Ward: Newsss

350

Boosting t-SNE Efficiency for Sequencing Data: Insights from Kernel Selection

arXiv:2512.15900v1 Announce Type: new
Abstract: Dimensionality reduction techniques are essential for visualizing and analyzing high-dimensional biological sequencing data. t-distributed Stochastic Neighbor Embedding (t-SNE) is widely used for this purpose, traditionally employing the Gaussian kern…

320

Can Transformers overcome the lack of data in the simulation of history-dependent flows?

arXiv:2512.16305v1 Announce Type: cross
Abstract: It is well known that the lack of information about certain variables necessary for the description of a dynamical system leads to the introduction of historical dependence (lack of Markovian character of the model) and noise. Traditionally, scienti…

320

The Emergence of Chunking Structures with Hierarchical RNN

arXiv:2309.04919v2 Announce Type: replace
Abstract: In Natural Language Processing (NLP), predicting linguistic structures, such as parsing and chunking, has mostly relied on manual annotations of syntactic structures. This paper introduces an unsupervised approach to chunking, a syntactic task tha…

321

MACL: Multi-Label Adaptive Contrastive Learning Loss for Remote Sensing Image Retrieval

arXiv:2512.16294v1 Announce Type: new
Abstract: Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article, Multi-Label Adaptive…

218

From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding

arXiv:2510.02262v2 Announce Type: replace
Abstract: Video Large Language Models (VLMs) have achieved strong performance on various vision-language tasks, yet their practical use is limited by the massive number of visual tokens produced from raw video frames, which quickly exhausts the model's cont…

242

Inside enterprise AI’s turning point: 31 interviews on theCUBE that defined 2025

TheCUBE spent 2025 talking directly with top tech executives as they worked through how computing is being rebuilt inside their organizations, driven by real-world constraints rather than abstract roadmaps. Across those conversations, a consistent shift emerged away from theory and toward execution.…

213

Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection

arXiv:2512.16905v1 Announce Type: new
Abstract: Recent advances in Text-to-Image (T2I) generative models, such as Imagen, Stable Diffusion, and FLUX, have led to remarkable improvements in visual quality. However, their performance is fundamentally limited by the quality of training data. Web-crawl…

222

Detailed balance in large language model-driven agents

Comments

230

MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions

arXiv:2507.21503v3 Announce Type: replace
Abstract: Recently Multimodal Large Language Models (MLLMs) have achieved considerable advancements in vision-language tasks, yet produce potentially harmful or untrustworthy content. Despite substantial work investigating the trustworthiness of language mo…

218

Roomba rival bets on AI to clean up market for robot vacuum cleaners

Roborock chief says innovations such as robotic arms and dog excrement recognition are key to survival

209

AdaGradSelect: An adaptive gradient-guided layer selection method for efficient fine-tuning of SLMs

arXiv:2512.15764v1 Announce Type: new
Abstract: Large Language Models (LLMs) can perform many NLP tasks well, but fully fine-tuning them is expensive and requires a lot of memory. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA reduce this cost by adding small low-rank updates to frozen…

211

Provable optimal transport with transformers: The essence of depth and prompt engineering

arXiv:2410.19931v3 Announce Type: replace
Abstract: Despite their empirical success, the internal mechanism by which transformer models align tokens during language processing remains poorly understood. This paper provides a mechanistic and theoretical explanation of token alignment in LLMs. We fir…

219

Generation is Required for Data-Efficient Perception

arXiv:2512.08854v2 Announce Type: replace
Abstract: It has been hypothesized that human-level visual perception requires a generative approach in which internal representations result from inverting a decoder. Yet today's most successful vision models are non-generative, relying on an encoder that …

210

Preparing Future-Ready Learners: K12 Skills Shift and GenAI EdTech Innovation Direction

arXiv:2512.16428v1 Announce Type: new
Abstract: Since Generative AI came out it has quickly embedded itself in our social fabric, triggering lots of discussions, predictions, and efforts from research, industry, government and capital market to experiment and embrace the technology. The question fo…

211

A Network Arena for Benchmarking AI Agents on Network Troubleshooting

arXiv:2512.16381v1 Announce Type: new
Abstract: Agentic systems, powered by Large Language Models (LLMs), assist network engineers with network configuration synthesis and network troubleshooting tasks. For network troubleshooting, progress is hindered by the absence of standardized and accessible …

210

Radiology Report Generation with Layer-Wise Anatomical Attention

arXiv:2512.16841v1 Announce Type: new
Abstract: Automatic radiology report generation is a promising application of multimodal deep learning, aiming to reduce reporting workload and improve consistency. However, current state-of-the-art (SOTA) systems - such as Multimodal AI for Radiology Applicati…

128

We ran Anthropic’s interviews through structured LLM analysis

Comments

120

Muon is Provably Faster with Momentum Variance Reduction

arXiv:2512.16598v1 Announce Type: cross
Abstract: Recent empirical research has demonstrated that deep learning optimizers based on the linear minimization oracle (LMO) over specifically chosen Non-Euclidean norm balls, such as Muon and Scion, outperform Adam-type methods in the training of large l…

122

DSO: Direct Steering Optimization for Bias Mitigation

arXiv:2512.15926v1 Announce Type: new
Abstract: Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Yet, VLM decisions are influenced by the perceived d…

122

Explainable AI in Big Data Fraud Detection

arXiv:2512.16037v1 Announce Type: new
Abstract: Big Data has become central to modern applications in finance, insurance, and cybersecurity, enabling machine learning systems to perform large-scale risk assessments and fraud detection. However, the increasing dependence on automated analytics intro…