Stay updated with the latest research and technology news
arXiv:2602.04288v1 Announce Type: new Abstract: Central to many self-improvement pipelines for large language models (LLMs) is the assumption that models can improve by reflecting on...
arXiv:2602.04289v1 Announce Type: new Abstract: Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often...
arXiv:2602.04290v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models...
arXiv:2602.04291v1 Announce Type: new Abstract: Multi-expert systems, where multiple Large Language Models (LLMs) collaborate to solve complex tasks, are increasingly adopted for high-performance reasoning and...
arXiv:2602.04292v1 Announce Type: new Abstract: Text-to-motion generation has advanced with diffusion models, yet existing systems often collapse complex multi-action prompts into a single embedding, leading...
arXiv:2602.04294v1 Announce Type: new Abstract: Large Language Models (LLMs) face increasing threats from jailbreak attacks that bypass safety alignment. While prompt-based defenses such as Role-Oriented...
arXiv:2602.04296v1 Announce Type: new Abstract: Large language models (LLMs) have revolutionized automated code generation, yet the evaluation of their real-world effectiveness remains limited by static...
arXiv:2602.04297v1 Announce Type: new Abstract: Large language models (LLMs) are widely used as zero-shot and few-shot classifiers, where task behaviour is largely controlled through prompting....
arXiv:2602.04299v1 Announce Type: new Abstract: Unilateral limb motor imagery (MI) plays an important role in upper-limb motor rehabilitation and precise control of external devices, and...
arXiv:2602.04300v1 Announce Type: new Abstract: Face fill-light enhancement (FFE) brightens underexposed faces by adding virtual fill light while keeping the original scene illumination and background...
arXiv:2602.04304v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text embedding space, but a fixed visual-token...
arXiv:2602.04306v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial....
arXiv:2602.04314v1 Announce Type: new Abstract: Biodiversity open-access databases are valuable resources in the structuring and accessibility of species occurrence data. By compiling different data sources,...
arXiv:2602.04315v1 Announce Type: new Abstract: Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization...
arXiv:2602.04317v1 Announce Type: new Abstract: Reconstructing high-fidelity animatable 3D human avatars from monocular RGB videos remains challenging, particularly in unconstrained in-the-wild scenarios where camera parameters...
arXiv:2602.04320v1 Announce Type: new Abstract: Information Extraction (IE), encompassing Named Entity Recognition (NER), Named Entity Linking (NEL), and Relation Extraction (RE), is critical for transforming...
arXiv:2602.04323v1 Announce Type: new Abstract: End-to-end prediction of high-order crystal tensor properties from atomic structures remains challenging: while spherical-harmonic equivariant models are expressive, their Clebsch-Gordan...
arXiv:2602.04326v1 Announce Type: new Abstract: Embodied agents operating in multi-agent, partially observable, and decentralized environments must plan and act despite pervasive uncertainty about hidden objects...
arXiv:2602.04328v1 Announce Type: new Abstract: Features of the same sample generated by different pretrained models often exhibit inherently distinct feature distributions because of discrepancies in...
arXiv:2602.04329v1 Announce Type: new Abstract: Achieving safe and stylized trajectory planning in complex real-world scenarios remains a critical challenge for autonomous driving systems. This paper...
arXiv:2602.04332v1 Announce Type: new Abstract: Despite their critical role in shaping student learning in computing education, the contributions of women teaching-support staff (TSS) often go...
arXiv:2602.04337v1 Announce Type: new Abstract: Large-scale vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization, but adapting them to downstream tasks typically requires costly...
arXiv:2602.04339v1 Announce Type: new Abstract: Evaluating fairness under domain shift is challenging because scalar metrics often obscure exactly where and how disparities arise. We introduce...
arXiv:2602.04340v1 Announce Type: new Abstract: Pre-trained vision-language models such as CLIP exhibit strong transferability, yet adapting them to downstream image classification tasks under limited annotation...