arXiv:2110.01950v3 Announce Type: replace Abstract: We study the classification problem for high-dimensional data with $n$ observations on $p$ features where the $p times p$ covariance matrix $Sigma$ exhibits a spiked eigenvalue structure and the vector $zeta$, given by the difference between the {em whitened} mean vectors, is sparse. We analyze an adaptive classifier (adaptive with respect to the sparsity $s$) that first performs dimension reduction on the feature vectors prior to classification in the dimensionally reduced space, i.e., […]

Ver mais

In-context learning (ICL) is a valuable capability exhibited by Transformers pretrained on diverse sequence tasks. However, previous studies have observed that ICL often conflicts with the model’s inherent in-weight learning (IWL) ability. By examining the representation space learned by a toy model in synthetic experiments, we identify the shared encoding space for context and samples in Transformers as a potential source of this conflict. To address this, we modify the model architecture to separately encode the context and […]

Ver mais

arXiv:2509.13805v3 Announce Type: replace-cross Abstract: Foundation models have revolutionized natural language processing through a “train once, deploy anywhere” paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation Model (PFM) would be transformative – democratizing access to high-fidelity simulations, accelerating scientific discovery, and eliminating the need for specialized solver development. Yet current physics-aware machine learning approaches remain fundamentally limited to single, narrow domains and require retraining for each new system. […]

Ver mais

arXiv:2602.15856v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge and is widely applied to Web-related tasks. However, its scalability is hindered by excessive context length and redundant retrievals. Recent research on soft context compression aims to address this by encoding long documents into compact embeddings, yet they often underperform non-compressed RAG due to their reliance on auto-encoder-like full-compression that forces the encoder to compress all document information regardless of relevance […]

Ver mais

I use AI tools every day. I think they’re genuinely brilliant. I hand Claude a disorganized pile of research notes and it finds connections I missed. I give it a rough thesis and it stress-tests it from angles I hadn’t considered. I’ve built entire websites, course curricula, and client deliverables with AI assistance. The technology is real, it’s powerful, and it has already changed how I work. But unless there is a serious breakthrough, AI is not ready […]

Ver mais

There is an entire category of commercial enterprise whose business model consists of hunting down small website operators and locating images of questionable or marginal legal exposure. These companies then threaten operators with financial demands that bear no rational relationship to any actual harm suffered, despite the fact that in the overwhelming majority of cases no meaningful financial harm or loss has occurred at all. We are speaking, to be precise, about companies such as Visual Rights Group, Copyright Agent, […]

Ver mais

Running is a widely practiced activity but shows a high incidence of knee injuries, especially Patellofemoral Pain Syndrome (PFPS) and Iliotibial Band Syndrome (ITBS). Identifying gait patterns linked to these injuries can improve clinical decision-making, which requires precise systems capable of capturing and analyzing temporal kinematic data. This study uses optical motion capture systems to enhance detection of injury-related running patterns. We analyze a public dataset of 839 treadmill recordings from healthy and injured runners to evaluate how […]

Ver mais

Anthropic defines “run-rate revenue” in two parts. Use the last 28 days of sales ⁠from customers charged on a consumption basis and multiply it by 13. Then, multiply the monthly subscription take by 12, ​and add the two together. — Karen Kwok for Reuters Breakingviews, citing “a person familiar with the matter” Tags: anthropic, ai

Ver mais