Stay updated with the latest research and technology news
arXiv:2601.21164v2 Announce Type: replace Abstract: Plane Geometry Problem Solving (PGPS) is a multimodal reasoning task that aims to solve a plane geometric problem based on...
arXiv:2601.21285v2 Announce Type: replace Abstract: Accurately capturing feature interactions is essential in recommender systems, and recent trends show that scaling up model capacity could be...
arXiv:2601.21343v2 Announce Type: replace Abstract: Ensuring safety, factuality and overall quality in the generations of large language models is a critical challenge, especially as these...
arXiv:2601.21358v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and reasoning...
arXiv:2601.21436v2 Announce Type: replace Abstract: Advances in multi-modal large language models (MLLMs) have inspired time series understanding and reasoning tasks, that enable natural language querying...
arXiv:2601.21468v2 Announce Type: replace Abstract: Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history...
arXiv:2601.21610v2 Announce Type: replace Abstract: Digital watermarking is essential for securing generated images from diffusion models. Accurate watermark evaluation is critical for algorithm development, yet...
arXiv:2601.21632v2 Announce Type: replace Abstract: Open-source AI is scaling rapidly, and model hubs now host millions of artifacts. Each foundation model can spawn large numbers...
arXiv:2601.21639v2 Announce Type: replace Abstract: The development of large vision language models drives the demand for managing, and applying massive amounts of multimodal data, making...
arXiv:2601.21702v2 Announce Type: replace Abstract: We consider representation misdirection (RM), a class of LLM unlearning methods that achieves forgetting by manipulating the forget-representations, that is,...
arXiv:2601.21896v3 Announce Type: replace Abstract: Video generation is pivotal to digital media creation, and recent advances in autoregressive video generation have markedly enhanced the efficiency...
arXiv:2601.21904v3 Announce Type: replace Abstract: As a foundational task in human-centric cross-modal intelligence, motion-language retrieval aims to bridge the semantic gap between natural language and...
arXiv:2601.21972v2 Announce Type: replace Abstract: Recent work has explored optimizing LLM collaboration through Multi-Agent Reinforcement Learning (MARL). However, most MARL fine-tuning approaches rely on predefined...
arXiv:2601.22199v2 Announce Type: replace Abstract: Robotics education fosters computational thinking, creativity, and problem-solving, but remains challenging due to technical complexity. Game-based learning (GBL) and gamification...
arXiv:2601.22409v2 Announce Type: replace Abstract: Kolmogorov--Arnold Networks (KANs) have recently emerged as a structured alternative to standard MLPs, yet a principled theory for their training...
arXiv:2601.22548v2 Announce Type: replace Abstract: Recent research has shown that large language models (LLMs) favor their own outputs when acting as judges, undermining the integrity...
arXiv:2601.22579v3 Announce Type: replace Abstract: Malicious bots pose a growing threat to e-commerce platforms by scraping data, hoarding inventory, and perpetrating fraud. Traditional bot mitigation...
arXiv:2601.22766v2 Announce Type: replace Abstract: Recent work has revealed a link between self-attention mechanisms in transformers and test-time kernel regression via the Nadaraya-Watson estimator, with...
arXiv:2601.22778v2 Announce Type: replace Abstract: As realistic AI-generated images threaten digital authenticity, we address the generalization failure of generative artifact-based detectors by exploiting the intrinsic...
arXiv:2601.22913v2 Announce Type: replace Abstract: Visual anomaly detection in real-world industrial settings faces two major limitations. First, most existing methods are trained on purely normal...
arXiv:2601.23174v2 Announce Type: replace Abstract: Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete tokens...
arXiv:2601.23209v2 Announce Type: replace Abstract: Additive models of interaction performance, such as the Keystroke-Level Model (KLM), are tools that allow designers to compare and optimize...
arXiv:2601.23228v2 Announce Type: replace Abstract: While multiagent systems have shown promise for tackling complex tasks via specialization, finetuning multiple agents simultaneously faces two key challenges:...
arXiv:2602.00158v2 Announce Type: replace Abstract: Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of...