Knowledge catalogue
arXiv:2604.22442v1 Announce Type: new Abstract: We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M =20 shows increasing seed sens
If a major car company had AI fan boys and released a car with loose lug nuts and the wheels came off, after hyping it as the greatest thing ever, and a bunch of people died, those fan boys would say
arXiv:2507.03014v2 Announce Type: replace-cross Abstract: Large language models (LLMs) face significant copyright and intellectual property challenges as the cost of training increases and model reuse
Introducing our new work: “Learning to Orchestrate Agents in Natural Language with the Conductor” accepted at #ICLR2026 https://arxiv.org/abs/2512.04388 What if we trained an AI not to solve problems
Kimi K2.6 has achieved the top ranking on OpenRouter's weekly LLM leaderboard, marking a significant achievement for the model. The announcement expresses gratitude to developers using Kimi and indica
arXiv:2604.22302v1 Announce Type: new Abstract: Recent text-to-image (T2I) models have demonstrated impressive capabilities in photorealistic synthesis and instruction following. However, their reliab
arXiv:2508.05633v2 Announce Type: replace-cross Abstract: Live streaming platforms have become a dominant form of online content consumption, offering dynamically evolving content, real-time interacti
arXiv:2505.14990v3 Announce Type: replace Abstract: Often, multilingual language models are trained with the objective to map semantically similar content (in different languages) in the same latent s
Lately I've been having fun with running coding agents fully locally. The setup I landed on is: - Pi agent - Gemma 4 26B A4B - Server of choice: LM Studio/Ollama/llama.cpp I wrote a step-by-step guide
arXiv:2604.22056v1 Announce Type: new Abstract: Optimal wireless transmitter placement is a central task in radio-network planning, yet exhaustive search becomes prohibitively expensive at scale. This
arXiv:2508.10695v2 Announce Type: replace-cross Abstract: Personalization is crucial for enhancing both the effectiveness and user satisfaction of language technologies, particularly in information-se
arXiv:2411.08027v3 Announce Type: replace-cross Abstract: Most learning-based approaches to complex physical reasoning sidestep the crucial problem of parameter identification (e.g., mass, friction) t
arXiv:2601.08919v2 Announce Type: replace-cross Abstract: A good deal of recent research has focused on how Large Language Models (LLMs) may be used as judges in place of humans to evaluate the qualit
Loan processors spend 40–60% of their time reconciling income across tax returns, pay stubs, W-2s, and bank statements. We built an end-to-end pipeline that automates it with LlamaParse + the Claude A
arXiv:2604.22714v1 Announce Type: new Abstract: Internet photo collections exhibit an extremely long-tailed distribution: a few famous landmarks are densely photographed and easily reconstructed in 3D
arXiv:2604.22034v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) are a recent neural network architecture offering an alternative to Multilayer Perceptrons (MLPs) with improved expl
arXiv:2602.09329v2 Announce Type: replace Abstract: Quality benchmarks are essential for fairly and accurately tracking scientific progress and enabling practitioners to make informed methodological c
Last year we introduced new geospatial analytics capabilities integrated for BigQuery. Building on this, we announced an expanded suite of tools at Google Cloud Next ‘26, designed to help your busines
arXiv:2604.21935v1 Announce Type: new Abstract: Although language models demonstrate remarkable proficiency on mathematical benchmarks, it remains unclear whether this reflects true mathematical reaso
microsoft/VibeVoice VibeVoice is Microsoft's Whisper-style audio model for speech-to-text, MIT licensed and with speaker diarization built into the model. Microsoft released it on January 21st, 2026 b
Model page: https://ollama.com/library/deepseek-v4-pro Try it with Codex: ollama launch codex --model deepseek-v4-pro:cloud Try it with OpenClaw: ollama launch openclaw --model deepseek-v4-pro:cloud T
arXiv:2604.21937v1 Announce Type: new Abstract: Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specializ
arXiv:2604.22492v1 Announce Type: cross Abstract: Understanding social dominance in animal behavior is critical for neuroscience and behavioral studies. In this work, we explore the capability of Mult
arXiv:2604.22548v1 Announce Type: cross Abstract: Problem definition: Data-driven models in machine learning have enabled efficient management of production systems. However, a majority of machine lea
arXiv:2604.21991v1 Announce Type: cross Abstract: Multi-task optimization is a powerful approach for solving a large number of tasks in parallel. However, existing algorithms face distinct limitations
arXiv:2604.22239v1 Announce Type: cross Abstract: This paper introduces the task of analytical question answering over large, semi-structured document collections. We present MuDABench, a benchmark fo
arXiv:2604.22240v1 Announce Type: new Abstract: Generative world models increasingly rely on 4D occupancy for realistic autonomous driving simulation. However, existing generation frameworks depend on
arXiv:2604.22230v1 Announce Type: cross Abstract: Benchmark hacking refers to tuning a machine learning model to score highly on certain evaluation criteria without improving true generalization or fa
🚨 OpenAI just REMOVED the AGI clause that was a structural protection of OpenAI's charitable mission, while jury selection was happening today The 2019 capped-profit structure had three protections fo
arXiv:2604.22067v1 Announce Type: cross Abstract: Psychiatric intake is a sequential, high-stakes information-gathering process in which clinicians must decide what to ask, in what order, and how to i
arXiv:2604.22168v1 Announce Type: new Abstract: Here, we explore the problem of error propagation mitigation in modular digital twins as a sequential decision process. Building on a companion study th
arXiv:2511.05456v2 Announce Type: replace Abstract: Graph network-based simulators (GNS) have demonstrated strong potential for learning particle-based physics (such as fluids, deformable solids, and
ParseBench: A benchmark for document parsing agents @llama_index just shipped a benchmark with 2k verified pages for real enterprise documents. Benchmarks are the major underrated component in the ML
arXiv:2405.10138v2 Announce Type: replace Abstract: In this paper, we introduce the Polish Massive Text Embedding Benchmark (PL-MTEB), a comprehensive benchmark for text embeddings in the Polish langu
Jer / @lifeof_jer: PocketOS founder Jer Crane says a Cursor agent running Claude Opus 4.6 accidentally deleted a production database when it was working in a staging environment — An AI Agent Just Des
Processing loan applications traditionally takes a staggering amount of time going through paperwork - ~dozens of hours every month looking at the loan application and cross-checking it with user-subm
arXiv:2112.02604v3 Announce Type: replace-cross Abstract: Accurately modeling pedestrian intention and understanding driver decision-making processes are critical for the development of safe and socia
arXiv:2604.22507v1 Announce Type: new Abstract: Automated train operation on existing railway infrastructure requires robust camera-based perception, yet the railway domain lacks public benchmark suit
arXiv:2506.14831v3 Announce Type: replace Abstract: With the emergence of powerful data-driven methods in human trajectory prediction (HTP), gaining a finer understanding of multi-agent interactions l
arXiv:2604.22390v1 Announce Type: new Abstract: Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods stru
arXiv:2602.12469v2 Announce Type: replace Abstract: Deep ensemble methods often improve predictive performance, yet they suffer from three practical limitations: redundancy among base models that infl
arXiv:2604.22746v1 Announce Type: cross Abstract: ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over t
arXiv:2604.22063v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly utilized in clinical reasoning and risk assessment. However, their interpretive reliability in critical
arXiv:2604.22180v1 Announce Type: cross Abstract: Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in infor
arXiv:2604.22026v1 Announce Type: new Abstract: AI research pipelines now produce a growing share of publishable academic output, including work that meets existing peer-review standards for quality a
arXiv:2602.18734v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in ex
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
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
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: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: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:2604.22136v1 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
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:2604.22156v1 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
arXiv:2510.07632v2 Announce Type: replace Abstract: Frontier AI models have achieved remarkable progress, yet recent studies suggest they struggle with compositional reasoning, often performing at or
The DeepSeek V4 garbled output bug in open source inference engine is fixed in SGLang. To everyone affected over the weekend, sorry for the trouble. Huge thanks to @Ant_Group for landing the fix PR. I