Knowledge catalogue
arXiv:2603.29245v3 Announce Type: replace Abstract: Monocular building height estimation from optical imagery is important for characterizing urban vertical structure, yet remains challenging due to t
Enterprises are increasingly evaluating alternative cloud providers beyond the major hyperscalers (AWS, Azure, Google Cloud) due to cost, performance, and vendor lock-in concerns. This shift reflects
arXiv:2606.21579v1 Announce Type: new Abstract: Procedural mistake detection is important for quality control and user assistance across many disciplines. Recent work in this field has achieved signif
arXiv:2606.22911v1 Announce Type: cross Abstract: Multi-zone HVAC control is a spatial decision problem in which indoor thermal evolution and control decisions depend not only on outdoor conditions an
arXiv:2606.23472v1 Announce Type: cross Abstract: Time series classification involves learning a mapping from a continuous, temporally ordered sequence of real-valued observations to a discrete respon
arXiv:2506.08026v3 Announce Type: replace-cross Abstract: Real-time market prediction services need correct predictions before a decision deadline; a correct prediction delivered late is not a usable
arXiv:2606.20748v1 Announce Type: new Abstract: Humanoid robots are emerging as co-workers in smart manufacturing, yet their dynamic, human-like movements introduce safety risks that differ fundamenta
arXiv:2606.22333v1 Announce Type: cross Abstract: A-mode ultrasound (US) has emerged as a promising modality for hand and wrist motion tracking. Prior works have mainly addressed static gesture classi
arXiv:2606.20131v2 Announce Type: replace Abstract: We present TriFlow, a new generative approach for producing compact 3D meshes with artist-like triangle topology directly from input geometry condit
arXiv:2606.13714v2 Announce Type: replace Abstract: Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent vi
arXiv:2606.23371v1 Announce Type: new Abstract: For imitation learning in robotic manipulation, high data collection costs result in the scarcity of high quality data. In this paper, we leverage the i
arXiv:2606.21185v1 Announce Type: cross Abstract: There is a precise sense in which drawing causal inferences from observational data is hard, even when identifiability is assumed. In particular, Robi
arXiv:2606.21385v1 Announce Type: new Abstract: This paper explores unsupervised disentangled representation learning from a functional perspective. We define latent concepts as factors that influence
arXiv:2606.21700v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) aims to learn a target-domain classifier from labeled source data and unlabeled target data under distribution shif
arXiv:2603.18581v2 Announce Type: replace-cross Abstract: With the advent of system-in-package (SiP) chiplet-based design and heterogeneous 2.5D/3D integration, thermal-induced warpage has become a cr
arXiv:2601.04687v2 Announce Type: replace Abstract: Cryptocurrency trading increasingly depends on timely integration of heterogeneous web information and market microstructure signals to support shor
Vector search is a retrieval method that converts unstructured data (text, images, audio) into numerical vector representations and finds similar items by comparing vectors in high-dimensional space,
arXiv:2106.06998v4 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagat
arXiv:2606.19340v2 Announce Type: replace Abstract: We present ZeroDex, a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans f
B9755 is a release of llama.cpp, a tool for LLM inference in C/C++ . The release represents a specific build version in the active development of the project, continuing the iterative improvements to
Release b9760 of llama.cpp includes a server refactoring/generalization of the input file schema and wire-up of input_video with raw base64 support. The release includes multiple build variants across
A developer created a local codebase memory system for agentic integrated development environments (IDEs) using Ollama and ChromaDB, enabling AI-assisted coding without reliance on cloud services. The
Together AI conducted a blind test comparing two landing pages—one created by GLM 5.2 and one by Opus 4.8—to evaluate whether users could distinguish between AI-generated designs. The test highlights
This episode likely discusses red-teaming methodologies and adversarial testing approaches in AI systems, featuring security researchers Zico Kolter and Matt Fredrikson from Carnegie Mellon University
Technological revolutions rarely destroy industries. More often, they destroy the reason those industries used to exist. Photography did not destroy painting. It destroyed painting’s monopoly on reali
The advanced civilizations of sci-fi legend (Banks, Asimov, etc) have some form of simulation to guide society. @joon_s_pk is taking a crack at building that simulator with @simile_ai. As Joon's cofou
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. For those of you enjoying your summer unaware of Anthropic’s l
A fundamental problem with extending Codex/Cowork/Code to all knowledge work is that they remain very 'software-brained' where the end result (the software) is what is important & that code serves as
Release b9754 of llama.cpp implements an AC parser for stricter grammar generation in the common/peg module , with builds available across multiple platforms including macOS, Linux, Android, and Windo
Clem Delangue, CEO of Hugging Face, celebrated reaching nearly 1,000 followers on the platform, marking a milestone in the company's social media presence. The post reflects growth in community engage
Samsung Electronics deployed OpenAI's ChatGPT and Codex tools to its employees, integrating AI capabilities into their workforce operations. This implementation likely enabled Samsung staff to leverag
This work demonstrates that frozen image encoders (neural networks trained on static images without video or physics supervision) contain implicit geometric signals that correspond to physical plausib
1.3 GW secured. 6 GW needed. The gap is the story. Anjney Midha @AnjneyMidha runs AMP, a grid operator that pools AI compute for frontier labs. His own pipeline shows 1.3 gigawatts secured against an
A humorous post listing essential items for desert island survival that prioritizes modern technology, including solar power generation, a Mac Studio computer with substantial storage capacity, and GL
Hermes Agent has a new Blank Slate setup mode. The default Quick/Full setup modes work great for most, but if you would rather build your agent from the ground up you can now start with just a provide
KernelBench-Hard and KernelBench-Mega results are in. Reasoning traces are open. Thanks to @calebfahlgren for showing me this feature. Scores published to http://kernelbench.com. I'll make an official
Luke Alonso has released a quantized version (NVFP4 format) of GLM 5.2 totaling 467GB in size, which can be deployed across four DGX Spark systems with an estimated hardware cost of approximately $20,
Many people think any given ML project is 99% training. In reality, it’s 50% evaluation, 40% data cleaning, 8% integration, and 2% training. The first two set the noise floor for learning. No ML magic
So true Many people think any given ML project is 99% training. In reality, it’s 50% evaluation, 40% data cleaning, 8% integration, and 2% training. The first two set the noise floor for learning. No
Yeah I agree. The big winner is going to be Ollama: I've offloaded all my supervisory, code review, and ontology learning agents to my $20 a month Ollama subscription, because I keep getting weight li
I suspect that companies underestimate the value of using higher intelligence for tasks where weaker AIs seem to be good enough to hit KPIs at a lower price. At least build architectures where you can
arXiv:2606.12160v1 Announce Type: new Abstract: In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal lo
arXiv:2606.11222v1 Announce Type: new Abstract: How much meaning does a text carry? Shannon's theory measures uncertainty over symbols and is intentionally indifferent to meaning, while pairwise metri
arXiv:2606.12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing approaches rely heavily on first-order mirror-descent
arXiv:2606.12371v1 Announce Type: new Abstract: Object detection and instance segmentation tasks are closely related. Existing top-down instance segmentation methods usually follow a detect-then-segme
arXiv:2606.11236v1 Announce Type: cross Abstract: Training deep spiking neural networks (SNNs) remains challenging due to sharp loss landscapes and temporal inconsistency caused by surrogate gradients
arXiv:2606.11615v1 Announce Type: new Abstract: The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent. To addre
arXiv:2606.12142v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring, and emergency response. However, mos
arXiv:2606.11869v1 Announce Type: cross Abstract: Custom AI agents areagents that live inside their own application, talk to their own data and tools, enforce their own security boundaries, and carry
arXiv:2606.12003v1 Announce Type: new Abstract: Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on
arXiv:2606.11533v1 Announce Type: cross Abstract: The advancement of AI capabilities compels researchers and the public to be more aware of its potential worldwide impact. A pressing near-term concern
arXiv:2606.12365v1 Announce Type: cross Abstract: We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics. High-quality, task-specif
arXiv:2606.11635v1 Announce Type: cross Abstract: For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral r
arXiv:2606.12059v1 Announce Type: new Abstract: We address transformer attention on energy-constrained physical substrates. Softmax attention requires exponentiation and global reduction, operations w
arXiv:2606.12258v1 Announce Type: new Abstract: Cross-domain day-night re-identification (ReID) is fundamentally challenged by the substantial visual appearance discrepancies between daytime and night
arXiv:2606.11578v1 Announce Type: new Abstract: Contactless body measurement technologies are becoming increasingly significant for smart health monitoring, digital health applications, and remote pat
arXiv:2606.12411v1 Announce Type: new Abstract: Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with
arXiv:2510.17816v2 Announce Type: replace-cross Abstract: Wi-Fi-based human activity recognition (HAR) provides substantial convenience and has emerged as a thriving research field, yet the coarse spa
arXiv:2606.11326v1 Announce Type: new Abstract: Recent feed-forward 3D reconstruction methods have demonstrated strong performance and flexibility in efficient end-to-end scene geometry estimation fro
arXiv:2606.12368v1 Announce Type: new Abstract: While monocular depth estimation has achieved significant progress, achieving generalized metric depth estimation for both narrow field-of-view (FoV) pe