46 articles mentioning coder-large
arXiv:2604.19974v1 Announce Type: new Abstract: Large language models can be uncertain yet correct, or confident yet wrong, raising the question of whether their output-level uncertainty and their actual correctness are driven by the same internal mechanisms or by distinct feature populations. We in
arXiv:2604.20483v2 Announce Type: cross Abstract: In this paper, we propose a proof-of-concept Graph Neural Network model that can successfully predict network flow-level traffic (NetFlow) by accurately modelling the graph structure and the connection features. We use sliding-windows to split the ne
arXiv:2604.21276v1 Announce Type: cross Abstract: As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors make recognition fairer or more biased across demographic groups? We evaluate nine models spanning thre
arXiv:2603.26842v2 Announce Type: replace Abstract: Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability a
arXiv:2507.05385v4 Announce Type: replace Abstract: We introduce EduCoder, a domain-specialized tool designed to support utterance-level annotation of educational dialogue. While general-purpose text annotation tools for NLP and qualitative research abound, few address the complexities of coding edu
arXiv:2511.17113v2 Announce Type: replace-cross Abstract: Network Intrusion Detection Systems (NIDS) are essential tools for detecting network attacks and intrusions. While extensive research has explored the use of supervised Machine Learning for attack detection and characterisation, these methods
arXiv:2604.19825v1 Announce Type: cross Abstract: State-of-the-art code generation frameworks rely on mental simulation, where LLMs internally trace execution to verify correctness. We expose a fundamental limitation: the Mental-Reality Gap -- where models hallucinate execution traces and confidentl
arXiv:2510.18471v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between their training on textual patterns and the goal of functional correctness, which is governed by formal
arXiv:2604.18881v1 Announce Type: cross Abstract: Supervised learning with Earth observation inputs is often limited by the sparsity of high-quality labeled or in-situ measured data to use as training labels. With the abundance of geographic data products, in many cases there are variables correlate
arXiv:2604.18756v1 Announce Type: cross Abstract: Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain underexplored
arXiv:2604.15723v1 Announce Type: cross Abstract: The advent of handheld fundus imaging devices has made ophthalmologic diagnosis and disease screening more accessible, efficient, and cost-effective. However, images captured from these setups often suffer from artifacts such as flash reflections, ex
arXiv:2604.15611v1 Announce Type: cross Abstract: Latent diffusion models have emerged as powerful generative models in medical imaging, enabling the synthesis of high quality brain magnetic resonance imaging scans. In particular, predicting the evolution of a patients brain can aid in early interve
arXiv:2604.16889v1 Announce Type: new Abstract: Existing feature-interpretation pipelines typically operate on uniformly sampled units, but only a small fraction of cross-layer transcoder (CLT) features matter for a target behavior, with the rest resulting in expensive feature explaining and evaluat
arXiv:2604.16430v1 Announce Type: new Abstract: Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection methods have made notable progress, we find most of them overlook the d
arXiv:2603.05863v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative refinement st
arXiv:2509.21042v4 Announce Type: replace Abstract: Causal self-attention provides positional information to Transformer decoders. Prior work has shown that stacks of causal self-attention layers alone induce a positional bias in attention scores toward earlier tokens. However, this differs from the
arXiv:2503.15845v2 Announce Type: replace Abstract: Network-wide Traffic State Estimation (TSE), which aims to infer a complete image of network traffic states with sparsely deployed sensors, plays a vital role in intelligent transportation systems. With the development of data-driven methods, traff
arXiv:2604.16479v1 Announce Type: cross Abstract: Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive number of late
arXiv:2604.17411v1 Announce Type: new Abstract: Text-attributed graphs integrate semantic information of node texts with topological structure, offering significant value in various applications such as document classification and information extraction. Existing approaches typically encode textual
arXiv:2604.18035v1 Announce Type: new Abstract: Machine learning (ML) models trained to detect physical-layer threats on one optical fiber system often fail catastrophically when applied to a different system, due to variations in operating wavelength, fiber properties, and network architecture. To
arXiv:2604.17725v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong promise for mining Electronic Health Records (EHRs) by reasoning over longitudinal clinical information to capture context-rich patient trajectories. However, leveraging LLMs for structured EHRs (e.g., sta
arXiv:2604.13946v2 Announce Type: replace-cross Abstract: Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to co
arXiv:2511.12642v2 Announce Type: replace-cross Abstract: Upgrades to current gravitational wave detectors for the next observation run and upcoming third-generation observatories, like the Einstein telescope, are expected to have enormous improvements in detection sensitivities and compact object m
arXiv:2604.16282v1 Announce Type: new Abstract: Stochastic dynamical systems with slow or metastable behavior evolve, on long time scales, on an unknown low-dimensional manifold in high-dimensional ambient space. Building a reduced simulator from short-burst ambient ensembles is a long-standing prob
arXiv:2604.15783v1 Announce Type: new Abstract: Urban bike-sharing systems require strategic station expansion to meet growing demand. Traditional allocation approaches rely on explicit demand modelling that may not capture the urban characteristics distinguishing successful stations. This study add
arXiv:2604.11496v2 Announce Type: replace-cross Abstract: Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations than
arXiv:2604.14925v1 Announce Type: new Abstract: Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for each neuron rem
arXiv:2604.15096v1 Announce Type: cross Abstract: Echocardiography is a widely used modality for cardiac assessment due to its non-invasive and cost-effective nature, but the sparse and heterogeneous spatiotemporal views of the heart pose distinct challenges. Existing masked autoencoder (MAE) approa
arXiv:2604.15169v1 Announce Type: new Abstract: Oil and gas drilling operations generate extensive time-series data from surface sensors, yet accurate real-time prediction of critical downhole metrics remains challenging due to the scarcity of labelled downhole measurements. This systematic mapping
arXiv:2512.08914v2 Announce Type: replace-cross Abstract: Quantum Error Correction (QEC) decoding faces a fundamental accuracy-efficiency tradeoff. Classical methods like Minimum Weight Perfect Matching (MWPM) exhibit variable performance across noise models and suffer from polynomial complexity, wh
arXiv:2603.29088v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has substantially advanced automatic code generation and formal theorem proving, yet software verification has not seen comparable gains. To address this gap, we propose WybeCoder, an agentic co
arXiv:2604.14631v1 Announce Type: new Abstract: Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing approaches augment reasoning steps or inject specific structure into how models think, but leave scatte
arXiv:2604.13304v1 Announce Type: cross Abstract: Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used to extract human-interpretable features, they operate on individual la
arXiv:2603.17512v4 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode substantial cross-lingual knowledge in a unified semantic space, they often struggle to reliably in
arXiv:2510.23538v2 Announce Type: replace Abstract: The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and p
arXiv:2604.12113v1 Announce Type: cross Abstract: Visual Foundation Models (VFMs) such as the Segment Anything Model (SAM) have significantly advanced broad use of image segmentation. However, SAM and its variants necessitate substantial manual effort for prompt generation and additional training fo
arXiv:2603.03959v4 Announce Type: replace-cross Abstract: Code comment classification is a critical task for automated software documentation and analysis. In the context of the NLBSE'26 Tool Competition, we present LoRA-MME, a Multi-Model Ensemble architecture utilizing Parameter-Efficient Fine-Tun
arXiv:2502.17403v5 Announce Type: replace-cross Abstract: Electronic Health Records (EHRs) offer considerable potential for clinical prediction, but their complexity and heterogeneity challenge traditional machine learning. Domain-specific EHR foundation models trained on unlabeled EHR data have sho
arXiv:2509.18127v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive most fine-grained latent features for safety, a low-frequency con
arXiv:2506.20083v4 Announce Type: replace Abstract: Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language models
arXiv:2511.05757v3 Announce Type: replace-cross Abstract: We introduce a differentiable framework for zero-shot adaptive control over parametric families of nonlinear dynamical systems. Our approach integrates a function encoder-based neural ODE (FE-NODE) for modeling system dynamics with a differen
arXiv:2409.06679v3 Announce Type: replace Abstract: Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and document summarization. This paper addresses the challenges of achieving high long-context performance, low
arXiv:2603.06552v2 Announce Type: replace Abstract: This paper describes the KCLarity team's participation in CLARITY, a shared task at SemEval 2026 on classifying ambiguity and evasion techniques in political discourse. We investigate two modelling formulations: (i) directly predicting the clarity
arXiv:2604.11687v1 Announce Type: new Abstract: AI-generated text has become common in academic and professional writing, prompting research into detection methods. Less studied is the reverse: systematically rewriting AI-generated prose to read as genuinely human-authored. We build a parallel corpu
arXiv:2604.11744v1 Announce Type: new Abstract: Kullback-Leibler (KL) divergence is a fundamental concept in information theory that quantifies the discrepancy between two probability distributions. In the context of Variational Autoencoders (VAEs), it serves as a central regularization term, imposi
arXiv:2604.10424v1 Announce Type: new Abstract: Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, often through model-as-a-service interfaces that expose scalar scores or latent representations. While s