arXiv:2604.02719v1 Announce Type: cross
Abstract: We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX,…
arXiv:2602.06932v2 Announce Type: replace
Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling p…
arXiv:2604.03058v1 Announce Type: cross
Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like “am I in the wrong?” rather than providing genuine assessment. We hypothesize that this behavior arises from incorrect ass…
arXiv:2604.03208v1 Announce Type: new
Abstract: Model predictive control (MPC) with learned world models has emerged as a promising paradigm for embodied control, particularly for its ability to generalize zero-shot when deployed in new environments. …
arXiv:2602.10419v2 Announce Type: replace
Abstract: Uncertainty quantification (UQ) is critical for assessing the reliability of machine learning interatomic potentials (MLIPs) in molecular dynamics (MD) simulations, identifying extrapolation regimes …
arXiv:2604.02692v1 Announce Type: new
Abstract: Accurate document parsing requires both robust content recognition and a stable parser interface. In explicit Document Layout Analysis (DLA) pipelines, downstream parsers do not consume the full detector…
arXiv:2604.02694v1 Announce Type: new
Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly rely on visual cues and l…
arXiv:2604.02045v1 Announce Type: new
Abstract: Transforming causal generative language models into bidirectional encoders offers a powerful alternative to BERT-style architectures. However, current approaches remain limited: they lack consensus on op…
arXiv:2604.02135v1 Announce Type: new
Abstract: Multilingual large language models (LLMs) often exhibit emergent ‘shadow’ capabilities in languages without official support, yet their performance on these languages remains uneven and under-measured. T…
arXiv:2410.17954v2 Announce Type: replace-cross
Abstract: Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many expert modul…