Knowledge catalogue
arXiv:2604.22405v1 Announce Type: new Abstract: K-plane clustering (KPC), hyperplane clustering, and mixture regression all essentially fall within the same class of problems. This problem can be conc
arXiv:2604.22040v1 Announce Type: new Abstract: Localization for autonomous vehicles on highways remains under-explored compared to urban roads, and state-of-the-art methods for urban scenes degrade w
arXiv:2604.22520v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensi
This post compares TensorRT-LLM and llama.cpp (GGUF) as inference frameworks for running coding agents like Cline and RooCode on RTX 5090 GPUs, examining the tradeoff between inference speed and VRAM
This post documents a technical demonstration of running the large Qwen3.5-397B-A17B model across distributed hardware using llama.cpp with advanced networking protocols. The approach leverages 4-bit
Safety and innovation are not mutually exclusive: for many companies, especially in high-trust industries, AI’s risks are also a hindrance to adoption. In this op-ed in the @FT, I underscore that Euro
Sam Altman cannot be trusted. • The OpenAI board fired him because he was not always honest with them. They said he should not control powerful AI. • A major report talked to over 100 people and saw s
arXiv:2604.22162v1 Announce Type: new Abstract: Automated sports analysis demands robust multi-object tracking (MOT), yet segmentation-based methods often struggle with mask errors and ID switches in
Paresh Dave / Wired: San Francisco public records: in 2024, Salesforce and Airbnb were among the top tech spenders in the city's 10B program, which lets them hire police officers — A recent attack on
Scam Altman Interesting how it works Elon puts up his own money, rounds up the absolute best AI talent on the planet, leverages every connection he has to secure serious resources, and launches OpenAI
Scam Altman and Greg Stockman stole a charity. Full stop. Greg got tens of billions of stock for himself and Scam got dozens of OpenAI side deals with a piece of the action for himself, Y Combinator s
Scam Altman didn’t tell the OpenAI board that he OWNED the OpenAI Startup Fund. Altman lied in congressional testimony that he didn’t have financial gain from OpenAI. Ex-board member of OpenAI calls S
Scam Altman owned the OpenAI Startup fund while simultaneously lying to the world that he didn’t financially benefit from OpenAI The main difference between Elon Musk and Scam Altman: Elon Musk actual
arXiv:2509.25003v2 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of t
arXiv:2503.12507v3 Announce Type: replace Abstract: Despite their success, Segment Anything Models (SAMs) experience significant performance drops on severely degraded, low-quality images, limiting th
arXiv:2603.29171v3 Announce Type: replace Abstract: Accurate segmentation of brain tissues such as gray matter and white matter from magnetic resonance imaging is essential for studying brain anatomy,
arXiv:2604.22374v1 Announce Type: new Abstract: Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mism
arXiv:2604.22338v1 Announce Type: cross Abstract: Depthwise separable convolutional (DSConv) layers have been successfully applied to deep learning (DL)-based joint source-channel coding (JSCC) scheme
arXiv:2511.17388v2 Announce Type: replace Abstract: Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (extit{RoPE}) encode positions through
arXiv:2511.14427v3 Announce Type: replace-cross Abstract: Effective contact-rich manipulation requires robots to synergistically leverage vision, force, and proprioception. However, Reinforcement Lear
arXiv:2604.22269v1 Announce Type: cross Abstract: This paper presents a semantic-enhanced receiver framework for transmitting natural language sentences over noisy wireless channels using multiple sho
arXiv:2603.02709v2 Announce Type: replace-cross Abstract: We propose a novel framework for sensory-aware sequential recommendation that enriches item representations with linguistically extracted sens
German robotics startup Sereact GmbH announced today that it has raised 110 million in new funding to scale up its artificial intelligence “robotic brain” platform and expand into the U.S. Founded in
arXiv:2510.05971v3 Announce Type: replace Abstract: The generalization of the Transformer architecture via MetaFormer has reshaped our understanding of its success in computer vision. By replacing sel
arXiv:2604.22134v1 Announce Type: new Abstract: Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedag
arXiv:2604.22072v1 Announce Type: cross Abstract: Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clien
arXiv:2604.22027v1 Announce Type: cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a
arXiv:2604.22170v1 Announce Type: new Abstract: Recommender Systems~(RS) have been shown to be vulnerable to injective attacks, where attackers inject limited fake user profiles to promote the exposur
.@shaunmmaguire says Elon Musk’s X acquisition was in service of civilizational-scale missions. 'I truly believe, like in my soul, that he is trying to help humanity.' 'He has these goals. Like back u
arXiv:2509.24004v2 Announce Type: replace Abstract: Generating high-fidelity 3D head avatars from a single image is challenging, as current methods lack fine-grained, intuitive control over expression
arXiv:2604.22065v1 Announce Type: new Abstract: We present Selective Non-Gaussian Refinement (SNGR), a SLAM framework that augments iSAM2 with targeted nested sampling on windows where Gaussian approx
Sam Altman expresses satisfaction with the positive reception of OpenAI's 5.5 release, highlighting that developer feedback and builders finding value in OpenAI's tools is particularly rewarding to hi
arXiv:2604.22355v1 Announce Type: new Abstract: Classical ReLU-based Input Convex Neural Networks (ICNNs) are equivalent to the optimal value functions of Linear Programming (LP). This intrinsic struc
arXiv:2604.21984v1 Announce Type: new Abstract: We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image
arXiv:2604.22558v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation. While Reinforcement Learni
arXiv:2604.22080v1 Announce Type: new Abstract: LLM-based agents are rapidly being adopted for scientific data analysis, automating tasks once limited by human time and expertise. This capability is o
arXiv:2604.22038v1 Announce Type: new Abstract: We define and investigate source-modality monitoring -- the ability of multimodal models to track and communicate the input source from which pieces of
Zac Bowden / Windows Central: Sources detail Microsoft's “Windows K2”, an ongoing initiative to address major Windows 11 user complaints about AI features, OS bloat, performance, and more — Microsoft
Financial Times: Sources: some UK officials fear Keir Starmer's plan for closer EU ties risks the US-UK alliance, and worry the UK may be forced to adopt the EU's AI regulation — Officials concerned a
arXiv:2604.22136v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly issue API calls that mutate real systems, yet many current architectures pass stochastic model outputs
arXiv:2604.22409v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence
Speech translation in Google Meet is now rolling out to mobile devices I just encountered this feature via a 'try this out now' prompt in a Google Meet meeting. It kind-of worked! This is Google's imp
arXiv:2604.22753v1 Announce Type: new Abstract: Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, asse
arXiv:2604.22575v1 Announce Type: new Abstract: Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenec
arXiv:2604.22109v1 Announce Type: cross Abstract: Large language models (LLMs) possess strong persuasive capabilities that outperform humans in head-to-head comparisons. Users report consulting LLMs t
Bloomberg: Spotify partners with Peloton to offer Premium subscribers access to curated playlists and 1,400+ ad-free fitness classes, its first foray into fitness content — Spotify Technology SA is no
arXiv:2604.22686v1 Announce Type: new Abstract: We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly pred
arXiv:2604.22438v1 Announce Type: cross Abstract: Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing appr
arXiv:2509.22630v3 Announce Type: replace-cross Abstract: Recurrent neural networks (RNNs), such as linear attention and state-space models, have gained popularity due to their constant per-token comp
arXiv:2604.22282v1 Announce Type: new Abstract: Knowledge Graph-based Question Answering (KGQA) plays a pivotal role in complex reasoning tasks but remains constrained by two persistent challenges: th
Stop blaming the users. It’s not that simple: People keep blaming the users for the growing number of vibe-coded reasoners. Doing so is *half* right. Users *are*screwing up - by letting vibe coded stu
arXiv:2604.22649v1 Announce Type: cross Abstract: Objective: Decoding visual information from electroencephalography (EEG) is an important problem in neuroscience and brain-computer interface (BCI) re
Recent research found that participants exposed to infrasound reported increased irritation, unease, and elevated stress levels regardless of other conditions. While infrasound appears to be one contr
arXiv:2604.22156v1 Announce Type: cross Abstract: Purpose: Accurate assessment of the Critical View of Safety (CVS) during laparoscopic cholecystectomy is essential to prevent bile duct injury, a comp
This post discusses a developer's weekend project combining soju and seafood broil with noodles while working on building custom AI agents using Ollama's pi-powered infrastructure and OpenAI models. I
Super ZSNES is a modern SNES emulator created by two of the original ZSNES developers, zsKnight and _Demo_, which has been rewritten from scratch as a GPU-powered successor. The emulator uses GPU acce
arXiv:2604.22452v1 Announce Type: new Abstract: Collective intelligence refers to the ability of a group to achieve outcomes beyond what any individual member can accomplish alone. As large language m
arXiv:2510.11586v2 Announce Type: replace Abstract: Many in-silico simulations of human survey responses with large language models (LLMs) focus on generating closed-ended survey responses, whereas LL
.@swyx on whether AI infrastructure has finally stabilized: Media Always enjoy getting to chat with @swyx on our annual cross-episode with @latentspacepod on the state of AI. We hit on what’s shifted,
arXiv:2601.12430v2 Announce Type: replace Abstract: Vision-language model (VLM) hallucination is commonly linked to imbalanced allocation of attention across input modalities: system, image and text.