Knowledge catalogue
arXiv:2605.06676v1 Announce Type: cross Abstract: Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compress
// LLMs Improving LLMs // Interesting progress the past of couple of weeks around self-improving AI agents. If autoresearch was interesting, you will like this read. (bookmark it) We've been hand-tuni
arXiv:2605.06809v1 Announce Type: new Abstract: Transformers dominate video recognition. They split videos into tokens, and processing them has expensive superlinear computational cost. Yet videos are
arXiv:2602.03797v2 Announce Type: replace Abstract: We present a new paradigm for creating random features to approximate bi-variate functions (in particular, kernels) defined on general manifolds. Th
arXiv:2605.06317v2 Announce Type: replace-cross Abstract: Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulatio
arXiv:2605.07140v1 Announce Type: cross Abstract: Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to inte
arXiv:2605.07660v1 Announce Type: new Abstract: Reinforcement-learning-based post-training has become a key approach for improving the reasoning ability of large language models, but its token-level l
arXiv:2605.06873v1 Announce Type: cross Abstract: Probabilistic conditioning is concerned with the identification of a distribution of a random variable X given a random variable Y. It is a cornerston
arXiv:2605.07572v1 Announce Type: new Abstract: When applying Bayesian optimization (BO) to scientific workflow, a major yet often overlooked source of uncertainty is the task itself -- namely, what t
arXiv:2605.06833v1 Announce Type: cross Abstract: Misbehavior detection in Vehicle-to-Everything (V2X) networks is a second line of defense against insider falsification attacks that cryptographic mec
arXiv:2602.03490v2 Announce Type: replace Abstract: Adaptive cognition requires structured internal models of objects and their relations. Predictive neural networks are often proposed to learn such w
arXiv:2605.08035v1 Announce Type: cross Abstract: Building a site-specific propagation model typically requires either ray-tracing over detailed 3D maps or dense measurement campaigns. Both approaches
arXiv:2605.07938v1 Announce Type: new Abstract: Single-cell representation learning (SCRL) from gene expression data offers a way to uncover the complex regulatory logic underlying cellular function.
arXiv:2605.07755v1 Announce Type: cross Abstract: The theory of state tracking in recurrent architectures has predominantly focused on expressive capacity: whether a fixed architecture can theoretical
arXiv:2605.07212v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a cornerstone of brain-computer interfaces and clinical neuroscience, yet deep learning models are typically trained a
This tutorial demonstrates how to implement full-text search functionality using Pinecone's vector database, using bird-related data as a practical example. It likely covers setting up Pinecone, index
arXiv:2602.03201v3 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) is sample-efficient but struggles in sparse reward settings. A critical bottleneck arises from the lack of
arXiv:2605.07908v1 Announce Type: cross Abstract: Belief functions are a powerful and popular framework for the mathematical characterisation of uncertainty, in particular in situations in which lack
arXiv:2405.00082v4 Announce Type: replace-cross Abstract: We study the problem of Hamiltonian structure learning from real-time evolution: given the ability to apply e^{-i Ht} for an unknown local Ham
arXiv:2605.07676v1 Announce Type: new Abstract: Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent struc
arXiv:2503.14998v3 Announce Type: replace Abstract: Contrastive learning methods in computer vision typically rely on augmented views of the same image or multimodal pretraining strategies that align
arXiv:2605.07086v1 Announce Type: new Abstract: Channel importance in vision networks is usually summarized by a single score. That summary hides two different questions: how much a channel is related
// The Memory Curse in LLM Agents // (bookmark it) Long histories apparently degrades agents as they become increasingly history-following and risk-minimizing. Across 7 LLMs and 4 social dilemma games
This is a tutorial on diffusion and flow matching, based on my previous postings here. I’ve made available the PDF, a python notebook for people to play with it, and the TEX source so hopefully one of
arXiv:2605.07471v1 Announce Type: new Abstract: Machine-learning models in high-energy physics are often trained on simulated data, where fully simulated samples are computationally expensive while fa
arXiv:2605.07922v1 Announce Type: new Abstract: Learning hierarchical features in Sparse Autoencoders (SAEs) is essential for capturing the structured nature of real-world data and mitigating issues l
arXiv:2509.22813v2 Announce Type: replace Abstract: State Space Models (SSMs) have emerged as efficient alternatives to Vision Transformers (ViTs), with VMamba standing out as a pioneering architectur
TurboQuant has drawn a lot of attention recently, but the accompanying evals didn't tell the full story. So we ran what I believe is the first comprehensive study of TurboQuant: where it helps, where
arXiv:2605.07470v1 Announce Type: new Abstract: Neural networks (NNs) are inherently multidimensional classifiers that learn complex, non-linear relationships among input observables. While their flex
arXiv:2605.07146v1 Announce Type: new Abstract: Underwater salient object detection (USOD) plays a vital role in marine vision tasks but remains fundamentally challenging due to severe visual degradat
arXiv:2508.06819v3 Announce Type: replace Abstract: The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as wel
arXiv:2605.07120v1 Announce Type: new Abstract: Template tasks have emerged as a clean testbed for asking whether transformers reason with abstract symbols rather than concrete token names. We study t
arXiv:2605.06831v1 Announce Type: cross Abstract: We theoretically study the hallucination phenomena in two canonical diffusion samplers: the stochastic Denoising Diffusion Probabilistic Model (DDPM)
The post discusses improvements in working with Horace (likely a tool or system) due to recent implementation of simultaneous speech capability in its underlying model. This advancement has made the i
Your AI Use Is Breaking My Brain Excellent, angry piece by Jason Koebler on how AI writing online is becoming impossible to avoid, filtering it is mentally exhausting and it's even starting to distort
As always, no insights and in personal capacity: The DeepMind unionization effort has very worthy goals it seems Maybe Google will finally grant GDM that /independent/ ethics oversight board that was
big 'Look what they need to mimic a fraction of our power' energy. the original DOOM impl is ~40k lines of C and a bit of assembly and is also a full software renderer. My Codex /goal that has been ru
If the AI models are so smart, why do I feel like I’m losing a few neurons every time I read a longer form content written by AI? We’ve come a long way but we still have long way to go. In terms of cl
Krysta Fauria / Associated Press: Anthropic, OpenAI, and other AI firms met with Hindu, Sikh, and Greek Orthodox leaders to draft principles on how to infuse models with ethics and morality — As conce
This post emphasizes a three-stage lifecycle for AI/LLM applications: evaluating systems before deployment to ensure quality, monitoring their performance in production to catch issues, and using the
I believe we'll achieve ASI, but it will be both narrow and finite in capability. We already have ASI in Go, Chess, some video games. In those domains, infinite amounts of training data can be generat
To anticipate that Anthropic will have 2T revenue in 2030 is a perfect example of the trillion pound baby fallacy. Just because a baby doubles in weight in its first four months doesn’t mean it will c
Google is rolling out updates to AI Overviews and AI Mode that include more direct links within responses and previews of websites to help users find trusted sources and original content more easily.
I gave a viral talk recently, and @swyx asked me to put something together to explain how I did it - to help future AIE speakers and anyone who wants to learn. I am, oddly, extremely qualified to do t
It's been 3 months since the 100x vibers started 100x vibin'! So, post your 25-years-of-work-equivalent project here, so we can signal boost and everyone can celebrate the Life's Work that you did in
Stability Matrix is a program designed to manage and run multiple stable diffusion interfaces, offering a centralized model checkpoint repository to install, uninstall, update, and switch between diff
'Technical writing completely changed my life.' - @trq212 In less than 2 years, Thariq (@AnthropicAI) cracked the code on writing technical articles that consistently pass 1M+ views. In this 15-min wo
Thank you to @robertwiblin for inviting me on the @80000Hours podcast to discuss the research progress we’re making at @LawZero_ to create safe-by-design AI systems. Our current approach, Scientist AI
Customer engagement is shifting from disconnected interactions to continuous, AI-driven experiences that span channels and adapt in real time — and unified data, orchestration and AI agents are rapidl
arXiv:2603.09789v2 Announce Type: replace Abstract: Accurate financial volatility forecasting is crucial but challenged by the non-linear, highly correlated nature of market data. Recently, quantum co
arXiv:2504.13614v2 Announce Type: replace-cross Abstract: The rapid growth of the internet has made personalized recommendation systems indispensable. Graph-based sequential recommendation systems, po
arXiv:2605.04193v1 Announce Type: cross Abstract: Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggl
arXiv:2605.04728v1 Announce Type: new Abstract: Recovering 3D human pose and shape from a single image remains a cornerstone of human-centric vision, yet most methods assume adult subjects and optimiz
arXiv:2605.04985v1 Announce Type: new Abstract: Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard tran
Can someone build the Reachy Mini app that lets it speak like Talkie from @AlecRad in a posh pre-1931 British voice? I want to hear a next-gen robot channeling the 1920s! Space: https://huggingface.co
arXiv:2605.05012v1 Announce Type: new Abstract: Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of stru
arXiv:2605.04052v1 Announce Type: cross Abstract: Low Earth orbit (LEO) satellites increasingly carry compute hardware capable of on-board processing, yet each satellite generates roughly two orders o
arXiv:2605.05136v1 Announce Type: new Abstract: Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen
arXiv:2408.09929v2 Announce Type: replace-cross Abstract: Inspired by the idea of Positive-incentive Noise (Pi-Noise or pi-Noise) that aims at learning the reliable noise beneficial to tasks, we scien
arXiv:2510.09885v5 Announce Type: replace Abstract: Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured text o