIRD benchmark demonstrate that our system achieves an execution accuracy of 47.78% and a validation efficiency score of 51.05%, achieving over 90% cost reduction compared to LLM-centric baselines as approximately 67% of queries are resolved using local SLMs. The system achieves an average cost per query of 0.0085 compared to 0.094 for LLM-only systems, achieving near-zero operational costs for locally executed queries. (Github repository: https://github.com/mindslab25/CESMA.)

---

### DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting

Authors: Mehran Shabanpour, Sadaf Khademi, Konstantinos N Plataniotis, Arash Mohammadi
Published: 2026-02-25
Categories: eess.SP, cs.CL, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2603.16885v1

Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural dynamics and the semantic context of behavioral tasks. We present the Dual-Enhanced COnditioned Diffusion (DECODE) for EEG, a novel framework that unifies semantic guidance from natural language descriptions with temporal dynamics from historical signals to generate event-specific neural responses. DECODE leverages pre-trained language models to condition the diffusion process on rich textual descriptions of cognitive events, while maintaining temporal coherence through history-based Langevin dynamics. Evaluated on a real-world driving task dataset with five distinct behaviors, DECODE achieves sub-microvolt prediction accuracy (MAE = 0.626 microvolt) over 75 timestep horizons while maintaining well-calibrated uncertainty estimates. Our framework demonstrates that natural language can effectively bridge high-level cognitive descriptions and low-level neural dynamics, opening new possibilities for zero-shot generalization to novel behaviors and interpretable BCIs. By generating physiologically plausible, event-specific EEG trajectories conditioned on semantic descriptions, DECODE establishes a new paradigm for understanding and predicting context-dependent neural activity.

---

### Tokenization vs. Augmentation: A Systematic Study of Writer Variance in IMU-Based Online Handwriting Recognition

Authors: Jindong Li, Dario Zanca, Vincent Christlein, Tim Hamann, Jens Barth, Peter Kämpf, Björn Eskofier
Published: 2026-02-25
Categories: cs.CV, cs.CL, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2603.16883v2

Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability. In this work, we systematically investigate two strategies to address these issues: subword tokenization and concatenation-based data augmentation. Our experiments on the OnHW-Words500 dataset reveal a clear dichotomy between handling inter-writer and intra-writer variance. On the writer-independent split, structural abstraction via Bigram tokenization significantly improves generalization to unseen writing styles, reducing the word error rate (WER) from 15.40% to 12.99%. In contrast, on the writer-dependent split, tokenization degrades performance due to vocabulary distribution shifts between the training and validation sets. Instead, our proposed concatenation-based data augmentation acts as a powerful regularizer, reducing the character error rate by 34.5% and the WER by 25.4%. Further analysis shows that short, low-level tokens benefit model performance and that the performance gains from concatenation-based data augmentation surpass those achieved by proportionally extended training. These findings reveal a clear variance-dependent effect: subword tokenization primarily mitigates inter-writer stylistic variability, whereas concatenation-based data augmentation effectively compensates for intra-writer distributional sparsity.

---

### Neural-Symbolic Logic Query Answering in Non-Euclidean Space

Authors: Lihui Liu
Published: 2026-02-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.15633v1

Answering complex first-order logic (FOL) queries on knowledge graphs is essential for reasoning. Symbolic methods offer interpretability but struggle with incomplete graphs, while neural approaches generalize better but lack transparency. Neural-symbolic models aim to integrate both strengths but often fail to capture the hierarchical structure of logical queries, limiting their effectiveness. We propose HYQNET, a neural-symbolic model for logic query reasoning that fully leverages hyperbolic space. HYQNET decomposes FOL queries into relation projections and logical operations over fuzzy sets, enhancing interpretability. To address missing links, it employs a hyperbolic GNN-based approach for knowledge graph completion in hyperbolic space, effectively embedding the recursive query tree while preserving structural dependencies. By utilizing hyperbolic representations, HYQNET captures the hierarchical nature of logical projection reasoning more effectively than Euclidean-based approaches. Experiments on three benchmark datasets demonstrate that HYQNET achieves strong performance, highlighting the advantages of reasoning in hyperbolic space.

---

### Multi-hop Reasoning and Retrieval in Embedding Space: Leveraging Large Language Models with Knowledge

Authors: Lihui Liu
Published: 2026-02-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.13266v1

As large language models (LLMs) continue to grow in size, their abilities to tackle complex tasks have significantly improved. However, issues such as hallucination and the lack of up-to-date knowledge largely remain unresolved. Knowledge graphs (KGs), which serve as symbolic representations of real-world knowledge, offer a reliable source for enhancing reasoning. Integrating KG retrieval into LLMs can therefore strengthen their reasoning by providing dependable knowledge. Nevertheless, due to limited understanding of the underlying knowledge graph, LLMs may struggle with queries that have multiple interpretations. Additionally, the incompleteness and noise within knowledge graphs may result in retrieval failures. To address these challenges, we propose an embedding-based retrieval reasoning framework EMBRAG. In this approach, the model first generates multiple logical rules grounded in knowledge graphs based on the input query. These rules are then applied to reasoning in the embedding space, guided by the knowledge graph, ensuring more robust and accurate reasoning. A reranker model further interprets these rules and refines the results. Extensive experiments on two benchmark KGQA datasets demonstrate that our approach achieves the new state-of-the-art performance in KG reasoning tasks.

---

### Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPA

Authors: Yongchao Huang, Hassan Raza
Published: 2026-02-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.13265v1

Modern self-supervised predictive architectures excel at capturing complex statistical correlations from high-dimensional data but lack mechanisms to internalize verifiable human logic, leaving them susceptible to spurious correlations and shortcut learning. Conversely, traditional rule-based inference systems offer rigorous, interpretable logic but suffer from discrete boundaries and NP-hard combinatorial explosion. To bridge this divide, we propose a bidirectional neuro-symbolic framework centered around Rule-informed Joint-Embedding Predictive Architectures (RiJEPA). In the first direction, we inject structured inductive biases into JEPA training via Energy-Based Constraints (EBC) and a multi-modal dual-encoder architecture. This fundamentally reshapes the representation manifold, replacing arbitrary statistical correlations with geometrically sound logical basins. In the second direction, we demonstrate that by relaxing rigid, discrete symbolic rules into a continuous, differentiable logic, we can bypass traditional combinatorial search for new rule generation. By leveraging gradient-guided Langevin diffusion within the rule energy landscape, we introduce novel paradigms for continuous rule discovery, which enable unconditional joint generation, conditional forward and abductive inference, and marginal predictive translation. Empirical evaluations on both synthetic topological simulations and a high-stakes clinical use case confirm the efficacy of our approach. Ultimately, this framework establishes a powerful foundation for robust, generative, and interpretable neuro-symbolic representation learning.

---

### Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations

Authors: Fernando Spadea, Oshani Seneviratne
Published: 2026-02-25
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2603.13264v1

Personalized recommendation increasingly relies on private user data, motivating approaches that can adapt to individuals without centralizing their information. We present Federated Targeted Recommendations with Evolving Knowledge graphs and Language Models (FedTREK-LM), a framework that unifies lightweight large language models (LLMs), evolving personal knowledge graphs (PKGs), federated learning (FL), and Kahneman-Tversky Optimization to enable scalable, decentralized personalization. By prompting LLMs with structured PKGs, FedTREK-LM performs context-aware reasoning for personalized recommendation tasks such as movie and recipe suggestions. Across three lightweight Qwen3 models (0.6B, 1.7B, 4B), FedTREK-LM consistently and substantially outperforms state-of-the-art KG completion and federated recommendation baselines (HAKE, KBGAT, and FedKGRec), achieving more than a 4x improvement in F1-score on the movie and food benchmarks. Our results further show that real user data is critical for effective personalization, as synthetic data degrades performance by up to 46%. Overall, FedTREK-LM offers a practical paradigm for adaptive, LLM-powered personalization that generalizes across decentralized, evolving user PKGs.

---

### Beyond Attention: True Adaptive World Models via Spherical Kernel Operator

Authors: Vladimer Khasia
Published: 2026-02-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.13263v1

The pursuit of world model based artificial intelligence has predominantly relied on projecting high-dimensional observations into parameterized latent spaces, wherein transition dynamics are subsequently learned. However, this conventional paradigm is mathematically flawed: it merely displaces the manifold learning problem into the latent space. When the underlying data distribution shifts, the latent manifold shifts accordingly, forcing the predictive operator to implicitly relearn the new topological structure. Furthermore, by classical approximation theory, positive operators like dot product attention inevitably suffer from the saturation phenomenon, permanently bottlenecking their predictive capacity and leaving them vulnerable to the curse of dimensionality. In this paper, we formulate a mathematically rigorous paradigm for world model construction by redefining the core predictive mechanism. Inspired by Ryan O'Dowd's foundational work we introduce Spherical Kernel Operator (SKO), a framework that replaces standard attention. By projecting the unknown data manifold onto a unified ambient hypersphere and utilizing a localized sequence of ultraspherical (Gegenbauer) polynomials, SKO performs direct integral reconstruction of the target function. Because this localized spherical polynomial kernel is not strictly positive, it bypasses the saturation phenomenon, yielding approximation error bounds that depend strictly on the intrinsic manifold dimension q, rather than the ambient dimension. Furthermore, by formalizing its unnormalized output as an authentic measure support estimator, SKO mathematically decouples the true environmental transition dynamics from the biased observation frequency of the agent. Empirical evaluations confirm that SKO significantly accelerates convergence and outperforms standard attention baselines in autoregressive language modeling.

---

### Evaluation of Audio Language Models for Fairness, Safety, and Security

Authors: Ranya Aloufi, Srishti Gupta, Soumya Shaw, Battista Biggio, Lea Schönherr
Published: 2026-02-25
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2603.13262v1

Audio large language models (ALLMs) have recently advanced spoken interaction by integrating speech processing with large language models. However, existing evaluations of fairness, safety, and security (FSS) remain fragmented, largely because ALLMs differ fundamentally in how acoustic information is represented and where semantic reasoning occurs. Differences that are rarely made explicit. As a result, evaluations often conflate structurally distinct systems, obscuring the relationship between model design and observed FSS behavior. In this work, we introduce a structural taxonomy (system-level and representational) of ALLMs that categorizes systems along two axes: the form of audio input representation (e.g., discrete vs. continuous) and the locus of semantic reasoning (e.g., cascaded, multimodal, or audio-native). Building on the taxonomy, we propose a unified evaluation framework that assesses semantic invariance under paralinguistic variation, refusal and toxicity behavior under unsafe prompts, and robustness to adversarial audio perturbations. We apply this framework to two representative systems and observe systematic differences in refusal rates, attack success, and toxicity between audio and text inputs. Our findings demonstrate that FSS behavior is tightly coupled to how acoustic information is integrated into semantic reasoning, underscoring the need for structure-aware evaluation of audio language models.

---

### Deep Convolutional Architectures for EEG Classification: A Comparative Study with Temporal Augmentation and Confidence-Based Voting

Authors: Aryan Patodiya, Hubert Cecotti
Published: 2026-02-25
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.13261v1

Electroencephalography (EEG) classification plays a key role in brain-computer interface (BCI) systems, yet it remains challenging due to the low signal-to-noise ratio, temporal variability of neural responses, and limited data availability. In this paper, we present a comparative study of deep learning architectures for classifying event-related potentials (ERPs) in EEG signals. The preprocessing pipeline includes bandpass filtering, spatial filtering, and normalization. We design and compare three main pipelines: a 2D convolutional neural network (CNN) using Common Spatial Pattern (CSP), a second 2D CNN trained directly on raw data for a fair comparison, and a 3D CNN that jointly models spatiotemporal representations. To address ERP latency variations, we introduce a temporal shift augmentation strategy during training. At inference time, we employ a confidence-based test-time voting mechanism to improve prediction stability across shifted trials. An experimental evaluation on a stratified five-fold cross-validation protocol demonstrates that while CSP provides a benefit to the 2D architecture, the proposed 3D CNN significantly outperforms both 2D variants in terms of AUC and balanced accuracy. These findings highlight the effectiveness of temporal-aware architectures and augmentation strategies for robust EEG signal classification.

---

### Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation

Authors: Minsang Kim, Seung Jun Baek
Published: 2026-02-25
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.13260v1

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's distribution over the entire output. However, a student with limited capacity can be overwhelmed by such extensive supervision causing a distribution mismatch, especially in complex reasoning tasks. We propose Token-Selective Dual Knowledge Distillation (TSD-KD), a framework for student-centric distillation. TSD-KD focuses on distilling important tokens for reasoning and encourages the student to explain reasoning in its own words. TSD-KD combines indirect and direct distillation. Indirect distillation uses a weak form of feedback based on preference ranking. The student proposes candidate responses generated on its own; the teacher re-ranks those candidates as indirect feedback without enforcing its entire distribution. Direct distillation uses distribution matching; however, it selectively distills tokens based on the relative confidence between teacher and student. Finally, we add entropy regularization to maintain the student's confidence during distillation. Overall, our method provides the student with targeted and indirect feedback to support its own reasoning process and to facilitate self-improvement. The experiments show the state-of-the-art performance of TSD-KD on 10 challenging reasoning benchmarks, outperforming the baseline and runner-up in accuracy by up to 54.4\% and 40.3\%, respectively. Notably, a student trained by TSD-KD even outperformed its own teacher model in four cases by up to 20.3\%. The source code is available at https://github.com/kmswin1/TSD-KD.

---

### How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing

Authors: Javier Marín
Published: 2026-02-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.13259v3

When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two pathways through hidden-state space diverge: displacement vectors from the query-only representation keep near-equal magnitude but rotate apart, with angular separation growing through mid-depth before late layers resolve an asymmetric outcome. A logit-lens preference in the incorrect run falls far below the equal-probability prior (roughly 11.5x more mass on the incorrect token than the correct one). We read this pattern, rotational divergence then late-layer asymmetric commitment, as the geometric signature of the model externally appearing to reject a wrong continuation, while staying explicit that it is observational, not causal: the incorrect run could equally reflect the model conforming to the token it is forced to carry, which only a random-token control can settle. It holds across six decoder-only transformers spanning four architecture families (Llama, Mistral, Gemma, StableLM) from 1B to 13B parameters; a seventh (Qwen2 1.5B) is flat under our protocol, plausibly a tokenizer artefact, leaving an emergence threshold open. Linear probes recover the distinction at intermediate depth, and cross-domain transfer is structurally asymmetric, a financial-medical corridor transferring far better than transport pairs. Where single-layer activation patching is cleanly interpretable (LLaMA-2 13B, Mistral 7B) it yields no layer band of consistent recovery; a third model (StableLM-2 1.6B) recovers uniformly above the ceiling, which we diagnose as a code-path artefact and exclude. Under this scoped null the late-layer asymmetry is not localized to a single component, fitting a distributed-by-trajectory account rather than single-layer localized recall. We document this with forced-completion probing across seven models, three domains, and 300 queries.

---

### Your Code Agent Can Grow Alongside You with Structured Memory

Authors: Yi-Xuan Deng, Xiaoqin Liu, Yi Zhang, Guo-Wei Yang, Shuojin Yang
Published: 2026-02-25
Categories: cs.LG, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.13258v1

While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal evolution of projects, failing to leverage the "reasoning trajectories" implicit in past successful practices. This limitation results in rigid behavioral logic and a lack of autonomous adaptability, ultimately hindering their ability to tackle complex, repository-level problems. To bridge this static-dynamic mismatch, we propose MemCoder, a framework designed to enable continual human-AI co-evolution. MemCoder first structures historical human experience to distill latent intent-to-code mappings from past commits. It then employs a self-refinement mechanism driven by verification feedback to correct agent behavior in real-time. Crucially, an experience self-internalization mechanism is introduced to crystallize human-validated solutions into long-term knowledge, thereby supporting sustained evolution. Experimental results on SWE-bench Verified demonstrate that MemCoder not only achieves State-of-the-Art (SOTA) performance but also delivers a 9.4% improvement in resolved rate over the general foundation model DeepSeek-V3.2. These findings indicate that equipping agents with the capability to co-evolve with humans via project history and real-time feedback effectively unlocks the potential of general models in complex software engineering tasks.

---

### Speculative Decoding Scaling Laws (SDSL): Throughput Optimization Made Simple

Authors: Amirhossein Bozorgkhoo, Igor Molybog
Published: 2026-02-25
Categories: cs.CL, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2603.11053v1

Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can be costly. This study of spec- ulative decoding proposes a theory that ana- lytically connects the key hyperparameters of pre-trained LLMs to the throughput efficiency of a downstream SD-based inference system. The theory allows the prediction of throughput- optimal hyperparameters for the components of an inference system before their pre-training.

---

### Architectural Design and Performance Analysis of FPGA based AI Accelerators: A Comprehensive Review

Authors: Soumita Chatterjee, Sudip Ghosh, Tamal Ghosh, Hafizur Rahaman
Published: 2026-02-25
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2603.08740v1

Deep learning (DL) has emerged as a rapidly developing advanced technology, enabling the performance of complex tasks involving image recognition, natural language processing, and autonomous decision-making with high levels of accuracy. However, as these technologies evolve and strive to meet the growing demands of real-life applications, the complexity of DL models continues to increase. These models require processing of massive volumes of data, demanding substantial computational power and memory bandwidth. This gives rise to the critical need for hardware accelerators that can deliver both high performance and energy efficiency. Accelerator types include ASIC based solutions, GPU accelerators, and FPGA based implementations. The limitations of ASIC and GPU accelerators have led to FPGAs becoming one of the prominent solutions, offering distinct advantages for DL workloads. FPGAs provide a flexible and reconfigurable platform, allowing model specific customization while maintaining high efficiency. This article explores various hardware level optimizations for DL. These optimizations include techniques such as loop pipelining, parallelism, quantization, and various memory hierarchy enhancements. In addition, it provides an overview of state-of-the-art FPGA-based neural network accelerators. Through the study and analysis of these accelerators, several challenges have been identified, paving the way for future optimizations and innovations in the design of FPGA-based hardware accelerators.

---

### RECAP: Local Hebbian Prototype Learning as a Self-Organizing Readout for Reservoir Dynamics

Authors: Heng Zhang
Published: 2026-02-25
Categories: cs.NE, cs.AI, cs.CV, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2603.06639v1

Robust perception in brains is often attributed to high-dimensional population activity together with local plasticity mechanisms that reinforce recurring structure. In contrast, most modern image recognition systems are trained by error backpropagation and end-to-end gradient optimization, which are not naturally aligned with local computation and local plasticity. We introduce RECAP (Reservoir Computing with Hebbian Co-Activation Prototypes), a bio-inspired learning strategy for robust image classification that couples untrained reservoir dynamics with a self-organizing Hebbian prototype readout. RECAP discretizes time-averaged reservoir responses into activation levels, constructs a co-activation mask over reservoir unit pairs, and incrementally updates class-wise prototype matrices via a Hebbian-like potentiation-decay rule. Inference is performed by overlap-based prototype matching. The method avoids error backpropagation and is naturally compatible with online prototype updates. We illustrate the resulting robustness behavior on MNIST-C, where RECAP remains robust under diverse corruptions without exposure to corrupted training samples.

---

### HEARTS: Benchmarking LLM Reasoning on Health Time Series

Authors: Sirui Li, Shuhan Xiao, Mihir Joshi, Ahmed Metwally, Daniel McDuff, Wei Wang, Yuzhe Yang
Published: 2026-02-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.06638v3

The rise of large language models (LLMs) has shifted time series analysis from narrow analytics to general-purpose reasoning. Yet, existing benchmarks cover only a small set of health time series modalities and tasks, failing to reflect the diverse domains and extensive temporal dependencies inherent in real-world physiological modeling. To bridge these gaps, we introduce HEARTS (Health Reasoning over Time Series), a unified benchmark for evaluating hierarchical reasoning capabilities of LLMs over general health time series. HEARTS integrates 16 real-world datasets across 12 health domains and 20 signal modalities, and defines a comprehensive taxonomy of 110 tasks grouped into four core capabilities: Perception, Inference, Generation, and Deduction. Evaluating 16 state-of-the-art LLMs on more than 20K test samples reveals intriguing findings. First, LLMs substantially underperform specialized models, and their performance is only weakly related to general reasoning scores. Moreover, LLMs often rely on simple heuristics and struggle with multi-step temporal reasoning. Finally, performance declines with increasing temporal complexity, with similar failure modes within model families, indicating that scaling alone is insufficient. By making these gaps measurable, HEARTS provides a standardized testbed and living benchmark for developing next-generation LLM agents capable of reasoning over diverse health signals.

---

### HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval

Authors: Sungho Park, Joohyung Yun, Jongwuk Lee, Wook-Shin Han
Published: 2026-02-25
Categories: cs.DB, cs.CL, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2603.02248v1

Table-text retrieval aims to retrieve relevant tables and text to support open-domain question answering. Existing studies use either early or late fusion, but face limitations. Early fusion pre-aligns a table row with its associated passages, forming "stars," which often include irrelevant contexts and miss query-dependent relationships. Late fusion retrieves individual nodes, dynamically aligning them, but it risks missing relevant contexts. Both approaches also struggle with advanced reasoning tasks, such as column-wise aggregation and multi-hop reasoning. To address these issues, we propose HELIOS, which combines the strengths of both approaches. First, the edge-based bipartite subgraph retrieval identifies finer-grained edges between table segments and passages, effectively avoiding the inclusion of irrelevant contexts. Then, the query-relevant node expansion identifies the most promising nodes, dynamically retrieving relevant edges to grow the bipartite subgraph, minimizing the risk of missing important contexts. Lastly, the star-based LLM refinement performs logical inference at the star graph level rather than the bipartite subgraph, supporting advanced reasoning tasks. Experimental results show that HELIOS outperforms state-of-the-art models with a significant improvement up to 42.6\% and 39.9\% in recall and nDCG, respectively, on the OTT-QA benchmark.

---

### OnDA: On-device Channel Pruning for Efficient Personalized Keyword Spotting

Authors: Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari
Published: 2026-02-25
Categories: eess.AS, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2603.02247v1

Always-on keyword spotting (KWS) demands on-device adaptation to cope with user- and environment-specific distribution shifts under tight latency and energy budgets. This paper proposes, for the first time, coupling weight adaptation (i.e., on-device training) with architectural adaptation, in the form of online structured channel pruning, for personalized on-device KWS. Starting from a state-of-the-art self-learning personalized KWS pipeline, we compare data-agnostic and data-aware pruning criteria applied on in-field pseudo-labelled user data. On the HeySnips and HeySnapdragon datasets, we achieve up to 9.63x model-size compression with respect to unpruned baselines at iso-task performance, measured as the accuracy at 0.5 false alarms per hour. When deploying our adaptation pipeline on a Jetson Orin Nano embedded GPU, we achieve up to 1.52x/1.57x and 1.64x/1.77x latency and energy-consumption improvements during online training/inference compared to weights-only adaptation.

---

### DINOv3 Meets YOLO26 for Weed Detection in Vegetable Crops

Authors: Boyang Deng, Yuzhen Lu
Published: 2026-02-25
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00160v1

Developing robust models for precision vegetable weeding is currently constrained by the scarcity of large-scale, annotated weed-crop datasets. To address this limitation, this study proposes a foundational crop-weed detection model by integrating heterogeneous datasets and leveraging self-supervised learning. A total of 618,642 crop-weed images were initially collected and subsequently refined to 199,388 filtered images for fine-tuning a DINOv3 vision transformer (ViT-small) through a sequential curation strategy. The fine-tuned DINOv3 backbone was then integrated into YOLO26, serving either as a primary backbone or part of a dual-backbone architecture. A feature alignment loss was introduced in the dual backbone framework to enhance feature fusion with minimal computational overhead. Experimental results show that the proposed DINOv3-finetuned ViT-small-based YOLO26-large achieved up to a +5.4% mAP50 gain on in-domain images collected in the 2025 season. Moreover, it demonstrated strong cross-domain generalization with mAP50 improvements of +14.0% on the 2021-2023 season dataset and +11.9% on the 2024 season dataset, compared to the standard YOLO26-large. Although the DINOv3-YOLO26-large model has 45.6% more parameters and a 2.9x increase in inference latency, it maintains real-time performance at ~28.5 frames per second (fps). The curated dataset and software programs developed in this study will be made publicly available.

---

### FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation

Authors: Weiting Tan, Andy T. Liu, Ming Tu, Xinghua Qu, Philipp Koehn, Lu Lu
Published: 2026-02-25
Categories: cs.CV, cs.AI, cs.MM, cs.SD
arXiv: https://arxiv.org/abs/2603.00159v1

Generating realistic talking-head videos remains challenging due to persistent issues such as imperfect lip synchronization, unnatural motion, and evaluation metrics that correlate poorly with human perception. We propose FlowPortrait, a reinforcement-learning framework for audio-driven portrait animation built on a multimodal backbone for autoregressive audio-to-video generation. FlowPortrait introduces a human-aligned evaluation system based on Multimodal Large Language Models (MLLMs) to assess lip-sync accuracy, expressiveness, and motion quality. These signals are combined with perceptual and temporal consistency regularizers to form a stable composite reward, which is used to post-train the generator via Group Relative Policy Optimization (GRPO). Extensive experiments, including both automatic evaluations and human preference studies, demonstrate that FlowPortrait consistently produces higher-quality talking-head videos, highlighting the effectiveness of reinforcement learning for portrait animation.

---

### FujiView: Multimodal Late-Fusion for Predicting Scenic Visibility

Authors: Bryceton Bible, Shah Md Nehal Hasnaeen, Hairong Qi
Published: 2026-02-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00157v1

Visibility of natural landmarks such as Mount Fuji is a defining factor in both tourism planning and visitor experience, yet it remains difficult to predict due to rapidly changing atmospheric conditions. We present FujiView, a multimodal learning framework and dataset for predicting scenic visibility by fusing webcam imagery with structured meteorological data. Our late-fusion approach combines image-derived class probabilities with numerical weather features to classify visibility into five categories. The dataset currently comprises over 100,000 webcam images paired with concurrent and forecasted weather conditions from more than 40 cameras around Mount Fuji, and continues to expand; it will be released to support further research in environmental forecasting. Experiments show that YOLO-based vision features dominate short-term horizons such as "nowcasting" and "samedaycasting", while weather-driven forecasts increasingly take over as the primary predictive signal beyond $+1$d. Late fusion consistently yields the highest overall accuracy, achieving ACC of approx 0.89 for same-day prediction and up to 84% for next-day forecasts. These results position Scenic Visibility Forecasting (SVF) as a new benchmark task for multimodal learning.

---

### BiCLIP: Bidirectional and Consistent Language-Image Processing for Robust Medical Image Segmentation

Authors: Saivan Talaei, Fatemeh Daneshfar, Abdulhady Abas Abdullah, Mourad Oussalah
Published: 2026-02-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00156v2

Medical image segmentation is a cornerstone of computer-assisted diagnosis and treatment planning. While recent multimodal vision-language models have shown promise in enhancing semantic understanding through textual descriptions, their resilience in "in-the-wild" clinical settings-characterized by scarce annotations and hardware-induced image degradations-remains under-explored. We introduce BiCLIP (Bidirectional and Consistent Language-Image Processing), a framework engineered to bolster robustness in medical segmentation. BiCLIP features a bidirectional multimodal fusion mechanism that enables visual features to iteratively refine textual representations, ensuring superior semantic alignment. To further stabilize learning, we implement an augmentation consistency objective that regularizes intermediate representations against perturbed input views. Evaluation on the QaTa-COV19 and MosMedData+ benchmarks demonstrates that BiCLIP consistently surpasses state-of-the-art image-only and multimodal baselines. Notably, BiCLIP maintains high performance when trained on as little as 1% of labeled data and exhibits significant resistance to clinical artifacts, including motion blur and low-dose CT noise.

---