Genetic variants are routinely reclassified in ClinVar after a patient is tested, sometimes from uncertain to pathogenic, yet patient recontact is inconsistent, with no clear duty and responsibility diffused among labs, providers, and patients. Many affected people discuss their results in public online health communit...
Kamalakkannan Ravi, Mengshu Nie, Annapurna Poduri et al.· 0 citations
Transductive adaptation improves vision-language models at test time by refining predictions on an unlabeled batch, but current methods face a key trade-off. Aggressive approaches exploit batch structure but can drift when batches are sparse, have prior shift, or cover little of the label space. Conservative methods be...
Mohammed Rahman Sherif Khan Mohammad, Ardhendu Behera, Sandip Pradhan et al.· 0 citations
Forecasting foundation models are increasingly used as frozen feature extractors for time series classification, but it remains unclear whether their pretrained representations offer an advantage over strong classifiers that do not require pretraining. This raises an important question: do these representations provide...
Rishit Jain, Rishit Kar, Chetashri Bhadane et al.· 0 citations
LLM-based proactive dialogue systems provide goal-directed support through sustained interaction. Fine-tuning their underlying models on externally supplied dialogue data introduces backdoor risks. Existing LLM backdoor studies primarily focus on eliciting an attacker-specified response upon trigger activation. We pres...
Zhiyang Xia, Yuming Shang, Xi Zhang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Continuous integration and AI-assisted review spend the same budget on every commit, although few commits introduce bugs. We study KG-AST, which scores each commit risk from git history and code-graph features before heavy tests or AI review run, so the budget goes to the riskiest commits first, and which hands the AI...
This paper advances a form of non-computational physicalism: consciousness depends upon intrinsically organized, metabolically grounded physical dynamics rather than abstract computation, whilst leaving open the possibility of artificial consciousness.
Across four independent cohorts, BrainPFN beats KRR on small sample prediction, and leads recent foundation models pre-trained at four to nine times larger scale, showing that a modest, openly available pool can match or beat models trained at Biobank scale.
Carlo Alberto Barbano, Demian Wassermann· 0 citations
This study reveals how OPC arises from network structures and task demands, offers insights into the implementation and computational mechanisms of OPC in biological systems, and inspires us to develop computational models for human-like cognitive functions.
Background. A connectome specifies the substrate available to a nervous system, not how much of it a given computation requires. Reported compact sufficient circuits are point estimates: one subset, one task, one fidelity threshold, one parameterisation. Methods. We formalise computational sufficiency as a cost-indexed...
Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi et al.· 0 citations
The rapid deployment of generative AI raises the question of whether pervasive cognitive offloading drives a measurable, potentially irreversible decline in unassisted human reasoning. We examine this question with a phenomenological dynamical model based on the Cattell-Horn-Carroll distinction between fluid intelligen...
Petar Jolakoski, Dimitar Trajanov, Qiyu Sun et al.· 0 citations
Reward alignment for diffusion- and flow-based generative models is often formulated over stochastic trajectories, making it less suitable for few-step deterministic generators. Initial noise optimization provides a trajectory-free alternative, but existing gradient-free methods require costly per-sample search at infe...
Hongeun Kim, Jeongsol Kim, Jong Chul Ye· 0 citations
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation...
