Stay updated with the latest research and technology news
arXiv:2601.17824v1 Announce Type: new Abstract: Browser-based language models often use retrieval-augmented generation (RAG) but typically rely on fixed, outdated indices that give users no control...
arXiv:2601.17826v1 Announce Type: new Abstract: The increasing frequency and complexity of regulatory updates present a significant burden for multinational pharmaceutical companies. Compliance teams must interpret...
arXiv:2601.17828v1 Announce Type: new Abstract: We present Information Gain Fine-Tuning (IGFT), a novel approach for training medical conversational AI to conduct effective patient interviews and...
arXiv:2601.17829v1 Announce Type: new Abstract: The construction of function calling agents has emerged as a promising avenue for extending model capabilities. A major challenge for...
arXiv:2601.17830v1 Announce Type: new Abstract: Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as...
arXiv:2601.17833v1 Announce Type: new Abstract: Smart contract security is paramount, but identifying intricate business logic vulnerabilities remains a persistent challenge because existing solutions consistently fall...
arXiv:2601.17834v1 Announce Type: new Abstract: We consider polynomial codes for private distributed matrix multiplication (PDMM/SDMM). Existing codes for PDMM are either specialized for the outer...
arXiv:2601.17835v2 Announce Type: new Abstract: Gaussian Splatting (GS) has demonstrated impressive quality and efficiency in novel view synthesis. However, shape extraction from Gaussian primitives remains...
arXiv:2601.17836v1 Announce Type: new Abstract: In recent years, the success of large language models (LLMs) has driven the exploration of scaling laws in recommender systems....
arXiv:2601.17837v1 Announce Type: new Abstract: Non-native speakers (NNSs) face significant language barriers in multilingual communication with native speakers (NSs). While AI-mediated communication (AIMC) tools offer...
arXiv:2601.17838v1 Announce Type: new Abstract: Multiple-input multiple-output (MIMO) systems using Rydberg atomic (RA) receivers face significant scalability challenges in signal detection due to their nonlinear...
arXiv:2601.17842v1 Announce Type: new Abstract: Leveraging Large Language Models (LLMs) for Mental Health Question Answering (MHQA) is promising for mitigating resource shortages. However, existing Cognitive...
arXiv:2601.17844v1 Announce Type: new Abstract: Electroencephalogram (EEG) decoding is a critical component of medical diagnostics, rehabilitation engineering, and brain-computer interfaces. However, contemporary decoding methodologies remain...
arXiv:2601.17845v1 Announce Type: new Abstract: Mixnet networks deliberately induce additional latency to communications to provide anonymity. Recent developments have allowed mixnets to reduce their latency...
arXiv:2601.17846v1 Announce Type: new Abstract: AI-assisted writing raises concerns about autonomy and ownership when benefiting writers. Personalization has been proposed as an effective solution while...
arXiv:2601.17855v1 Announce Type: new Abstract: Load balancing-the allocation of work across parallel resources to reduce delay, energy and cost-is a pervasive challenge in science and...
arXiv:2601.17857v1 Announce Type: new Abstract: Recent advances in fMRI-based image reconstruction have achieved remarkable photo-realistic fidelity. Yet, a persistent limitation remains: while reconstructed images often...
arXiv:2601.17858v1 Announce Type: new Abstract: Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition...
arXiv:2601.17859v1 Announce Type: new Abstract: Perfect Doppler compensation and synchronization is nontrivial due to multi-path Doppler effects and Einstein's theory of relativity in the space-air-ground-integrated...
arXiv:2601.17862v1 Announce Type: new Abstract: Medical image artificial intelligence models often achieve strong performance in single-center or single-device settings, yet their effectiveness frequently deteriorates in...
arXiv:2601.17865v1 Announce Type: new Abstract: The predictive probability of the next token (P_token) in large language models (LLMs) is inextricably linked to the probability of...
arXiv:2601.17866v1 Announce Type: new Abstract: Promptable segmentation has emerged as a powerful paradigm in computer vision, enabling users to guide models in parsing complex scenes...
arXiv:2601.17868v1 Announce Type: new Abstract: Standard Autoregressive Video LLMs inevitably suffer from causal masking biases that hinder global spatiotemporal modeling, leading to suboptimal understanding efficiency....
arXiv:2601.17869v1 Announce Type: new Abstract: Learning structural information from observational data is central to producing new knowledge outside the training corpus. This holds for mechanistic...