Knowledge catalogue
arXiv:2607.22687v1 Announce Type: new Abstract: Foundation vision models trained on natural images transfer to medical tasks without domain pre-training, but volumetric classification requires aggrega
arXiv:2607.23197v1 Announce Type: new Abstract: Anomaly detection on multivariate sensor time series is critical for industrial monitoring of cyber-physical systems (CPS), where even subtle deviations
arXiv:2607.23466v1 Announce Type: new Abstract: Parameterized and coupled partial differential equations (PDEs) are central to modeling phenomena in science and engineering, yet neural operator method
arXiv:2607.24267v1 Announce Type: new Abstract: Humans plan physical interactions by imagining the possible outcomes of candidate actions. However, existing visual world models primarily capture appea
arXiv:2602.14947v2 Announce Type: replace-cross Abstract: This paper presents a physics-constrained neural network framework for dynamic modeling of saturable synchronous machines, including spatial h
arXiv:2607.24314v1 Announce Type: new Abstract: Predicting the absorption, distribution, metabolism, excretion and toxicity (ADMET) properties of small molecules remains a major challenge in drug disc
Hello guys. I found some problems in current frontier models. And want to share. # math_code_hallucination > Record of a failure caused by combining mathematics and code in a single prompt. --- ## Cas
arXiv:2601.11809v2 Announce Type: replace Abstract: Connected automated vehicles (CAVs) possess the ability to communicate and coordinate with one another, enabling cooperative platooning that enhance
arXiv:2508.02929v3 Announce Type: replace-cross Abstract: Scaling laws have been established for recommender systems, yet efficiently deploying foundation model (FM) across multiple recommendation sur
arXiv:2607.23019v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not
arXiv:2607.24492v1 Announce Type: new Abstract: The goal of schema integration is, given a set of input schemata or tables, to derive a global, unified schema that is able to represent the concepts, a
arXiv:2505.11421v2 Announce Type: replace Abstract: This work explores the journey towards achieving Bahnaric-Vietnamese translation for the sake of culturally bridging the two ethnic groups in Vietna
arXiv:2607.22704v1 Announce Type: cross Abstract: Nuclear fusion has made significant progress in recent years and is expected to become one of the most important pathways to addressing global energy
arXiv:2607.21918v1 Announce Type: new Abstract: We present an action-conditioned world model framework for goal plane probe guidance in robotic ultrasound, with a focus on neck ultrasound scanning. Au
“An open-weight frontier model helped contain the intrusion.” Attackers have frontier AI. Defenders need a frontier AI ecosystem—the best open and closed models, force-multiplied by a global community
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
Microsoft Corp. today introduced its first in-house cybersecurity model, MAI-Cyber-1-Flash, and a companion agentic system called Project Perception that fields teams of artificial intelligence agents
The LangChain podcast where @hwchase17 interviews agent builders is full of alpha. Recent one with @EnoReyes was the best one yet. Sharing my unstructured notes: Eno keeps bringing back some core conc
Great to see this out, proud of the team!!! @AMD Instella 16B MoE foundation model, fully open with checkpoint after each stage from pretraining, long-context, SFT, DPO and RL. Dataset detail, trainin
So I've taken some time to actually test laguna on a few of my own projects. I wanted to share as I feel most peoples comments at this point have just been about getting it running or saying it doesnt
arXiv:2607.20507v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for program-aided reasoning, agentic decision making, and structured task execution, but these applic
arXiv:2607.21594v1 Announce Type: new Abstract: Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evo
arXiv:2311.15365v3 Announce Type: replace Abstract: We study an idealized training process for deep neural networks in a continuous-depth, mean-field model in which each layer is parameterized by a pr
arXiv:2607.19038v1 Announce Type: new Abstract: Translating novels into films poses a grand challenge for generative artificial intelligence, requiring conversion of abstract literary prose into long-
Poolside AI’s co‑CEO Eiso Kant explains that a small, top‑research team built a model‑factory capable of training Laguna S, a 118‑billion‑parameter mixture‑of‑experts model that outperforms the ~1 tri
arXiv:2607.20339v1 Announce Type: new Abstract: Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformati
Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality generation What's new: • Fine-grained inline tags-steer [whispe
arXiv:2607.20090v1 Announce Type: cross Abstract: Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like cont
arXiv:2607.18709v2 Announce Type: replace Abstract: Existing robot datasets remain expensive to curate, embodiment-specific, and insufficiently annotated with the fine-grained structure required for g
arXiv:2607.20145v1 Announce Type: cross Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed trainin
arXiv:2607.17890v2 Announce Type: replace Abstract: Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. Howeve
Beyond horizontal expansion, depth is another key trait of Rich Content — testing the model's semantic deconstruction and logical nesting: rendering multiple nested interfaces layer by layer within a
Hey HN, Henry & Roman here from Cactus. A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-t
I wrote about the completely wild incident where OpenAI were testing a new model and it broke out of its sandbox and broke INTO Hugging Face to steal the answers to the benchmark https://simonwillison
🎨 Meet Qwen-Image-3.0 — the third generation of our foundational image generation model. If 1.0 was about 'Precision,' and 2.0 added 'Variety, Completeness, Beauty & Authenticity,' then 3.0 comes down
Hi everyone, I'm working on extracting the hierarchical structure of long PDF documents (legal/regulatory text, lots of numbered sections) and would like to gather some feedback on my approach before
arXiv:2607.13877v1 Announce Type: new Abstract: Brain tumor progression exhibits spatially heterogeneous growth, patient-specific treatment response, and complex interactions with surrounding anatomy,
arXiv:2606.16667v2 Announce Type: replace Abstract: Large vision-language models (LVLMs) hallucinate: they assert visual details that the image does not support. A principled remedy is selective predi
arXiv:2607.13998v1 Announce Type: cross Abstract: The rapid proliferation of Agentic Artificial Intelligence fundamentally disrupts traditional customer loyalty paradigms. As AI evolves from passive r
A closer look at improved intelligence in GPT-Live: the model can keep a conversation going while helping with multiple tasks at once, like checking flights, pulling up local weather, and shaping an i
arXiv:2604.25834v2 Announce Type: replace Abstract: With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumptio
arXiv:2603.25112v2 Announce Type: replace-cross Abstract: Standard evaluation of LLM confidence relies on calibration metrics (ECE, Brier score) that conflate how much a model knows (Type-1 accuracy)
arXiv:2607.12557v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) face significant challenges in long video understanding due to the excessive computational cost and information los
AlloyDB powers enterprise-grade search for some of the largest organizations, providing robust hybrid search capabilities that combine text, vector, and keyword searches into a simple ranked SQL query
arXiv:2412.15239v4 Announce Type: replace-cross Abstract: Consumers' engagement with stories is shaped by their expectations about what will happen next, yet modeling these forward-looking beliefs ove
arXiv:2209.14125v3 Announce Type: replace-cross Abstract: Diffusion models have proven to be a flexible and effective framework for modelling probability distributions on finite-dimensional spaces. Ho
Thinking Machines just dropped a ~1T Omni model 🔥 > 1M context window, trained on 48T tokens of image, text, audio 🤯 > comes with a drafter, NVFP4 weights and Unsloth quants > transformers, llama.cpp
arXiv:2607.12815v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extend
We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 se
Who touches every token that flows through @anthropic? It’s not any one model, but it’s @katelyn_lesse, @angjiang and the platform team. A year ago, it was just a messages API. Today, their platform s
Running frontier AI in production is demanding — accelerators to manage, latency to hold steady across continents, regulated data to keep in-region, and long-context requests to serve reliably. Claude
New research from Google DeepMind on effective model routing. LLM routers get judged on accuracy and cost. Both can look great while the router is meaningless. If every model in your society responds
Our free monthly DevRel webinar series kicks off this Thursday, 10am PST. Fine-tune an open vision model to extract clean, structured JSON from messy receipt images, managed start to finish on Firewor
Today, we’re announcing Bonsai 27B: the first 27B-class model to run on a phone. Bonsai 27B is the new multimodal flagship of the Bonsai family. Based on Qwen3.6 27B, it brings a new capability tier t
uhm this gpt 5.6 launch might be the openai's most successful model ever since... since chatgpt? this is IPO altering stuff going on here Did... Codex just overtake Claude Code? 24.5 hours ago Tibo an
Elon Musk announced the availability of a free trial for the Grok 4.5 model through the Grok Build CLI, allowing developers to access and test the latest version of xAI's Grok language model. This ann
Glad to share what I've been building in public. A lightweight AI news feed. We also finetuned a model to write new stories better than Claude or GPT with extensive prompting (believe me not for a lac
One of the most confusing aspects of GPT-5.6 is figuring out which model to use at which reasoning effort - sounds like Sol on Medium might be a good new default for coding work, if it's an upgrade fr
arXiv:2607.07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decompo
This time it is novel math proofs with a public model (most of the other big math breakthroughs have been with experimental LLMs). Yesterday, we made GPT-5.6 Sol Ultra generally available. Today, we'r