Stay updated with the latest research and technology news
arXiv:2601.17641v1 Announce Type: new Abstract: Brain decoding aims to interpret and translate neural activity into behaviors. As such, it is imperative that decoding models are...
arXiv:2601.17642v1 Announce Type: new Abstract: Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in \emph{over-refusal}...
arXiv:2601.17644v2 Announce Type: new Abstract: The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g. visual QA) introduces important privacy challenges. In...
arXiv:2601.17646v1 Announce Type: new Abstract: Empirical risk minimization (ERM) stability is usually studied via single-valued outputs, while convex non-strict losses yield set-valued minimizers. We identify...
arXiv:2601.17647v1 Announce Type: new Abstract: Quantifying the causal relationship between ice melt and freshwater distribution is critical, as these complex interactions manifest as regional fluctuations...
arXiv:2601.17654v1 Announce Type: new Abstract: The computing demand of AI is growing at an unprecedented rate, but energy supply is not keeping pace. As a...
arXiv:2601.17656v1 Announce Type: new Abstract: This paper presents a battery-free and gateway-free water leak detection system capable of direct communication over LTE-M (Cat-M1). The system...
arXiv:2601.17657v1 Announce Type: new Abstract: Contrastive Language-Image Pre-training (CLIP) has accomplished extraordinary success for semantic understanding but inherently struggles to perceive geometric structure. Existing methods...
arXiv:2601.17658v1 Announce Type: new Abstract: The rise of conspiracy theories has created far-reaching societal harm in the public discourse by eroding trust and fueling polarization....
arXiv:2601.17660v1 Announce Type: new Abstract: This work presents a self powered water leak sensor that eliminates both batteries and local gateways. The design integrates a...
arXiv:2601.17661v1 Announce Type: new Abstract: Industrial Control Systems (ICS) rely on sensor feedback to keep safety-critical processes within operational limits. This research presents a hardware-root-of-trust...
arXiv:2601.17664v1 Announce Type: new Abstract: Urdu, spoken by 230 million people worldwide, lacks dedicated transformer-based language models and curated corpora. While multilingual models provide limited...
arXiv:2601.17666v1 Announce Type: new Abstract: Real-world meal images often contain multiple food items, making reliable compositional food image generation important for applications such as image-based...
arXiv:2601.17667v1 Announce Type: new Abstract: We propose a provably correct Monte Carlo tree search (MCTS) algorithm for solving \textit{risk-aware} Markov decision processes (MDPs) with \textit{entropic...
arXiv:2601.17668v1 Announce Type: new Abstract: Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques...
arXiv:2601.17670v1 Announce Type: new Abstract: This work investigates generative mathematical programming through the lens of Algebraic Modelling Languages (AMLs) and compiler-guided model synthesis. By leveraging...
arXiv:2601.17671v1 Announce Type: new Abstract: Despite the impressive reasoning abilities demonstrated by large language models (LLMs), empirical evidence indicates that they are not language agnostic...
arXiv:2601.17673v1 Announce Type: new Abstract: Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: Although they can accurately recognize and describe object locations...
arXiv:2601.17676v1 Announce Type: new Abstract: Smart glasses are accelerating progress toward more seamless and personalized LLM-based assistance by integrating multimodal inputs. Yet, these inputs rely...
arXiv:2601.17678v1 Announce Type: new Abstract: We study inverse mechanism learning: recovering an unknown incentive-generating mechanism from observed strategic interaction traces of self-interested learning agents. Unlike...
arXiv:2601.17679v1 Announce Type: new Abstract: Bangla, one of the most widely spoken languages, remains underrepresented in state-of-the-art automatic speech recognition (ASR) research, particularly under noisy...
arXiv:2601.17680v1 Announce Type: new Abstract: The Mixture of Experts (MoE) selects a few feed-forward networks (FFNs) per token, achieving an effective trade-off between computational cost...
arXiv:2601.17683v1 Announce Type: new Abstract: Control barrier functions guarantee safety but typically require accurate system models. Parametric uncertainty invalidates these guarantees. Existing robust methods maintain...
arXiv:2601.17684v1 Announce Type: new Abstract: Due to the fundamental connection between next-symbol prediction and compression, modern predictive models, such as large language models (LLMs), can...