The accuracy of detecting protein crystals for fluorescence microscopy images is very critical for high throughput and automated systems. Although the trace fluorescent labeling method could highlight protein crystals, reflection and emission from the fluorescence dye is not always due to crystal regions. Therefore, th...
Truong X. Tran, Marc L. Pusey, Ramazan S. Aygun· 0 citations
Large Language Models (LLMs) have made substantial progress in multilingual question answering, yet their ability to understand low-resource sociolinguistic contexts remains under-explored. We study North Korea as a unique testbed where decades of division have produced distinct differences from South Korea in vocabula...
Kiwoong Park, Seyoung Song, Donghyun Woo et al.· 0 citations
Depth estimation and Gaussian reconstruction share a need for multi-scale feature processing, yet use different prediction interfaces and training objectives. Whether a decoder's internal computation can be optimized once and reused across these systems remains a structural design question. Search over primitive config...
Joint-embedding predictive architectures (JEPAs) learn world models directly in latent space, but unconstrained autoregressive predictors may contract the latent distribution over long rollouts. We introduce Symplectic Hamiltonian JEPA (LeHami), which replaces the standard predictor with an action-conditioned Hamiltoni...
Post-training raises the 4B model's per-attempt accuracy and four-sample all-correct reliability and reduces average SMT calls from 4.10 to 2.52 and tokens per attempt from 18.97k to 12.72k.
Debargha Ganguly, Wei-Cong Chen, Mohsen Hariri et al.· 4 citations
Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to emerge only after deployment. We introduce a new attack surface, the self-evolving backdoor, whose payload stays dormant in the initial agent and is progressively activate...
Chuan Zou, Yang Xiang, Zexin Li et al.· 0 citations
Condensed matter stands to gain profoundly from widespread adoption of artificial intelligence (AI). However, its current means of data organization impedes this endeavor. As a premier measure of electronic structure underlying material properties, Angle-Resolved Photoemission Spectroscopy (ARPES) has accumulated over...
Zhi-Xun Shen, Jin Gene Wong, Karen Lei et al.· 0 citations
Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigations grow, agents must maintain research state across model calls and check findings before errors propagate into subsequent work. We introduce PANINI-DR, a m...
M. Yigit Turali, Shreyas Rajesh, M. Efe Lorasdagi et al.· 0 citations
This paper makes the following key observations: Shallow exits are consistently more robust to jailbreak attacks than deeper ones; Exit depth affects how easily the adversarial suffix can be optimized, with deeper exits reaching lower attack loss; and adversarial suffixes affect utility uniformly across exit depths.
Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally recognized human rights standards remains underexplored. We introduce UDHRBench, a large-scale benchmark for operationalising the evaluation of large language model compli...
Alak Raad, Noreldin Morssy, Zeerak Suhail et al.· 0 citations
This work proposes a learning algorithm that uses Kullback--Leibler lower confidence bounds on the unknown reliability parameters to guide deferral decisions, and establishes matching lower bounds, showing that these rates are optimal up to logarithmic factors.
Vasileios Saketos, William Réveillard, Alexandre Proutière et al.· 0 citations
Real-Time Image Enhanced CNN (RIECNN) for Traffic Sign Recognition is a real-time, novel approach that tackles multiple, diverse traffic sign datasets, and out-performs the state-of-the-art architectures in terms of recognition rate and execution time.
Reem Abdel-Salam, Rana Mostafa, Ahmed H. Abdel-Gawad· Neural computing & applicati...· 40 citations· ⚡1
