Knowledge catalogue
When running modern AI workloads, there’s often a conflict between performance and cost. Workloads like large language models (LLMs) load massive files, and may serve thousands of AI agents that need
arXiv:2609.21032v1 Announce Type: cross Abstract: Science advances not in isolation but through collaboration, yet existing agentic systems capture little of this. Whether communicating agents help re
arXiv:2609.21767v1 Announce Type: new Abstract: Vision-language models (VLMs) can replace human annotators in preference-based reward learning, but sequential API requests and single-environment data
arXiv:2602.00279v2 Announce Type: replace Abstract: Reliable uncertainty quantification (UQ) is essential for safe deployment of large language models (LLMs) in scientific question answering, where lo
arXiv:2609.21754v1 Announce Type: new Abstract: Deep learning-based visual odometry (VO) has achieved significant progress, yet most existing methods focus on a monocular approach, which suffers from
arXiv:2609.21709v1 Announce Type: new Abstract: Large language models (LLMs) provide limited support for sign language interaction. Unifying sign language translation (SLT) and generation (SLG) to ena
arXiv:2609.21402v1 Announce Type: new Abstract: Surgical instrument segmentation (SIS) plays a critical role in robotic assistance and surgical workflow analysis. However, most existing SIS methods fo
arXiv:2609.21983v1 Announce Type: new Abstract: Reusing manipulation experience across robot embodiments is important for scaling robot learning and reducing repeated task-specific data collection. Ho
Bloomberg: Some startups, like Harvey, Abridge, Ramp, and Rogo, are embracing open-weight models or training their own models to reduce expensive reliance on frontier labs — The $15.6 billion legal st
arXiv:2511.13254v2 Announce Type: replace Abstract: Large Language Models (LLMs) have displayed remarkable capabilities across diverse domains, but their training remains resource- and time-intensive,
arXiv:2609.21165v1 Announce Type: new Abstract: Off-target protein binding is a major source of adverse effects for small-molecule drugs, yet most structure-based molecular design methods focus on gen
https://preview.redd.it/nulsv53o8vqh1.png?width=4500&format=png&auto=webp&s=74765dbd409f4c221640f9f6000a685f6fdbb242 Spent weekend benchmarking the Splash engine (by Incoai) and extending its architec
arXiv:2609.21307v1 Announce Type: new Abstract: Although conventional controllers and disturbance observers (DOBs) are the standard for precision tracking in manipulators, they suffer from parameter u
arXiv:2609.21039v1 Announce Type: new Abstract: A pervasive structural pattern in modern deep learning is the linear factorization block: a submodule of the form W = BA in which two parameter matrices
arXiv:2609.21650v1 Announce Type: cross Abstract: Fine-tuning Vision-Language-Action (VLA) models commonly relies on human teleoperation demonstrations, while reinforcement learning (RL) with sparse b
arXiv:2609.21109v1 Announce Type: new Abstract: Recent advances in large language models have improved their effectiveness as back-end components for voice assistants, particularly in intent understan
arXiv:2603.12110v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) policies trained in simulation often degrade once deployed on real systems, where the controller must reject exter
arXiv:2609.20832v1 Announce Type: new Abstract: We introduce TatBLiMP, the first benchmark of linguistic minimal pairs for Tatar (tt, ISO 639-3 tat), a Qypchaq Turkic language written in Cyrillic. To
Thanks @sgl_project for the day-0 support! 🙌 SGLang-Diffusion now serves Qwen-Image-2.1: text-to-image generation, multi-image editing, and transparent RGBA output. Try it out! 🎨 Day-0 support for @Al
arXiv:2609.21509v1 Announce Type: new Abstract: When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How mu
The headlines right now are full of stories about AI models 'escaping their sandboxes' and literally killing all humans, lol. I've even heard several commentators and writers say that AI escaped an 'A
arXiv:2609.21989v1 Announce Type: new Abstract: Latent flow models have proven to be a reliable and cost-effective method for time series generation. However, the latent compression induces unwanted a
arXiv:2609.21139v1 Announce Type: new Abstract: Replacing attention in a pretrained language model is a compatibility problem: a plausible substitute may alter representations expected by later layers
arXiv:2609.21015v1 Announce Type: new Abstract: Improvements to Visual-Inertial Simultaneous Localization and Mapping (VI-SLAM) for low-cost autonomous underwater vehicles (AUVs) are critical for tran
arXiv:2609.20834v1 Announce Type: new Abstract: In the rapidly evolving landscape of cloud-native computing, Organizations are increasingly adopting infrastructure models that emphasize scalability, f
arXiv:2603.16086v2 Announce Type: replace-cross Abstract: While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts o
arXiv:2609.21425v1 Announce Type: new Abstract: Zero-shot time-series forecasting (TSF) is often described as forecasting without target-specific parameter updates, but that training-status condition
arXiv:2609.21605v1 Announce Type: new Abstract: Recurrent Transformers increase computational depth through temporal recurrence, feeding each token's high-level hidden state into the computation of th
arXiv:2609.21859v1 Announce Type: new Abstract: Nearly 90% of drugs entering clinical development ultimately fail, despite billions of dollars in investment. Pharmaceutical companies therefore rely on
arXiv:2609.20905v1 Announce Type: cross Abstract: In this work, we present an uncertainty-driven training framework for three-dimensional computed tomography (CT) lung nodule classification, where val
arXiv:2505.05145v4 Announce Type: replace-cross Abstract: To perform few-shot learning, language models extract signals from a few input-label pairs, aggregate them into a learned prediction rule, and
arXiv:2609.21450v1 Announce Type: new Abstract: Post-training weight-activation quantization reduces the memory and inference costs of large language models, but aggressive W4A4 quantization remains d
arXiv:2512.11881v2 Announce Type: replace-cross Abstract: From the relative scarcity of training data to the lack of standardized benchmarks, the creation of effective foundation models for polymers f
arXiv:2609.21225v1 Announce Type: new Abstract: Parametric CAD reconstruction requires recovering both precise geometry and editable modeling operations from visual observations, making it challenging
arXiv:2609.21521v1 Announce Type: cross Abstract: While Video Large Language Models (Video-LLMs) have recently demonstrated strong performance, reliably evaluating their fine-grained video understandi
arXiv:2609.20843v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) enables models to answer natural-language questions through structured graph reasoning and has achieved substa
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their ex
arXiv:2609.21567v1 Announce Type: cross Abstract: Quantum Signal Processing is a powerful quantum framework for generating and approximating univariate polynomials. However, QSP is often limited by ci
Welcome back to Hermes Agent, Claude New official plugin that uses Claude SDK without the tradeoffs to enable Claude Code subscriptions to work in Hermes Agent again! Check it out and install it here:
We’re working with an independent advisory group of mathematicians to help OpenAI responsibly share advances in AI and mathematics. The group will advise on how we assess and communicate new mathemati
arXiv:2609.20942v1 Announce Type: new Abstract: Large language models (LLMs) increasingly participate in scientific evaluation, both as automated reviewers and as assistants to human reviewers. As mod
arXiv:2609.21187v1 Announce Type: new Abstract: Agent models are frequently evaluated one decision at a time, where the model predicts the next action based on the gold interaction history, which is s
arXiv:2609.21412v1 Announce Type: new Abstract: Medical image segmenters often get worse when sites, scanner vendors, or protocols change. Continual test-time adaptation (CTTA) addresses this problem
arXiv:2609.21942v1 Announce Type: cross Abstract: A robot that fails at a task faces the first decision in corrective dialogue: act on its own diagnosis, consult another onboard sensor, or interrupt a
I have been reasonably satisfied with my single R9700 (32GB) as I can run practical quants of Qwen 3.8-27B at good speeds, as well as other similar models in its weight class (Gemma 4 is still my go-t
where it stops: geometry. relative size 0.52, diagonal direction 0.65, while GPT-5.6 and Gemini 3.1 Pro get 100%. UI screens: finding what to click is ~100% for everyone, one step of reasoning 0.90 vs
arXiv:2609.20892v1 Announce Type: cross Abstract: Closed-loop visual servoing requires predictions that indicate whether an action reduces task error, not only whether the action is plausible. We call
xAI's Grok 4.6 is now available in Amazon Bedrock: a frontier model for long-running agents, coding, and knowledge work, with a 500K token context window and four reasoning effort levels. It runs on b
Xiaomi: Xiaomi debuts open-weight omnimodal models MiMo-V2.6 Pro and Flash; Pro allegedly performs “on par with Opus 5 and GPT-5.6 Sol across most agent benchmarks” — Frontier intelligence, all the mo
https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base It's not a Qwen3 finetune, it's actually its own fully custom architecture. No Llama.cpp support yet sadly (Also note that this model is N
You can simply run any GGUF with llama.cpp with n_predict=1 and n_probs=10, disable reasoning, and prompt it such as 'If the following email is spam, respond with 1, if not spam, respond with 0. Do no
ZCode is now open source, and the reported security issues have been addressed. Source code: https://github.com/zai-org/ZCode The repo includes its desktop app, web workspace, backend, Agent CLI, and
arXiv:2609.21712v1 Announce Type: new Abstract: Generative world models offer controllable and repeatable closed-loop simulation for end-to-end and vision-language-action driving policies, but product
This weekend, I did a fun experiment to create something similar to Jev. I LoRA fine-tuned Qwen3.5 4B using a mix of publicly available datasets and synthetic data. For the synthetic data, I used Deep
Jev from TypeSafe AI got me thinking about non-autoregressive decision engines, so I built a small proof-of-concept called AES to test the concept locally on open weights. It uses Qwen/Qwen2.5-1.5B-In
AGI FTW @ FT “The most popular AI models from ChatGPT, Claude, Copilot, Grok and Gemini provided wrong answers to financial queries 57 per cent of the time on average, according to research from techn
Not a pic sharing thread, bunch of those already - mainly just a discussion about first impressions Very underwhelming to me personally. I know its a matter of settings but normally comfy default temp
chat : add dedicated Ling 3.0 (Bailing V3) parser (#28682) chat: add dedicated Ling 3.0 (Bailing V3) parser Ling 3.0 Flash templates pre-open the think block in the generation prompt, so the model nev
metal: add F16 input to the FWHT (#29094) metal: add F16 input to the FWHT The Metal FWHT kernel accepts F32 input only. This change makes the source type a template parameter, so the kernel reads an
fix(mamba) : make time-step projection input contiguous (#28832) mamba : make time-step projection input contiguous Assisted-by: ChatGPT mamba : skip contiguous copy after normalization Assisted-by: C