⚡️⚡️Run Qwen3.6-27B locally! @UnslothAI
⚡️⚡️Run Qwen3.6-27B locally! @UnslothAI Qwen3.6-27B can now run locally! 💜 Run on 18GB RAM via Unsloth Dynamic GGUFs. Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks. GGUFs: htt
Knowledge catalogue
⚡️⚡️Run Qwen3.6-27B locally! @UnslothAI Qwen3.6-27B can now run locally! 💜 Run on 18GB RAM via Unsloth Dynamic GGUFs. Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks. GGUFs: htt
running 3 async deepagents in parallel for real time investigation for manufacturing plant downtime. I believe these are the most capable agents in the world right now @LangChain @hwchase17 @lguaman.
Runway meetup in Tokyo, Japan. Huge shoutout to Miho, Hero, and Yves for organizing a fantastic community get-together. Runway meetups are happening everywhere, we're getting closer to 100 meetups so
Reuters: S-1 excerpts: SpaceX says its total addressable market could be as much as 28.5T, with 26.5T from the AI sector, most of it from AI for businesses — Over the last quarter century, Elon Musk r
David Ha shared an enthusiastic post about receiving a Sakana AI branded mug, expressing joy with fish emoji decorations. The post appears to be a personal social media update celebrating Sakana AI me
arXiv:2604.20146v1 Announce Type: cross Abstract: Grounded Multimodal Named Entity Recognition (GMNER) aims to extract named entities and localize their visual regions within image-text pairs, serving
Salesforce Inc. said today it’s trying to break down the siloes that separate enterprise’s customer relationship management data from their productivity tools, specifically for artificial intelligence
arXiv:2512.08923v2 Announce Type: replace Abstract: We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in mul
arXiv:2510.15751v2 Announce Type: replace Abstract: While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network cali
arXiv:2505.02242v2 Announce Type: replace Abstract: Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computatio
Reuters: SAP reports Q1 revenue up 6% YoY to €9.56B, vs. €9.53B est., non-IFRS operating profit up 17% to €2.87B, cloud revenue up 19% to €5.96B; SAP up 10%+ after hours — Europe's largest software ma
arXiv:2604.19768v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit systematic miscalibration with rhetorical intensity not proportionate to epistemic grounding. This study tests th
arXiv:2604.20420v1 Announce Type: cross Abstract: AI research often emphasizes model design and algorithmic performance, while deployment and inference remain comparatively underexplored despite being
arXiv:2509.16002v2 Announce Type: replace-cross Abstract: A scalable and resource-efficient quantum reinforcement learning framework is presented that eliminates the linear qubit-scaling barrier in mu
arXiv:2604.20209v1 Announce Type: new Abstract: LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both i
arXiv:2604.19907v1 Announce Type: new Abstract: Recent agentic frameworks for 3D scene synthesis have advanced realism and diversity by integrating heterogeneous generation and editing tools. These to
arXiv:2601.12910v3 Announce Type: replace-cross Abstract: Discrepancies between scientific papers and their code undermine reproducibility, a concern that grows as automated research agents scale scie
arXiv:2604.20003v1 Announce Type: cross Abstract: The integration of single-cell proteomic data is often hindered by the fragmented nature of targeted antibody panels. To address this limitation, we i
arXiv:2604.20245v1 Announce Type: cross Abstract: Fundamental rate-distortion-perception (RDP) trade-offs arise in applications requiring maintained perceptual quality of reconstructed data, such as n
arXiv:2604.20311v1 Announce Type: cross Abstract: Micro-video popularity prediction (MVPP) aims to forecast the future popularity of videos on online media, which is essential for applications such as
arXiv:2512.08730v2 Announce Type: replace Abstract: Most existing methods for training-free open-vocabulary semantic segmentation are based on CLIP. While these approaches have made progress, they oft
arXiv:2604.20598v1 Announce Type: cross Abstract: Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it w
arXiv:2604.20413v1 Announce Type: new Abstract: Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is compl
arXiv:2604.19777v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context win
arXiv:2604.20601v1 Announce Type: new Abstract: We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language
arXiv:2604.20392v1 Announce Type: new Abstract: Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are comput
arXiv:2604.20169v1 Announce Type: new Abstract: We propose Semantic-Fast-SAM (SFS), a semantic segmentation framework that combines the Fast Segment Anything model with a semantic labeling pipeline to
arXiv:2509.00800v3 Announce Type: replace Abstract: Accurate 3D reconstruction in degraded imaging conditions remains a key challenge in photogrammetry and neural rendering. In underwater environments
arXiv:2604.19971v1 Announce Type: cross Abstract: Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can auto
arXiv:2604.20417v1 Announce Type: cross Abstract: We introduce Semantic Recall, a novel metric to assess the quality of approximate nearest neighbor search algorithms by considering only semantically
arXiv:2604.20128v1 Announce Type: new Abstract: Fusing a low resolution (LR) mosaiced hyperspectral image (HSI) with a high resolution (HR) panchromatic (PAN) image offers a promising avenue for video
senpai blogging!! Cursor and SpaceX: In search of a complete loop Quick notes on the deal: - the new AI lab meta of needing to own product and model in coding - why spacex and cursor need each other t
Jagmeet Singh / TechCrunch: Sensor Tower: India's mobile app IAP revenue crossed 300M in Q1, up 33% YoY, with non-gaming apps generating 200M+, much of it captured by global platforms — India's mobile
arXiv:2604.20039v1 Announce Type: new Abstract: Causal discovery through experimentation and intervention is fundamental to robust problem solving. It requires not just updating beliefs within a fixed
Claude's Opus 4.7 model was experiencing issues when used within Claude Code, and Anthropic's team was actively investigating the problems with plans to provide updates as they continued the rollout.
arXiv:2604.19888v1 Announce Type: new Abstract: Driver gaze estimation is essential for understanding the driver's situational awareness of surrounding traffic. Existing gaze estimation models use dri
arXiv:2604.20308v1 Announce Type: new Abstract: Graph neural networks face two fundamental challenges rooted in the linear structure of Euclidean vector spaces: (1) Current architectures represent geo
The Robot Report: Shenzhen-based Pudu Robotics, which makes commercial service robots, raised ~150M, bringing its total funding to 300M+, and says its valuation exceeds 1.5B — Pudu Technology Inc. tod
arXiv:2604.20436v1 Announce Type: cross Abstract: Generative AI (GenAI) is reshaping software engineering by shifting development from manual coding toward agent-driven implementation. While vibe codi
This article by Ethan Mollick likely discusses emerging capabilities and implications of GPT-5.5, OpenAI's next-generation language model, exploring how it represents advancement in AI technology and
arXiv:2604.20357v1 Announce Type: cross Abstract: Sign-language datasets are difficult to preprocess consistently because they vary in annotation schema, clip timing, signer framing, and privacy const
Reuters: Singapore is slowly emerging as a neutral ground for AI companies, offering an alternative place to build without worrying about US or Chinese regulations — Singapore is transforming from Eas
arXiv:2604.19793v1 Announce Type: new Abstract: LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering
arXiv:2604.20087v1 Announce Type: new Abstract: Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how
arXiv:2604.19807v1 Announce Type: new Abstract: In multi-criteria graph traversal, paths are compared via Pareto dominance, an ordering that identifies which paths are non-dominated, but says nothing
arXiv:2604.19946v1 Announce Type: new Abstract: Indoor localisation techniques suffer from attenuated Global Navigation Satellite System (GNSS) signals and from the accumulation of unbounded drift by
arXiv:2604.20161v1 Announce Type: new Abstract: Multi-task learning is effective for related applications, but its performance can deteriorate when the target sample size is small. Transfer learning c
arXiv:2509.15174v3 Announce Type: replace-cross Abstract: WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMAR
Written by: JP Glab, Tufail Ahmed, Josh Kelley, Muhammad Umair Introduction Google Threat Intelligence Group (GTIG) identified a multistage intrusion campaign by a newly tracked threat group, UNC6692,
So right now basically anyone with a 16GB VRAM card can go on @huggingface and download a model which BEATS Claude Sonnet 4.5, all running locally 🤯 LOOK AT THE WATER PARTICLES?? What are they doing i
arXiv:2604.19752v1 Announce Type: cross Abstract: Multi-agent AI systems exhibit emergent risks that no single agent produces in isolation. Existing safety frameworks rely on binary classifications of
arXiv:2604.19825v1 Announce Type: cross Abstract: State-of-the-art code generation frameworks rely on mental simulation, where LLMs internally trace execution to verify correctness. We expose a fundam
This post likely contains additional references and citations presented in footnote format, discussing topics related to a decade in review or retrospective analysis. The content appears to be from Sw
Bloomberg: Sources: AI coding firm Cognition is in early talks to raise hundreds of millions of dollars at a 25B valuation, up from 10.2B announced in September 2025 — Cognition AI Inc. is in early ta
Reuters: Sources: Bain Capital seeks to sell a stake of 40%+ in Bridge Data Centres in a deal that would value the Singapore-based data infrastructure builder at $5B — U.S. investment firm Bain Capita
Zijing Wu / Financial Times: Sources: DeepSeek is fundraising to keep its researchers, some of whom have left for rivals whose valuations have soared; it is targeting a $20B valuation — Chinese AI sta
Alastair Marsh / Bloomberg: Sources: Microsoft told carbon-removal project developers it is shelving contracts under negotiation; Microsoft has been a major backer of carbon capture tech — In the earl
ABC News: Sources: the US DOJ arrested a soldier involved in the capture of Nicolás Maduro for allegedly making $400K+ on Polymarket by betting on his removal from office — The bet was allegedly place
Reuters: Sources: Thoma Bravo prepares to hand over customer experience management company Medallia to creditors, leading to a ~$5.1B wipeout for Medallia's investors — Private equity firm Thoma Bravo
arXiv:2604.20395v1 Announce Type: new Abstract: Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D