Knowledge catalogue
arXiv:2509.26405v2 Announce Type: replace Abstract: We introduce InVirtuoGen, a discrete flow generative model for fragmented SMILES for de novo and fragment-constrained generation, and target-propert
**Shieldstral** is a 3‑billion‑parameter open‑weights model developed by Mistral AI for content safety. It can be deployed on-device and is distributed under the Apache 2.0 license. The model is avail
arXiv:2608.00246v1 Announce Type: new Abstract: Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localiz
arXiv:2603.08091v2 Announce Type: replace Abstract: Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by j
arXiv:2608.00640v1 Announce Type: new Abstract: Large language models are increasingly viewed as a potential means of mitigating global health inequities, yet their outputs often reflect dominant high
arXiv:2608.02551v1 Announce Type: cross Abstract: Fairness evaluation concerns not only what a model produces, but also what its outputs ought to be compared against. When a model generates 'a CEO in
arXiv:2607.29077v1 Announce Type: new Abstract: Counterfactual explanations (CEs) enhance the interpretability of machine learning models by identifying the smallest change to an input required to obt
arXiv:2603.20075v2 Announce Type: replace-cross Abstract: Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable
llama : MTP support for DeepSeek V3.2 (#26457) llama : MTP support for DeepSeek V3.2 model : no need to include MTP layers during DeepSeek V3.2 model type discovery Co-authored-by: Stanisław Szymczyk
arXiv:2607.28801v1 Announce Type: cross Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial
arXiv:2607.28840v1 Announce Type: new Abstract: Large language models are increasingly deployed in financial applications that combine retrieval, proprietary data, tool use, orchestration logic, monit
arXiv:2607.28796v1 Announce Type: new Abstract: High-throughput phenotyping requires AI-enabled computer vision models that generalize across genotypes, locations, and growing seasons, yet such models
arXiv:2607.13683v2 Announce Type: replace Abstract: Large Language Models (LLMs) have enabled capable agents across diverse applications. Beyond the foundation model, the performance of an agent is go
Each villager in Pepperton is a different model — a mistral, a qwen3, a qwen2.5, a phi4-mini, a llama3.2 — because model families have genuinely different temperaments, and the friction between them i
arXiv:2607.28669v1 Announce Type: new Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rat
The post announces an “Ask Me Anything” (AMA) about Qwen, the Alibaba‑developed foundation model. It introduces the Qwen Foundation Model Team and directs readers to their GitHub repository @QwenDevs,
arXiv:2512.03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally opt
arXiv:2511.00847v5 Announce Type: replace-cross Abstract: The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: th
arXiv:2607.29238v1 Announce Type: cross Abstract: InMyStyle is a privacy first, single user system that adapts small language models to rewrite AI-edited text towards an individual user's writing styl
arXiv:2505.18660v5 Announce Type: replace Abstract: Recent advances in AI-powered generative models have enabled the creation of increasingly realistic synthetic images, posing significant risks to in
arXiv:2601.02430v3 Announce Type: replace-cross Abstract: Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate their code generation capabilities and com
GPT-Live is so good that I use it almost every day. I've been wanting to replicate it since it was released. My first attempt was to fine-tune Gemma 4 12B to behave like a full-duplex model. Something
Hey y'all. I'll be concise. TL;DR: DS V4-Flash-0731 @ UD-IQ2_M running fully in VRAM on 3xMI50s (90.9 GB model, 96 GB VRAM). Actual speed on llama-server is: - Text Generation: ~15-16 tokens/second st
I know in in this community LLM's are generally used for coding but there are other usecases besides coding and those usecases should be tested too. I also know benchmarks can sometimes be benchmaxxed
arXiv:2511.22078v2 Announce Type: replace Abstract: Many real-world scenarios involving streaming information can be represented as temporal graphs, where data flows through dynamic changes in edges o
arXiv:2607.27405v1 Announce Type: new Abstract: Both expressions of uncertainty and inferences are ubiquitous in natural language, and valid inferences over natural-language expressions of uncertainty
arXiv:2607.27816v1 Announce Type: new Abstract: Role-playing agents (RPAs) have become one of the most important consumer applications of large language models. Users engage in multi-turn conversation
arXiv:2607.27700v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) suffer from prohibitive inference overhead due to long sequences of visual tokens. However, existing visual token re
arXiv:2607.28119v1 Announce Type: new Abstract: In this paper, we draw a comparison between linguists in training, a trained linguist, and annotations generated by large language models (LLMs) to find
arXiv:2510.05554v2 Announce Type: replace Abstract: As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity
arXiv:2607.27779v1 Announce Type: new Abstract: Large chest radiography archives are difficult to search because most studies are paired only with free-text reports rather than structured clinical ann
arXiv:2504.16616v4 Announce Type: replace Abstract: Event cameras, characterized by microsecond temporal resolution and very High Dynamic Range (HDR), emit high-speed event streams for perception task
arXiv:2607.28582v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) is a promising approach to improve reasoning language models, but it remains brittle in practice: making it work reli
arXiv:2607.09306v3 Announce Type: replace Abstract: Behavioural auditing asks whether a language model behaves as it claims, but detection scores are reported without separating two targets: whether a
arXiv:2607.28319v1 Announce Type: new Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias
arXiv:2607.28196v1 Announce Type: new Abstract: Practitioners accept a compressed language model once it clears a stack of data-cheap quality guards: perplexity within a small factor of the original,
arXiv:2607.27610v1 Announce Type: new Abstract: Reinforcement learning (RL) finetuning significantly enhances the reasoning capabilities of large language models (LLMs), yet its effectiveness critical
arXiv:2512.01557v3 Announce Type: replace Abstract: This study examines the digital representation of African languages and the challenges this presents for current language detection tools. We evalua
arXiv:2410.06458v2 Announce Type: replace Abstract: Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multipl
arXiv:2607.27806v1 Announce Type: new Abstract: In clinical practice, patients often undergo multiple imaging examinations over successive visits, yielding longitudinal data. Modeling such temporal in
arXiv:2607.27616v1 Announce Type: new Abstract: Text-to-image and personalized editing models now synthesize high-fidelity single-subject images with ease. Yet placing multiple named people into share
arXiv:2607.28277v1 Announce Type: new Abstract: Hyperspectral imaging is widely used in remote sensing and engineering. Therefore, research on its classification methods is crucial. While CNN and Tran
arXiv:2603.16140v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven recent capability advances of large language models across various domains. Recent
arXiv:2607.27913v1 Announce Type: new Abstract: Foundation models offer a promising paradigm for Electroencephalography (EEG) analysis, leveraging generalizable representations from vast unlabeled dat
arXiv:2607.27826v1 Announce Type: cross Abstract: Recent advances in sign language (SL) understanding (SLU) have led to remarkable progress in tasks such as continuous SL recognition and SL translatio
arXiv:2607.27680v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become the standard mechanism for fine-tuning large pretrained models, yet its statistical properties remain only parti
A few weeks ago I posted about if it was worth using a V620 for Comfyui, and was told it likely wouldn't work, at least in Windows 11. And if it did, it would be far too slow and unusable. I decided t
@ArtificialAnlys ok @openai gets it https://x.com/OpenAI/status/2082878156483219672 We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are
metal: fix memory unwire if model is freed without any GPU operations (#26082) metal: fix memory leak if model is freed without any GPU operations metal: run dummy work only if residency sets are used
arXiv:2607.26596v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified tran
Kimi K3 is a 2.8‑trillion‑parameter Mixture of Experts model released by Moonshot AI on July 27, 2026, with its weights publicly available for self-hosting. Its architecture—using Kimi Delta Attention
arXiv:2607.26780v1 Announce Type: new Abstract: The ability of large language models (LLMs) to process and generate text has introduced potential for applications in information extraction (IE). While
arXiv:2607.27134v1 Announce Type: cross Abstract: Writing and communication are increasingly mediated by large language models (LLMs) that are being used to draft, revise and polish text. Although suc
arXiv:2607.26191v1 Announce Type: cross Abstract: Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessmen
arXiv:2607.26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning
arXiv:2607.26370v1 Announce Type: cross Abstract: We propose a self-adaptive online learning for control method for tracking unknown target dynamics. The target dynamics can exhibit switching behavior
arXiv:2503.10647v2 Announce Type: replace Abstract: This study evaluated the diagnostic reliability of two Large Language Models (LLMs), Google Gemini 2.0 Flash and OpenAI ChatGPT-4o, across three dim
Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many benchmarks. To test its speed, we plugged it into HF's speech
model: add NextN/MTP speculative decoding support for GLM_DSA (GLM-5.2) (#25980) model: add NextN/MTP speculative decoding support for GLM_DSA (GLM-5.2) Adds GLM-5.2 NextN/MTP as a --spec-type draft-m
arXiv:2607.25830v1 Announce Type: new Abstract: Deep learning models in computer vision face significant challenges when trained on long-tailed datasets, where a few majority classes dominate while ma