Knowledge catalogue
Maddy Varner / Wired: Claude chats showed in Google and Bing search results, despite Anthropic's robots.txt saying not to crawl them, likely because the pages lacked a “noindex” tag — The screwup show
arXiv:2607.22221v1 Announce Type: cross Abstract: Zermelo's algorithm is a classical method for computing the maximum likelihood estimator in the Bradley--Terry (BT) model, but its convergence can be
arXiv:2607.22334v1 Announce Type: cross Abstract: Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through
I've been seeing a lot of news about the latest gemma 4 and qwen 3.6 being really good and the current go-to models but those are out of reach for my GPU at the moment. With 4GB VRAM and 40 GB RAM, I
arXiv:2607.21861v1 Announce Type: new Abstract: We study baking documents directly into the weights of a 4-bit Gemma-4-e4b model via LoRA, so a system can answer questions about a corpus closed-book:
arXiv:2607.22165v1 Announce Type: cross Abstract: LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation a
arXiv:2512.03424v4 Announce Type: replace Abstract: State Space Models (SSMs) model long token sequences of point cloud with linear complexity, but require an unordered point cloud to be serialized. E
arXiv:2607.21186v1 Announce Type: cross Abstract: Numerous studies have analyzed the use of hybrid quantum-classical convolutional neural networks as a promising alternative to classical deep learning
arXiv:2607.21617v1 Announce Type: cross Abstract: Vision Language Models (VLMs) are increasingly used in place of traditional OCR pipelines for document understanding. In this paper, we show they do n
arXiv:2607.22026v1 Announce Type: new Abstract: Detecting LLM-generated text remains challenging under zero-shot and training-free conditions, especially when detectors must generalize across datasets
arXiv:2607.22136v1 Announce Type: new Abstract: Empathetic Response Generation (ERG) requires models to recognize users' emotions and generate empathetic responses. Commonsense knowledge has been show
arXiv:2607.21680v1 Announce Type: new Abstract: Bridge infrastructure deteriorates gradually, yet its root causes---salt intrusion, freezing, fatigue cracking, and others---remain invisible to the nak
arXiv:2607.22004v1 Announce Type: new Abstract: Energy natural gradient descent (ENGD) aligns parameter updates with the curvature of an underlying function-space energy, but existing formulations ass
arXiv:2607.10428v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: person
arXiv:2607.22039v1 Announce Type: new Abstract: Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language mo
arXiv:2607.21685v1 Announce Type: new Abstract: A systematic review begins with someone reading thousands of abstracts to identify the few that are relevant, and classifiers are used to prioritise tha
arXiv:2607.22016v1 Announce Type: new Abstract: MEMEs are widely used on the internet and often carry strong elements of sarcasm or irony. Understanding their hidden meanings typically requires a join
arXiv:2607.21688v1 Announce Type: cross Abstract: Machine-learning surrogates of physical systems face a paradox: explainable models facing the challenge of expressivity to capture complex nonlinear f
arXiv:2607.22263v1 Announce Type: cross Abstract: A data-driven inverse optimization problem (DDIOP) is the problem of estimating the objective-function parameters (weights) that explain observed opti
arXiv:2607.22205v1 Announce Type: new Abstract: Remote sensing multimodal large language models (RS-MLLMs) have improved general aerial-image understanding. However, Earth observation applications req
arXiv:2607.22145v1 Announce Type: new Abstract: Open-source LiDAR-inertial odometry (LIO) systems have achieved remarkable benchmark accuracy, yet current state-of-the-art implementations are primaril
arXiv:2607.22302v1 Announce Type: new Abstract: Reconstructing dynamic human faces from brain activity provides a powerful way to study how the mind perceives identity, expression, and facial motion.
I have been trying to do GLM 5.2 as plan / K2.7 as execute, but i hit my usage so fast it's not viable. It's hitting limits much faster than claude code / codex $20 plan. Using in opencode. What are y
arXiv:2411.19715v4 Announce Type: replace Abstract: We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLI
Fresh off the launch of Opus 5, Claude Code creator Boris Cherny (@bcherny) joins YC's @sdianahu at Startup School 2026 to talk about what the newest models can do, how Claude Code came to be, and wha
arXiv:2607.22135v1 Announce Type: new Abstract: Existing BraTS-GLI datasets provide a widely used benchmark for adult glioma MRI segmentation, but their task definition focuses on tumor subregions and
Great technical paper from Google. Great read on why context beats scale for agents working against unfamiliar APIs. (bookmark it) GPU kernel optimization has KernelBench to hillclimb on. TPUs had not
Grok Build with Grok 4.5 stands far ahead on the efficiency frontier....completely alone inside the chart’s most attractive quadrant It delivers top-tier coding-agent performance while using only arou
arXiv:2607.21962v1 Announce Type: new Abstract: Benchmarks for LLM-agent memory typically generate conversations first and extract answer keys afterwards -- with documented label-error and contaminati
Happy to have @FireworksAI_HQ as our day0 launch partner and bring Kimi K3 to more developers. With Fireworks, you can now deploy and fine-tune the 2.8T Kimi K3 model with just a few clicks! Kimi K3 i
arXiv:2607.22444v1 Announce Type: new Abstract: For scale-invariant deep networks, Hyperball-style optimizers have shown strong performance in large-scale training by fixing the norms of matrix-valued
Someone in the comments of my 27B post-train bakeoff asked for the 35B version, so I ran it. Same setup as last time: fresh Coder workspaces on my k8s cluster, each driving my own agent (Hermes) headl
arXiv:2607.22251v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for large language models, but its performance depends strongly on ho
arXiv:2507.18311v3 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, suc
arXiv:2607.22361v1 Announce Type: new Abstract: We study information bottlenecks in modern deep-learning architectures -- RNNs, softmax transformers, linear-attention transformers and state-space mode
arXiv:2510.24668v2 Announce Type: replace Abstract: Language agents have demonstrated remarkable potential in web search and information retrieval. However, many search-agent benchmarks assume that us
arXiv:2607.16811v2 Announce Type: replace Abstract: We revisit Gaussian Mixture Models (GMMs) as a lightweight, interpretable tool for anomaly detection and, in particular, for detecting distributiona
arXiv:2607.22508v1 Announce Type: new Abstract: Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features
arXiv:2607.22380v1 Announce Type: new Abstract: Efficient processing is becoming increasingly important in infrared remote sensing, where satellite constellations produce large volumes of observations
arXiv:2607.21981v1 Announce Type: new Abstract: Chain-of-thought prompting improves language-model reasoning by carrying intermediate states across successive computation steps. However, relying on na
arXiv:2607.22489v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matri
I tested Kat Coder 2.5 with this prompt: Create a spaceship game inspired by Star Fox using vanilla Three.js and HTML. It should have at least five levels, keyboard and mouse controls, enemies, and a
arXiv:2607.21780v1 Announce Type: new Abstract: Document packets, multiple documents concatenated into a single file, are common in government and administrative workflows, yet splitting them into the
Kimi K3 is live on Fireworks. Day 0, inference and training. US-hosted, and zero data retention. This is the first frontier open model in the 3 trillion parameter class. It sports 1M context, native v
Kimi K3 is now available for inference & training in @FireworksAI_HQ. Crazy how easy they make it to tune frontier open models like K3 using LoRA adapters. Best time to figure out how to own your inte
Kimi K3 is now available on Ollama’s cloud. To use it with Claude Code, run: ollama launch claude --model kimi-k3:cloud Currently Kimi K3 requires a Pro or Max subscription, and consumes extra usage c
tldr; we are going to host K3 on A100s (yes, thats correct, we'll try to see if it holds up), H200s & B300s - expect results for A100s & H200s this week while we setup the B300 cluster this weekend &
@Kimi_Moonshot K3 on Together AI is built for long-running agent workflows: → 2.8T parameters and a 1M context window → Native vision for screenshot-guided coding → Repository navigation and terminal
arXiv:2603.07025v2 Announce Type: replace Abstract: Speech Large Language Models (LLMs) that understand and follow instructions in many languages are useful for real-world interaction, but are difficu
arXiv:2607.22215v1 Announce Type: new Abstract: In this study, we introduce latent PDE mapping, a broadly applicable physics-informed learning technique designed to enable efficient geometric generali
arXiv:2602.05988v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their p
arXiv:2607.21856v1 Announce Type: cross Abstract: Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs. However, a rich and largely un
arXiv:2607.21692v1 Announce Type: cross Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input. These selectors are often trained
Some Ling-3.0-flash threads here last week ended on the same two questions with no real answer, so I went through the repos. State as of writing, with links so you can check instead of taking my word
arXiv:2606.16794v2 Announce Type: replace Abstract: This study proposes a domain-specific LLM-based Visual Explanation Evaluation Framework for assessing visual attention explanations in facial skin d
arXiv:2603.12572v5 Announce Type: replace Abstract: Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchm
arXiv:2607.22381v1 Announce Type: new Abstract: Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Ne
love this frame. calls to mind the role of the hippocampus in human navigation (via place cells and grid cells), and how navigation is, in a sense, what makes agents *agents* vs plain old LLM calls in
arXiv:2607.21998v1 Announce Type: new Abstract: This paper introduces a new benchmark test, Medical-Checklist, for assessing medical multimodal models. The recent advancements in multimodal models hav
New York Times: Microsoft introduces MAI-Cyber-1-Flash, an AI model trained for cybersecurity, and launches Perception, an agentic security system to patch vulnerabilities — As some executives fret ov