Stay updated with the latest research and technology news
arXiv:2602.10983v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot...
arXiv:2602.10961v2 Announce Type: replace Abstract: Standard geometric control relies on force-moment decoupling, an assumption that breaks down in many aerial platforms due to spurious forces...
arXiv:2602.10934v2 Announce Type: replace Abstract: Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Despite recent progress,...
arXiv:2602.10915v2 Announce Type: replace Abstract: The evolution of Large Language Models (LLMs) has shifted mobile computing from App-centric interactions to system-level autonomous agents. Current implementations...
arXiv:2602.10796v2 Announce Type: replace Abstract: Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing...
arXiv:2602.10763v2 Announce Type: replace Abstract: Our work utilized a non-sequential simulation-based inference algorithm to provide an amortized neural density estimator, which approximates the posterior distribution...
arXiv:2602.10739v2 Announce Type: replace Abstract: Two-sided marketplaces embody heterogeneity in incentives: producers seek exposure while consumers seek relevance, and balancing these competing objectives through constrained...
arXiv:2602.10718v2 Announce Type: replace Abstract: While FP8 attention has shown substantial promise in innovations like FlashAttention-3, its integration into the decoding phase of the DeepSeek...
arXiv:2602.10706v2 Announce Type: replace Abstract: Estimating the expectation of a real-valued function of a random variable from sample data is a critical aspect of statistical...
arXiv:2602.10699v2 Announce Type: replace Abstract: Generative recommendation via autoregressive models has unified retrieval and ranking into a single conditional generation framework. However, fine-tuning these models...
arXiv:2602.10687v2 Announce Type: replace Abstract: Existing forgery detection methods are often limited to uni-modal or bi-modal settings, failing to handle the interleaved text, images, and...
arXiv:2602.10633v2 Announce Type: replace Abstract: With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models...
arXiv:2602.10606v2 Announce Type: replace Abstract: Generative recommendation models sequence generation to produce items end-to-end, but training from behavioral logs often provides weak supervision on underlying...
arXiv:2602.10564v2 Announce Type: replace Abstract: Federated fine-tuning of on-device large language models (LLMs) mitigates privacy concerns by preventing raw data sharing. However, the intensive computational...
arXiv:2602.10520v2 Announce Type: replace Abstract: Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at...
arXiv:2602.10516v2 Announce Type: replace Abstract: Audio-driven 3D talking avatar generation is increasingly important in virtual communication, digital humans, and interactive media, where avatars must preserve...
arXiv:2602.10480v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs), where...
arXiv:2602.10467v2 Announce Type: replace Abstract: Bargaining is often regarded as a logical arena rather than an art or a matter of intuition, yet Large Language...
arXiv:2602.10445v2 Announce Type: replace Abstract: Generative Recommendation (GR) has excelled by framing recommendation as next-token prediction. This paradigm relies on Semantic IDs (SIDs) to tokenize...
arXiv:2602.10437v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which...
arXiv:2602.10431v2 Announce Type: replace Abstract: Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged...
arXiv:2602.10271v2 Announce Type: replace Abstract: Understanding multimodal long-context documents that comprise multimodal chunks such as paragraphs, figures, and tables is challenging due to (1) cross-modal...
arXiv:2602.10125v2 Announce Type: replace Abstract: Network segmentation is a popular security practice for limiting lateral movement, yet practitioners lack a metric to measure how segmented...
arXiv:2602.10117v2 Announce Type: replace Abstract: Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call...