Knowledge catalogue
On September 9, 2026 Together AI announced that its new **glm‑5.3 flash** model outperforms OpenAI’s **Claude Fable 5.1** on agentic automation tasks. The benchmark also shows glm‑5.3 flash achieves a
arXiv:2412.09529v4 Announce Type: replace Abstract: Radiology, with its heterogeneous modalities, anatomies, and evolving protocols, is a natural yet high-stakes testbed for agentic AI. As LLMs grow m
arXiv:2609.05946v1 Announce Type: new Abstract: Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods have
arXiv:2609.07816v1 Announce Type: new Abstract: Linear attention is increasingly used in frontier language models for efficient long-context inference and constant-memory decoding. Its fixed-size recu
arXiv:2609.06437v1 Announce Type: new Abstract: Diffusion-weighted imaging (DWI) is widely used in clinical settings but remains vulnerable to geometric distortion. Conventional correction methods oft
arXiv:2602.12351v2 Announce Type: replace-cross Abstract: This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VL
arXiv:2609.08084v1 Announce Type: new Abstract: Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in scene reconstruction, computationa
arXiv:2609.08879v1 Announce Type: new Abstract: Cancer segmentation models can fail silently, generating plausible but incorrect masks that risk missed findings or unnecessary biopsies. A critical que
arXiv:2609.07155v1 Announce Type: new Abstract: Model compression is key to mitigate deployment challenges of ever growing machine learning models. In this area of research, singular value decompositi
arXiv:2609.06251v1 Announce Type: new Abstract: Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for vision-language-action (VLA) systems on
arXiv:2609.07009v1 Announce Type: cross Abstract: Multimodal continual learning has recently shown great potential for developing agents with human-like intelligence by continuously learning new tasks
arXiv:2609.07681v1 Announce Type: new Abstract: Associative Recall (AR) is the cognitive ability to learn and retrieve links between items in memory. In NLP, AR is used as a benchmark for evaluating t
arXiv:2609.06870v1 Announce Type: new Abstract: Visual perception of built environments contributes to the affective impressions that people form in everyday life. However, how these impressions are r
arXiv:2609.06869v1 Announce Type: new Abstract: Three-dimensional bioheat simulation aims to predict transient temperature distributions in biological tissue and is commonly modeled using the Pennes b
I’ve been using Qwen a lot recently and I’m honestly very impressed with it. For some of my tasks, Qwen seems to understand what I’m actually trying to achieve better than ChatGPT/GPT-5.6. I currently
Hi, I'm the co-creator of this Qwen3.8-Flash-Next engine support in MLX-serve. I've been tuning this one to run both fast, efficient and correct up 1m context using kv cache 8 bits in M5 Max 128GB. Qw
arXiv:2609.07740v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) replace the fixed activation functions and linear weights of Multi-Layer Perceptrons (MLPs) with learnable univariat
arXiv:2609.08155v1 Announce Type: new Abstract: Scientific figures are the interface through which research claims are inspected and reused, but final published panels rarely expose the data or plotti
arXiv:2507.18073v2 Announce Type: replace Abstract: Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can s
arXiv:2609.07952v1 Announce Type: new Abstract: We study the local errors of classical machine-learning surrogate models, which approximate the time evolution of the one-dimensional viscous Burgers eq
Technology is only good if it empowers you. If it locks you down, saps your attention, or steals your ideas, then it should be discarded. LLMs could go either way. That's why we are dedicated to open,
arXiv:2609.08505v1 Announce Type: new Abstract: Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual
This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m
arXiv:2609.06893v1 Announce Type: cross Abstract: Direct preference optimization DPO is a promising offline approach for aligning large language models (LLMs) due to its simplicity, computational effi
arXiv:2609.07420v1 Announce Type: new Abstract: Vision cues are available and informative for pedestrian action prediction, but obtaining stable target-centric representations from video frames remain
arXiv:2609.05636v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are able to achieve impressive zero-shot classification performance by aligning visual and textual representations, but ea
arXiv:2609.06100v1 Announce Type: new Abstract: Verifiable outcome rewards guide language-model post-training, but sequence-level advantages do not identify which token-level decisions should be prese
arXiv:2606.17463v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) policies have achieved remarkable single-step manipulation, yet they remain brittle precisely where each stage depends
We're introducing Q2D-Web (Query2Doc-Web), a benchmark and public leaderboard for evaluating retrieval in agentic RAG systems. Q2D-Web tests how embedding models perform on large-scale web search usin
Catch up on July and August in Microsoft Foundry: stable Hosted Agent and Toolbox SDK paths, Claude tools on Azure-hosted deployments, Model Router updates, local inference improvements, and the SDK m
model : support Kimi-K3 recurrent-state rollback (#28466) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45866131 macOS/iOS: macOS Apple Silicon (arm64) ma
Benchmark two 30B Mixture-of-Experts models, Qwen3-Coder-30B and NVIDIA Nemotron-3-Nano-30B, across G5, G6, G6e, and G7 GPU instances on Amazon SageMaker AI. Compare throughput, latency, and cost-per-
Bravo to Mistral! So great to see them killing it, they are an inspiration to everyone as we need more sovereign & open-source AI everywhere around the world. Excited to keep supporting them on https:
ChatGPT Images 2.5 is rolling out today to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web. We’re also introducing two new models in the API: GPT-Image-2.5 Flare brings the
Google LLC’s DeepMind research unit said today it has used its AlphaGenome artificial intelligence model to predict the biological consequences of the more than 9 billion possible single-letter change
I don't think anyone posted about this here, but Qwen released a finetuned version of 3.5 4 for driving. The full Bf16 checkpoint is 9B. This is a very interesting development of Chinese AI labs tackl
We want to celebrate with people using GPT-6. We did this for GPT-5.5 and it was really fun. We’re getting together in SF on September 16 to talk about the model, what we should build next, and mostly
arXiv:2609.05069v1 Announce Type: cross Abstract: Large language models (LLMs) show potential for medical tasks, but their single-turn question-answer format does not reflect how clinical diagnosis is
arXiv:2609.04819v1 Announce Type: new Abstract: Multilingual language models develop shared cross-lingual representations, and various interpretability methods claim to quantify this sharing. These me
arXiv:2609.05016v1 Announce Type: cross Abstract: Scaling laws guide the design choices for training large foundation models, but deriving them involves training an exhaustive grid over hyperparameter
arXiv:2609.04830v1 Announce Type: new Abstract: Personalized federated learning (PFL) is a promising paradigm for collaborative learning over distributed devices, where edge nodes collaboratively trai
arXiv:2609.04648v1 Announce Type: new Abstract: Reinforcement learning (RL) has become one of the primary paradigms for reasoning enhancement of large language models (LLMs). In particular, Group Rela
arXiv:2609.05239v1 Announce Type: new Abstract: We present a system that uses a Vision-Language Model (VLM) as a diagnostic agent for adapting a detect-to-track pipeline to a new target domain without
arXiv:2603.25183v2 Announce Type: replace Abstract: Context-aware machine translation (MT) leverages document-level information, yet it does not consistently outperform sentence-level MT, as contextua
arXiv:2609.04782v1 Announce Type: new Abstract: Autoregressive (AR) large language models formulate reasoning as token-level probabilistic sampling, which induces three fundamental defects in complex
I got 2x 20GB RTX 3080s + 128GB of DDR4 2666hz RAM (only 4 of 6 channels populated) + a Xeon 6148 I've always been a llama.cpp person and I've been running Unsloth's Q4_K_XL quant of Qwen 3.8 Flash Ne
arXiv:2609.05223v1 Announce Type: new Abstract: Artificial intelligence models are promising for medical diagnosis, but they require large numbers of unbiased data, which in medicine are distributed a
arXiv:2609.04963v1 Announce Type: new Abstract: Reasoning allows artificial intelligence models to revisit and correct their mistakes, enabling recent frontier advances in mathematical theorem solving
arXiv:2512.15751v2 Announce Type: replace-cross Abstract: Agentic Workflows (AWs) have emerged as a promising paradigm for solving complex tasks. However, automatically generating high-quality AWs rem
arXiv:2609.04304v1 Announce Type: new Abstract: We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe be
OpenAI released GPT‑6 “Astra” — a model benchmarked for superior computer navigation, coding and complex math that can book DMV appointments and hunt apartments faster than an average user. The rollou
arXiv:2609.05093v1 Announce Type: new Abstract: We present Discovery Loop, a lightweight system that uses a large language model (LLM) to iteratively evolve optimization algorithms. Starting from a si
arXiv:2609.04274v1 Announce Type: cross Abstract: Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family
arXiv:2609.05395v1 Announce Type: new Abstract: Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across
arXiv:2609.05070v1 Announce Type: new Abstract: Automated gastrointestinal (GI) endoscopy classification requires models that generalize across diverse modalities and class distributions, often far fr
TL;DR My TAK quant of Qwen 3.8 27b scored 82.81% on reasoning, comparted with 77.34% for the byte matched Unsloth UD IQ2_S and 83.59% for BF16. Edit: Some of you have tried coding with this reasoning-
arXiv:2603.13320v2 Announce Type: replace-cross Abstract: Nepali, a low-resource language, faces significant challenges in building an effective information retrieval system due to the unavailability
arXiv:2609.05038v1 Announce Type: new Abstract: Species identification in camera trap images has been widely studied, but key ecological modeling tasks such as species abundance or density estimation
arXiv:2609.04271v1 Announce Type: new Abstract: Wi-Fi-based human activity recognition (HAR) has become an important part of integrated sensing and communications, paving the way for a range of contex
I’ve been setting up an M1 Max Mac Studio (24-core GPU, 32GB unified memory) as a local LLM server and wanted to compare MLX vs llama.cpp on Qwen3.8-27B. I tried to keep the model footprint and benchm