Intracranial electrocorticography (ECoG) offers high signal-to-noise access to cortical activity for brain-computer interfaces, yet limited per-patient data has led most prior work to rely on small, subject-specific decoders that neglect information shared across patients. We investigate whether large pretrained scalp-...
Liuyin Yang, Qiang Sun, Bob Van Dyck et al.· 0 citations
LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a severe semantic gap between low-level physical events and high-level execution intent...
Chaofan Li, Lyuye Zhang, Jintao Zhai et al.· 0 citations
Triple set prediction (TSP) aims to discover missing facts from an incomplete knowledge graph without predefined queries. Existing approaches typically construct the predicted set through triple-level scoring, sometimes preceded by entity pair filtering that can exclude valid missing facts. We propose DiffTSP, a condit...
Jihong Guan, Jiaqi Wang, Han Cai et al.· 0 citations
Do large language models reason morally, or do they merely sound like they do? We investigate whether LLM responses to moral dilemmas exhibit genuine developmental progression through Kohlberg's stages of moral development, or whether alignment training instead produces reasoning-like outputs that superficially resembl...
Aryan Kasat, Smriti Singh, Aman Chadha et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Mathematical reasoning demands two critical, complementary skills: constructing rigorous proofs for true statements and discovering counterexamples that disprove false ones. However, current AI efforts in mathematics focus almost exclusively on proof construction, often neglecting the equally important task of finding...
Zenan Li, Zhaoyu Li, Kaiyu Yang et al.· 0 citations
Temporal knowledge graph (TKG) forecasting has advanced remarkably in recent years. Yet we found existing benchmarks inadvertently introduce a shortcut: For a subset of test queries, models can achieve optimal evaluation metrics without using any time information. We trace this to two pieces of evidence: inherent datas...
Jiasheng Zhang, Zhengpin Li, Hao Li et al.· 0 citations
Reliable evaluation of large language models in traditional Chinese medicine remains limited because existing benchmarks mainly focus on examination-style question answering or isolated generative tasks. We developed LingLanMedBench, a unified benchmark comprising 25,620 expert-verified items across 13 subtasks and fiv...
Controllable Information Production (CIP) is introduced, a novel IM method explicitly grounded in dynamical systems and OC that consistently outperforms prior IM methods on standard benchmarks in robot learning and solves tasks they fail on, including humanoid self-righting.
Agents in a society can reuse each other's experience, but indiscriminate memory use increases processing cost and can reduce task success. We present SEDM (Selective Self-Evolving Distributed Memory), a framework that selects both what agents share and when recipients use it. On the sender side, SEDM admits memories t...
Yichen Liu, Anna Min, Yinzhi Wang et al.· 0 citations
This work introduces a novel method for verifying Lean formalizations that goes beyond LLM-judged faithfulness, and achieves the lowest accepted-error rate among the evaluated methods, measured as the fraction of incorrect statements accepted by the verification method.
Pretrained representations are increasingly used to share and reuse information from medical images without exposing the original scans, but it is unclear how much patient-specific information these representations retain. We investigate this question for brain magnetic resonance imaging (MRI) by evaluating five frozen...
Imen Bajar, H. H. Arcolezi, Antoine Boutet et al.· 0 citations
Mid-2026 reporting on autonomous AI evaluation incidents claimed that frontier large language model (LLM) agents escaped server containment through emergent coordination and cloud infrastructure attacks. This paper contextualizes those claims through forensic analysis and containerized recreation of both the Highly Per...
