Resting-state functional connectivity is widely used in machine learning-based classification of neuropsychiatric disorders. Quantum machine learning models have been proposed for functional connectivity data, but few studies have evaluated them under leave-site-out validation or against matched classical models. We co...
Utsav Poudel, Anuj Nepal, Vyas Viswanath et al.· 0 citations
DocPilot is introduced, an agentic document framework that supports expressive orchestration and makes complex document solving learnable by small language models (SLMs) and integrates local visual inspection, code-based numerical reasoning, and cross-modal reasoning for multimodal understanding.
Zhuo-Wen Liang, Xiao-Tian Lin, Yu-Yu Luo et al.· 0 citations
In controlled tests on one task per benchmark, pricing the model's cost advantages at parity more than halves a cost-blind learner's cost and meets a tight continuous-control limit the learned multiplier misses, suggesting the model's cost estimates are not the bottleneck.
Money-mule networks move criminal funds through many small transfers, each of which looks ordinary on its own. What marks an account as a mule lies outside any single transfer: in the counterparties and addresses its network shares, and in the shape of its activity over time. Production systems remain largely rule-base...
Owais Ahmad, Anirudh Deodhar· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision should be trusted? Resolving such disagreements is difficult because agents'decisions are susceptible to non-semantic biases such as majority pressure and response-style...
Sungjae Lee, Soheil Abbasloo, Jabin Koo et al.· 0 citations
We investigate whether variation in information density across chain-of-thought (CoT) reasoning steps predicts answer correctness and can serve as a controllable inference-time target. We prompt frozen pretrained models to solve problems via CoT and measure the density of each reasoning step with two independent metric...
Tanush Kalhan, Anupam Chattopadhyay, Sriram Ranga et al.· 0 citations
Code world models represent world dynamics through explicit state and executable rules. We investigate how to coordinate object representations, behavioral revisions, and visual memory within this formulation. We present Mallea, a system for building, steering, and memorizing worlds from text. A coding agent infers obj...
Diviner (Domain-Informed Verifiable Incident Navigation through Evidence and Review), an agentic RCA system operating at Meta and organized around a four-stage reliability lifecycle is presented.
Pradipta Ghosh, Gaurav Mitra, S. Nadgowda et al.· 0 citations
Trustworthy biomedical AI requires reliable action selection when evidence is missing, stale, conflicting, or late, not only accurate answers on static inputs. We instantiate an episode-level evaluation protocol as 400 synthetic healthcare workflow episodes: 40 hand-authored semantic seeds across four task classes, two...
Zihao Zheng (Washington University in St. Louis), Junyi Yao (Washington University in St. Louis), Baichuan Li (Southern Methodist University) et al.· 0 citations
Agentic large language models have been documented to lose reasoning capability when placed inside a harness, the software that mediates their observations and actions. To reconcile these losses, we introduce AutoOnboarder, an autonomous system that adapts an agent to a task the way a trainer onboards a new employee. I...
Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a binary judgment from an LLM verifier. However, judgment certainty varies substantially across criteria. Existing methods uniformly aggregate these judgments into a final...
Li-Cheng Pan, Hao Yang, Hao-Xuan Li et al.· 0 citations
When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks before it answers, but we do not know what extra thinking does to such everyday inferences. We study this directly: we keep a model's weights fixed, change only how much...
Zhizhuo Kou, Jian Yang, Pengfei Hao et al.· 0 citations
