arXiv:2606.24168v1 Announce Type: cross Abstract: Automated diabetic retinopathy (DR) grading from colour fundus photographs can achieve strong predictive performance, but clinical interpretation requires more than an…
arXiv:2509.03647v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own…
arXiv:2606.24259v1 Announce Type: cross Abstract: Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption of feature statistics, and no…
arXiv:2606.23884v1 Announce Type: new Abstract: General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate and inconsistent across clinical…
arXiv:2606.23740v1 Announce Type: new Abstract: Offline reinforcement-learning losses (RFT, RIFT, DFT, Offline GRPO, DPO) are widely used to distill reasoning from large teachers into smaller students,…
arXiv:2601.03673v2 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) provide a framework for integrating physical laws with data. However, their application to Prognostics and Health Management…
arXiv:2606.23897v1 Announce Type: new Abstract: Prompt distillation compresses large vision-language models (VLMs) such as CLIP into lightweight student models by matching teacher predictions on unlabeled domain…
arXiv:2606.24774v1 Announce Type: new Abstract: Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in…
arXiv:2606.24244v1 Announce Type: cross Abstract: AI-assisted interviews promise to reduce respondent burden in surveys by allowing respondents to describe experiences naturally while an AI system noisily…
arXiv:2606.24797v1 Announce Type: cross Abstract: Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on video question answering (VideoQA). Nevertheless, existing benchmarks are…
arXiv:2606.24112v1 Announce Type: new Abstract: Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed provenance, and subtle text--image…
arXiv:2606.23701v1 Announce Type: new Abstract: Qualitative product feedback can reveal nuanced user experiences, but its implicit sentiment is difficult to measure. This paper presents a scalable…
arXiv:2602.14612v4 Announce Type: replace-cross Abstract: Answering natural-language questions over multi-hour audio requires both event recognition and temporal grounding. Current large audio-language models perform well on short…
arXiv:2606.23851v1 Announce Type: new Abstract: This work investigates the implementation of artificial intelligence and machine learning (AI/ML) for real-time monitoring in laser powder bed fusion (LPBF)…
arXiv:2606.23843v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are typically pre-trained on large-scale image-text datasets to capture semantic correspondences between visual content and natural language. However,…
arXiv:2306.05239v3 Announce Type: replace-cross Abstract: Sampled point and voxel methods are usually employed to downsample the dense events into sparse ones. After that, one popular way…
arXiv:2606.23944v1 Announce Type: cross Abstract: State--space models provide a flexible framework for analyzing dynamical systems, yet they often rely on Gaussian assumptions that fail to capture…
arXiv:2603.20750v2 Announce Type: replace Abstract: Social actors do not observe a common social world: each individual forms judgments from a partial and potentially distorted view of…
arXiv:2606.24460v1 Announce Type: cross Abstract: Commercial large language models bill, scale latency, and budget context per token. Yet tokenizers assign more subword tokens to the same…
arXiv:2606.23700v1 Announce Type: new Abstract: Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates…
arXiv:2606.11552v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference…
arXiv:2604.11284v5 Announce Type: replace Abstract: We present THEIA, a 2.75M-parameter modular neural architecture that learns the complete Kleene three-valued logic (K3) truth table from task data…
arXiv:2606.23885v1 Announce Type: new Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward…
arXiv:2601.03509v2 Announce Type: replace-cross Abstract: We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of…