Knowledge catalogue
New from the LangSmith Signal. Over the last 2 weeks, we looked at which models teams reach for, and which ones are doing the work. ✅ Reach: gpt-4o-mini was used by 13% of orgs ✅ Work: gpt-4.1-mini sa
Moving Large Language Models (LLMs) from experimental prototypes into enterprise production exposes a critical truth: your infrastructure dictates both your performance ceilings and your unit economic
arXiv:2609.03026v1 Announce Type: cross Abstract: Mechanistic interpretability is increasingly used to guide interventions such as activation steering, circuit removal, and safety monitoring. Yet an i
arXiv:2609.03104v1 Announce Type: cross Abstract: Conformal risk control is an emerging framework for the safe deployment of machine learning models with finite-sample guarantees. To accommodate a bro
🦙 @ollama is used by 9 million developers and 85% of the Fortune 500, giving co-founder and CEO Jeffrey Morgan (@jmorgan) a unique view into which AI models people are actually using and how that’s ch
“OpenAI didn’t notice their internal agents were posting on the internet for a month! This is crazy! It feels like AI companies (and specifically OpenAI) are playing whack-a-mole, this is extremely sc
Zac Hall / 9to5Mac: OpenAI rolls out GPT-6 Astra to Pro, Enterprise, and Business Premium users in ChatGPT Work and Codex and in the API — Update: A day later, GPT-6 Astra is rolling out to Pro custom
Celia Ford / Transformer: OpenAI says it can't read all of Astra's reasoning and admits covert sandbagging would likely go uncaught, yet still calls it the world's most aligned model — OpenAI is haili
Here we go again... Discovery of a new OpenAI agent message board by Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, and Thomas Larsen describes the latest accidental cyberattack by models being tra
arXiv:2609.04165v1 Announce Type: cross Abstract: Parameterised graph theory studies how the complexity of graph-theoretic problems depends on structural parameters of the input graph. This perspectiv
arXiv:2609.04075v1 Announce Type: cross Abstract: AI agents have recently demonstrated strong performance in automated vulnerability patching. However, existing evaluations often validate a patch only
arXiv:2609.03487v1 Announce Type: cross Abstract: Knowledge graph embedding (KGE) demonstrates its effectiveness for predicting missing links in knowledge graphs (KGs) by projecting entities and relat
arXiv:2602.13312v2 Announce Type: replace-cross Abstract: As a pioneer of the third-generation photovoltaic revolution, Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic per
arXiv:2609.04151v1 Announce Type: new Abstract: Generative image models can now produce high-quality images, follow complex instructions, and support precise edits, but they still struggle to preserve
arXiv:2609.02966v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) offer a promising framework for modeling semiconductor devices, yet standard architectures struggle with seve
arXiv:2609.03450v1 Announce Type: cross Abstract: An agent that inherits six one-line memories may pull at most one archived source record before acting; a directive written into the store can steer t
arXiv:2609.04200v1 Announce Type: new Abstract: Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate, object scale, and camera calibrati
arXiv:2609.02971v1 Announce Type: cross Abstract: As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and inf
arXiv:2609.02947v1 Announce Type: cross Abstract: Significant challenges remain in AI-driven educational systems in balancing privacy preservation with accurate cognitive diagnosis. To overcome this,
arXiv:2602.14048v2 Announce Type: replace-cross Abstract: Real-time embodied social interaction places two equally demanding requirements on an agent: continuously generating fluent multimodal interac
arXiv:2609.02893v1 Announce Type: new Abstract: Linear probes can be used to detect behaviors and concepts inside language model activations, but may fail to transfer to out-of-distribution examples.
arXiv:2609.04134v1 Announce Type: new Abstract: Temporal integration gives continuous-time recurrent networks memory, but in deep stacks it also delays bottom-up signals and attenuates top-down errors
arXiv:2609.04196v1 Announce Type: new Abstract: We propose Puffin-World, a unified multimodal architecture that integrates physical understanding, spatial simulation, and 3D world generation and recon
This is nothing impressive but, i had so much fun i wanted to share my experience with this model. (yes this post is written by human) I made an FPS with local Q4_K_XL 3.8 Flash Next (256k context) (i
I've got an refurb Dell R740 running Proxmox that I put a Tesla T4 in, mainly to run some CTC local transcription work, but thought it would be fun to try DS4 when it came out, and it was appalling at
arXiv:2609.03773v1 Announce Type: cross Abstract: Parametric computer-aided design (CAD) modeling is difficult to evaluate with a single metric. Existing CAD benchmarks often emphasize synthetic or CA
arXiv:2603.09968v2 Announce Type: replace Abstract: Online novel view synthesis requires a model to reconstruct a scene causally from a stream of observations while keeping it renderable at every mome
arXiv:2609.02944v1 Announce Type: cross Abstract: Democratizing data access through natural language is a crucial goal for modern enterprises, but the practical adoption of Text-to-SQL is critically h
arXiv:2609.03749v1 Announce Type: cross Abstract: Third-party retrieval-augmented generation (RAG) marketplaces create a new auditing problem: data providers may license corpora to a RAG operator, yet
arXiv:2609.04022v1 Announce Type: cross Abstract: Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet mode
Seattle-based artificial intelligence research startup Resect AI announced Thursday it has raised 25 million in early funding to build an accountability layer for enterprise AI by capturing and reduci
arXiv:2609.03516v1 Announce Type: new Abstract: Infrared-visible object detection (IVOD) integrates complementary evidence from visible and infrared sensors for reliable perception in challenging scen
arXiv:2609.03686v1 Announce Type: new Abstract: Experimental design is commonly framed as choosing the experiment expected to provide the most information. Under partial identifiability however, persi
arXiv:2609.03504v1 Announce Type: new Abstract: Restricted eigenvalue (RE) bounds govern stable recovery by norm-regularized estimators. For isotropic sub-Gaussian measurements, the benchmark sample s
arXiv:2609.03657v1 Announce Type: new Abstract: 3D scene representations like NeRF and 3D Gaussian Splatting (3DGS) suffer severe artifacts in sparse-view settings. Recent generative 3D artifact fixer
arXiv:2609.04189v1 Announce Type: new Abstract: We introduce the first Probably Approximately Correct (PAC) learning framework for general-sum concurrent stochastic games (CSGs) with transition uncert
arXiv:2609.03150v1 Announce Type: cross Abstract: Multi-domain fine-tuning often combines MoE routing with LoRA, assuming that token-level routing separates domain-specific updates. We test this assum
arXiv:2609.03591v1 Announce Type: new Abstract: Learning generalist policies for robust bimanual manipulation is bottlenecked by the scarcity of high quality large scale human demonstration data. In t
arXiv:2609.03106v1 Announce Type: new Abstract: Scaling laws in modern deep learning describe how held-out loss improves as model capacity, training data, and compute increase, often following power-l
arXiv:2609.03689v1 Announce Type: new Abstract: Histopathological subtyping relies on the recognition of characteristic histological patterns. These patterns may be expressed by individual tissue stru
arXiv:2609.03142v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies fuse multimodal sensory inputs, but training on limited and homogeneous robot demonstrations encourages spurious
arXiv:2609.04159v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale:
arXiv:2609.04108v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have emerged as two dominant methods for post-training reasonin
arXiv:2609.03981v1 Announce Type: new Abstract: Brain-MRI inpainting replaces a masked region of a scan with synthesized, anatomically plausible healthy tissue, so that analysis tools built for health
arXiv:2609.03047v1 Announce Type: cross Abstract: Libraries and archives manage large collections with limited staff and computing budgets, yet common benchmarks do not systematically test their bibli
Claude Code is absolutely horrendous at managing docx XML structures and it's obscene that the best these frontier companies can do are skills. Skills are prone to breaking, burn tokens (hello busines
When Google's Finance Engineering team needed to modernize their legacy data layer, they chose Spanner, a globally distributed, strongly consistent, multi-model database with high availability capabil
arXiv:2609.03813v1 Announce Type: new Abstract: Real-world image super-resolution (SR) increasingly relies on Diffusion Transformer (DiT) backbones, whose internal activations can be dominated by a sm
arXiv:2609.03495v1 Announce Type: new Abstract: This paper examines the relationship between the parameters of autoencoder models and the statistical properties of the data on which they are trained.
arXiv:2609.04063v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is widely studied for reinforcement learning with verifiable rewards, where its advantage estimator assigns ea
arXiv:2609.03874v1 Announce Type: new Abstract: Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs
arXiv:2609.04066v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human pref
arXiv:2609.03602v1 Announce Type: new Abstract: World models (WMs) have demonstrated strong potential for end-to-end autonomous driving by learning predictive representations of future scene dynamics.
arXiv:2609.03806v1 Announce Type: new Abstract: Scalable Vector Graphics (SVG) generation is attracting increasing attention as generative models improve in expressiveness and controllability. Progres
arXiv:2609.04167v1 Announce Type: cross Abstract: Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measur
arXiv:2609.03702v1 Announce Type: new Abstract: General-purpose code embeddings power tools for code search, classification, and retrieval. Compact transformer encoders for code typically rely on eith
arXiv:2609.03395v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong performance on table question answering, yet their accuracy often degrades as table size increases. We
arXiv:2609.04071v1 Announce Type: cross Abstract: Pathology foundation models improve transferable representation learning for histopathology, but recent gains often rely on encoders with hundreds of
arXiv:2609.02959v1 Announce Type: cross Abstract: What does a language model predict when it has few clues? The answer lurks in its unembedding geometry: a single direction of the unembedding matrix e
arXiv:2609.03652v1 Announce Type: new Abstract: Synthetic data augmentation has become a common strategy for addressing class imbalance in NLP, but most approaches focus on the quantity and diversity