Knowledge catalogue
Appreciate it when the AI doomer crowd occasionally lets the mask slip a little (Allen is a co-founder of the anti-AI group Humans First and frequent guest on conservative podcasts pushing, uh, Unabom
This post reflects on how Pixar films resonate differently with adults, particularly uncles, compared to children, suggesting that mature viewers gain deeper emotional appreciation for themes of respo
The power of Trump, Putin, and Netanyahu appears to be waning. 'Plummeting approval ratings for these three poisonous comrades-in-arms show voters are demoralized and tiring of forever wars.' https://
The salvation is Project Tapestry https://thealliance.ai/projects/tapestry I don't think people understand just how bad it will be if an American open source champion doesn't emerge soon and the big l
The Top AI Papers of the Week (May 11 - May 17) - AEvo - δ-mem - AutoTTS - AI Co-Mathematician - Lighthouse Attention - Is Grep All You Need? - A Geometric Calculator Inside a Neural Network Read on f
1/3 My time at Meta FAIR will soon come to a close. I joined nearly two years ago full-time to help advance LLM reasoning. It has been a remarkable journey working with and leading an exceptionally ta
I cannot provide a reliable summary for this entry. The title appears to be a social media post containing political rhetoric rather than factual information suitable for a knowledge base. Without acc
I don’t know why data centers have become this generations nuclear power. Unlike nuclear power, there is a 0% chance that a data center can lead to any sort of disaster scenario. This project in Utah
I just learned that the 'data centers are using our water!' bullshit started because of a book called Empire of AI by Karen Hao in which she totally fucks up the math when determining how much water t
If you're not obsessed with the research problem you're working on, for its own sake, you're unlikely to succeed. Intrinsic motivation is far more powerful than external rewards. An Econ PhD student a
KDD 2026 Cycle 2 Results covers the announcement of review decisions and outcomes from the second submission cycle of KDD 2026, which accepts papers across multiple tracks including Research, Applied
Trump disparages the European Union as a collective force against the United States, but his threats, tariffs, and arbitrary conduct have done more than anything else in recent years to unify Europe.
arXiv:2304.03641v4 Announce Type: replace-cross Abstract: Nonsmooth composite optimization with orthogonality constraints has a wide range of applications in statistical learning and data science. How
arXiv:2605.14949v1 Announce Type: new Abstract: Carotid atherosclerosis is a major contributor to ischemic stroke and transient ischemic attack. Conventional ultrasound assessment is commonly based on
arXiv:2605.14360v1 Announce Type: cross Abstract: Wearable devices capture physiological and behavioral data with increasing fidelity, but the psychological context shaping these outcomes is difficult
arXiv:2605.14929v1 Announce Type: new Abstract: Scaled Outer Product (SOP) is a post-training quantization methodology for large language model weights, designed to deliver near-lossless fidelity at 4
arXiv:2605.14802v1 Announce Type: new Abstract: Large language models often suffer from fact loss, timeline confusion, persona drift, and reduced stability during long-range interaction, especially un
arXiv:2605.13858v1 Announce Type: cross Abstract: Large Language Models have demonstrated remarkable capabilities in generating contextually relevant and grammatically correct text. However, they fund
arXiv:2605.14917v1 Announce Type: new Abstract: Active learning for continuous regression has lacked an acquisition function that targets epistemic uncertainty when the predictive distribution is mult
arXiv:2605.14860v1 Announce Type: cross Abstract: Training deep neural networks at scale can benefit from domain decomposition, where the network is split into subdomains trained in parallel and coupl
arXiv:2605.14426v1 Announce Type: cross Abstract: Reliable precipitation monitoring is essential for disaster risk reduction, water resources management, and agricultural decision-making. Multi-source
arXiv:2605.14147v1 Announce Type: new Abstract: Objective: The primary goal of this study was to systematically examine the impact of commonly used imbalance handling methods (IHMs) on predictive perf
arXiv:2605.13943v1 Announce Type: new Abstract: Contrastive learning (CL) aims to preserve relational structure between samples by learning representations that reflect a similarity graph. Yet, the ge
arXiv:2602.05319v3 Announce Type: replace Abstract: Sequential probabilistic inference from streaming observations requires modeling distributions over future trajectories as new observations arrive.
arXiv:2605.14983v1 Announce Type: cross Abstract: An index is a function that given an election outputs a value between 0 and 1, indicating the extent to which this election has a particular feature.
arXiv:2605.14761v1 Announce Type: new Abstract: Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI. Various deep learning (DL)-based models have been pr
arXiv:2605.14327v1 Announce Type: cross Abstract: Drug-drug interaction (DDI) prediction is a critical task in computational biomedicine, as adverse interactions between co-administered drugs can caus
arXiv:2605.14584v1 Announce Type: cross Abstract: Implicit solvent models are widely used to decrease the number of solvent degrees of freedom and enable the calculation of solvation energetics withou
America is eating its young. We’re a nation built on the greatness of our research universities, it’s what gave us the Manhattan Project, victory in the Cold War, over HIV/AIDS. Our future depends on
arXiv:2605.14393v1 Announce Type: new Abstract: We study analogical trajectory transfer, where the goal is to translate motion trajectories in one 3D environment to a semantically analogous location i
arXiv:2605.14587v1 Announce Type: cross Abstract: Extensive research has highlighted the severe threats posed by backdoor attacks to deep reinforcement learning (DRL). However, prior studies primarily
Any arguments against open source and open weights are mendacious and malicious by their very nature. Open source is the foundation of modern society worth 8.8 trillion to the economy and the foundati
arXiv:2605.14341v1 Announce Type: new Abstract: Existing diffusion models have made significant progress in generating realistic images. However, their direct adaptation to remote sensing imagery ofte
arXiv:2605.14518v1 Announce Type: new Abstract: Activation functions are central to deep networks, influencing non-linearity, feature learning, convergence, and robustness. This paper proposes the Ada
arXiv:2605.14255v1 Announce Type: cross Abstract: Industrial visual inspection systems increasingly rely on deep classifiers whose heatmap explanations may appear visually plausible while failing to i
arXiv:2605.14689v1 Announce Type: new Abstract: Deep learning has profoundly impacted domains such as computer vision and natural language processing by uncovering complex patterns in vast datasets. H
arXiv:2605.14242v1 Announce Type: cross Abstract: The monitoring of fetal heart rate (FHR) and the assessment of its variability are crucial for preventing fetal compromise and adverse outcomes. Howev
arXiv:2602.15249v2 Announce Type: replace-cross Abstract: This study examines the distribution of Artificial Intelligence (AI) research across European NUTS-3 regions during the period 2015-2024. Usin
arXiv:2605.05686v2 Announce Type: replace Abstract: Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM). We
arXiv:2506.01015v2 Announce Type: replace Abstract: Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio m
arXiv:2605.15082v1 Announce Type: cross Abstract: We study a prototypical situation when a learned predictor can discover useful low-dimensional structure in data, while using fewer samples than are n
arXiv:2508.11845v3 Announce Type: replace-cross Abstract: Bioacoustics, the study of sounds produced by living organisms, plays a vital role in conservation, biodiversity monitoring, and behavioral st
arXiv:2605.14883v1 Announce Type: cross Abstract: Mild traumatic brain injury (mTBI) is a prevalent condition that remains difficult to diagnose in its early stages. Oculomotor dysfunction is a well-e
arXiv:2605.14106v1 Announce Type: new Abstract: We investigate whether behavior cloning is sufficient to produce active perception in a structured object-finding task. A low-cost robot arm equipped wi
arXiv:2603.28205v2 Announce Type: replace Abstract: Aspect-Based Sentiment Analysis (ABSA) faces critical challenges due to representation entanglement and false-negative collisions in real-valued emb
arXiv:2605.14773v1 Announce Type: cross Abstract: Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly f
arXiv:2605.14169v1 Announce Type: new Abstract: Memory systems are critical for role-playing agents (RPAs) to maintain long-horizon consistency. However, existing RPA memory methods (e.g., profiling)
arXiv:2602.04265v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LL
arXiv:2605.13887v1 Announce Type: cross Abstract: Transformer-based Spiking Neural Networks (SNNs) integrate SNNs with global self-attention and have demonstrated impressive performance. However, exis
arXiv:2605.14569v1 Announce Type: new Abstract: Reconstructing dynamic visual experiences as videos from functional magnetic resonance imaging (fMRI) is pivotal for advancing the understanding of neur
arXiv:2605.14810v1 Announce Type: new Abstract: In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received strangely less attention than obstacle n
arXiv:2512.11484v1 Announce Type: cross Abstract: This paper reveals and exploits a critical security vulnerability: the electromagnetic (EM) side channel of capacitive touchscreens leaks sufficient i
arXiv:2605.15141v1 Announce Type: new Abstract: Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation me
arXiv:2605.15133v1 Announce Type: new Abstract: Causal inference, estimating causal effects from observational data, is a fundamental tool in many disciplines. Of particular importance across a variet
arXiv:2602.09969v2 Announce Type: replace Abstract: We study a canonical multi-task demand-learning problem motivated by retail pricing, where a firm seeks to estimate heterogeneous linear price-respo
arXiv:2602.04473v2 Announce Type: replace Abstract: Recently, diffusion models have brought novel insights to pan-sharpening and notably boosted fusion precision. However, most existing models perform
arXiv:2202.05568v2 Announce Type: replace-cross Abstract: PAC-Bayes generalisation bounds are derived via change-of-measure inequalities that transfer concentration properties from a reference measure
arXiv:2605.14461v1 Announce Type: new Abstract: Existing object removal tools often rely on manual masks or text prompts, making precise removal difficult for non-expert users in complex scenes and of
arXiv:2511.14751v2 Announce Type: replace Abstract: We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the
arXiv:2605.14988v1 Announce Type: new Abstract: Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relation