Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding. To address this, we...
Chunxiao Li, Yuan Xiong, Lijun Li et al.· 0 citations
The cardiac attractor provides a phase-space representation of cardiovascular dynamics reconstructed from scalar observations under standard delay-embedding conditions. We introduce Attractor Domain Theory (ADT), a theory in which linked mathematical transformations expose distinct properties of reconstructed dynamics:...
LLM agents are promising for alpha mining via combining financial priors, symbolic reasoning, executable factor generation, and feedback-driven refinement. Yet, they face a combinatorial search space, noisy non-stationary feedback, redundant discoveries, and overfitting risks from naively reusing past successes. To add...
Hang Yu, Zifan Zheng, Chun Gan et al.· 0 citations
A theory can accommodate a counterexample by adding an exception. The harder problem is deciding how far the exception should extend and which predictions should survive. We present DeFAb, a dataset and symbolic verification framework built from curated biological knowledge in the Gene Ontology. Models fill gaps in a t...
Patrick Cooper, Avyay Sadhu, Alvaro Velasquez· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
GUI grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordinates. On-policy self-distillation (OPSD) is a promising post-training approach for this coordinate-sensitive task because it provides dense token-level teacher signals...
Jingyuan Huang, Zuming Huang, Yucheng Shi et al.· 0 citations
The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length.
To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe f...
Kai Liu, Peijie Dong, Xinchen Xie et al.· 0 citations
Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is fundamentally constrained by a lack of systematic skill construction, accumulation, and transfer. In particular, without a unified framework for skill consolidation, agents tend to redundantly construct similar capabi...
Yuan Xiong, Ziqi Miao, Qian Chen et al.· 0 citations
inspired by medicinal chemists, who probe the pocket-ligand complex with controlled analog edits before choosing an optimization direction, PROBE is proposed, an optimization framework built around edit--response probing that achieves state-of-the-art performance and substantially mitigates the failure modes exposed by...
Zai-Fei Yang, Wei-Yu Chen, Ya-Qing Wang et al.· arXiv.org· 1 citation
Large language models (LLM) can state their confidence in an answer (verbalized confidence), or the confidence can be read from the probability of the answer's tokens (token confidence). Comparisons of the two ask which is better calibrated, but the token probability of an answer depends on the text that precedes it. A...
Biomedical discovery often requires connecting broad biomedical knowledge with specific experimental or clinical data. Background knowledge suggests relevant mechanisms but is usually too general to map directly onto dataset variables, while data-driven patterns can be dataset-specific and hard to interpret mechanistic...
Qingyuan Zeng, Ziyang Chen, Pengxiang Cai et al.· 0 citations
Financial Numerical Entity (FNE) understanding aims to recover the meaning of numerical mentions in financial reports. Existing studies focus on concept name prediction and face two important limitations. First, labels derived from inline XBRL may contain errors because filings are usually prepared manually. Second, ot...
Sheng-Hua Tsai, Chen-Yang Lai, Yi-Jhen Li et al.· 0 citations
Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language system as a trainable and scalable neural-network-like architecture with LLM agen...
Haoran Lu, Luyang Fang, Wenxuan Zhong et al.· 0 citations
