Knowledge catalogue
arXiv:2604.16823v1 Announce Type: new Abstract: Vision Transformer (ViT) has brought new breakthroughs to the field of image classification by introducing the self-attention mechanism and Graph Convol
arXiv:2507.05920v2 Announce Type: replace Abstract: State-of-the-art large multi-modal models (LMMs) face challenges when processing high-resolution images, as these inputs are converted into enormous
arXiv:2604.18349v1 Announce Type: new Abstract: Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions withou
arXiv:2604.17751v1 Announce Type: cross Abstract: Adapting foundation models under resource budgets relies heavily on Parameter-Efficient Fine-Tuning (PEFT), with LoRA being a standard modular solutio
arXiv:2508.00553v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) encode images and videos into abundant tokens, which contain substantial redundancy and computation cost. While visual
arXiv:2604.17745v1 Announce Type: new Abstract: Recent advances in large language models have highlighted their potential to automate computational research, particularly reproducing experimental resu
arXiv:2604.17271v1 Announce Type: new Abstract: Node classification on text-attributed graphs (TAGs) is a fundamental task with broad applications in citation analysis, social networks, and recommenda
arXiv:2505.15087v3 Announce Type: replace Abstract: Multi-Hop Question Answering (MHQA) is crucial for evaluating the model's capability to integrate information from diverse sources. However, creatin
arXiv:2604.17259v1 Announce Type: cross Abstract: User behavior in the real world is diverse, cross-domain, and spans long time horizons. Existing user modeling benchmarks however remain narrow, focus
arXiv:2604.16464v1 Announce Type: cross Abstract: Passenger assistance services are essential for accessible rail travel, yet demand varies substantially across stations and over time, creating challe
arXiv:2604.17283v1 Announce Type: new Abstract: User preferences evolve across months of interaction, and tracking them requires inferring when a stated preference has been changed by a subsequent lif
arXiv:2604.18242v1 Announce Type: cross Abstract: We introduce the horospherical depth, an intrinsic notion of statistical depth on Hadamard manifolds, and define the Busemann median as the set of its
arXiv:2604.18031v1 Announce Type: new Abstract: Molecule generation requires satisfying multiple chemical and biological constraints while searching a large and structured chemical space. This makes i
Tiffany Ng / Wired: How GrapheneOS lead developer Daniel Micay's legal fights with his former partner James Donaldson over CopperheadOS led to the privacy-focused tool's creation — There's a lot of lo
arXiv:2510.06700v3 Announce Type: replace Abstract: Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning proble
arXiv:2604.17935v1 Announce Type: new Abstract: The key-value (KV) cache is the dominant memory bottleneck during Transformer inference, yet little is known theoretically about how aggressively it can
arXiv:2604.17581v1 Announce Type: new Abstract: How much data is enough to make a scientific discovery? As biomedical datasets scale to millions of samples and AI models grow in capacity, progress inc
arXiv:2604.17828v1 Announce Type: new Abstract: Whether the Indus Valley sign system (c. 2600-1900 BCE) encodes spoken language has been debated for decades. This paper introduces a multi-metric discr
NPR: How opposition to data centers, over concerns like power demands, pollution, and water needs, has become a voting issue for many people in the 2026 US midterms — Fifteen minutes after Susan Bourg
arXiv:2604.16320v1 Announce Type: cross Abstract: LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains o
arXiv:2505.15404v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enha
arXiv:2604.16714v1 Announce Type: new Abstract: Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance
This article explains how to ground Korean AI agents in realistic demographic data by utilizing synthetic personas, likely leveraging NVIDIA's Nemotron models available on Hugging Face. The approach e
arXiv:2604.17105v1 Announce Type: new Abstract: Tokenization is the first step in every language model (LM), yet it never takes the sounds of words into account. We investigate how tokenization influe
arXiv:2510.02370v3 Announce Type: replace Abstract: Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially,
How we secure every layer of the vibe coding stack- a note from our CTO 👇 Vibe coding is changing how software gets built. But as AI agents write more of our code, the question security teams are aski
arXiv:2511.01066v3 Announce Type: replace Abstract: We present an ongoing initiative to provide open, very large, high-quality, and richly annotated textual datasets for almost 200 languages. At 30 tr
arXiv:2604.16499v1 Announce Type: new Abstract: Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be consi
arXiv:2604.17454v1 Announce Type: new Abstract: Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview
HUGGING FACE JUST AUTOMATED THEIR ENTIRE POST-TRAINING TEAM WITH AN AGENT. It reads papers, runs GPU experiments, iterates, and builds research-backed models autonomously. Pushed a benchmark from 10%
arXiv:2508.01486v3 Announce Type: replace Abstract: Sentiment analysis for low-resource languages remains challenging in an era where interpretability, human alignment, and fairness are increasingly n
arXiv:2604.16592v1 Announce Type: cross Abstract: This comprehensive report distinguishes prior works by the cognitive functions they innovate. Many works claim an almost 'human-like' cognitive capabi
Lily Mae Lazarus / Fortune: Humble unveils a fully electric cabless autonomous truck called the Humble Hauler and comes out of stealth with a 24M seed led by Eclipse — The autonomous vehicle wave has
This is an informal social media post expressing enthusiasm about an upcoming development or project, tagging several notable figures and companies including Harrison Chase (LangChain co-founder), And
arXiv:2604.17107v1 Announce Type: new Abstract: Magnetic Resonance Imaging (MRI) is vital for prostate cancer (PCa) diagnosis. While advanced techniques such as Hybrid Multi-dimensional MRI (HM-MRI) h
arXiv:2604.16953v1 Announce Type: cross Abstract: Breast cancer diagnosis through thermographic image analysis remains a critical challenge in medical AI, with classical deep learning approaches facin
arXiv:2604.16589v1 Announce Type: new Abstract: Structural health monitoring plays a critical role in ensuring structural safety by analyzing vibration responses from engineering systems. This paper p
arXiv:2510.22215v2 Announce Type: replace-cross Abstract: Retrieval over visually rich documents is essential for tasks such as legal discovery, scientific search, and enterprise knowledge management.
arXiv:2604.17446v1 Announce Type: new Abstract: Purpose: 3D reconstruction in minimally invasive surgery (MIS) enables enhanced surgical guidance through improved visualisation, tool tracking, and aug
arXiv:2604.16959v1 Announce Type: cross Abstract: Incomplete Multi-View Clustering (IMVC) faces the challenge of learning discriminative representations from fragmentary observations while maintaining
arXiv:2604.16969v1 Announce Type: new Abstract: Unmixing reveals the spatial distribution and spectral details of different constituents, called endmembers, in a hyperspectral image. Because unmixing
I agree, and I will add to this. Companies should own their memories, skills and other resources agents need. Use Claude code, codex, copilot, etc for intelligence but your execution layer should plug
I agree with Connor that most folks concerned about AI have been far too coy about extinction risk, and that ControlAI is one of few exceptions. The world needs more earnest communication efforts. We
A free, open-source CLI coding agent that runs locally using Ollama and can read, write, and edit files while running shell commands through natural language. The tool supports Claude API as an altern
A developer created a command-line tool that integrates Graph RAG (Retrieval-Augmented Generation) with Obsidian, using Ollama to run a local LLM for extracting entity relationships from notes. The to
I built a web analytics system to track traffic and events across all my @Replit projects in one place. Drop-in @posthog stack: → Full analytics dashboard → Reverse proxy (beat ad blockers) → AI skill
I came up with a somewhat foolish new benchmark for testing image generation models, to exercise the new ChatGPT Images 2.0: 'Do a where's Waldo style image but it's where is the raccoon holding a ham
I find that open weights models over-perform on benchmarks compared to actual real-world usage, and Kimi feels like no exception. For example, a small amount of use will show that Kimi is not as good
Simon Willison expresses hope that OpenAI will commit to long-term maintenance of an AI tool, citing concerns about his own tool potentially becoming stale or discontinued. The post reflects broader u
I had a great exchange with @ElonMusk discussing the next frontier of @SpaceX and space exploration to the transformative progress of @Tesla with Optimus and @boringcompany’s urban innovation. I reaf
I have been using GPT ImageGen-2 for the past weeks I didn't think that better image-generators would be a big deal but it turns out that there is a quality threshold I didn't expect, where you can no
I have done no promotion at all for our @LangChain for Beginners course and I just checked and it has 371 stars on GitHub🌟 Working on updating some of our docs today and at some point will do a video
I hope this helps. If you need more help let me know: Connecting OpenClaw to the X API is straightforward now thanks to X’s official native support... The best and most direct method uses the official
I love the way this is framed. New congressional districts that would disenfranchise almost half of Virginia GOP voters are designed 'to restore fairness in the upcoming elections.' Modern American po
This post discusses visual artifacts in Final Fantasy VI, speculating that they resulted from the original game's pixelated graphics being interpolated during upscaling or enhancement processes. The s
I tested @huggingface ml-intern, given the prompt 'Fine-tune a Segment Anything Model (SAM) on a useful medical dataset. Train the model, and provide a comprehensive tutorial in a Jupyter Notebook fil
The CoALA paper proposes a classification system for agent memory that distinguishes between semantic memory (facts and concepts), episodic memory (specific experiences and events), and procedural mem
I was kicked off the AI Ascent swag committee bc of last year’s “ai a scent” candle nonsense 😂 This year @Alfred_Lin leveled us up. Can’t wait for the aliens to find our AI Ascent 2026 swag one day. “
IBM and the University of Illinois Urbana-Champaign (UIUC) have established a partnership focusing on quantum computing and related algorithmic research. The agreement, discussed by IBM researcher Han
arXiv:2604.16405v1 Announce Type: cross Abstract: Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physi