Knowledge catalogue
🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities! Native audio-video understanding, reasoning, and tool use come together in one model: understand the content
arXiv:2609.19183v1 Announce Type: cross Abstract: Whether human or large language model (LLM), an agent in a discussion reads only a few of the others' contributions, bounded by cognition, context, or
arXiv:2609.19002v1 Announce Type: cross Abstract: Execution-based verification enhances large language models' mathematical reasoning through computational soundness and dependency-aware filtering. Ho
arXiv:2609.18989v1 Announce Type: new Abstract: How many dimensions does a language model's computation actually use? The question is ill-posed until one names a functional. Task-weighted charts make
arXiv:2601.11716v2 Announce Type: replace-cross Abstract: Accurate and efficient detector simulation is essential for modern collider experiments. To reduce the high computational cost, various fast m
arXiv:2609.17119v1 Announce Type: new Abstract: Large language models can easily generate explanations for their own outputs, but such self-explanations are not necessarily faithful to the model's beh
arXiv:2609.17391v1 Announce Type: new Abstract: Model serving is one of the largest cost drivers in production recommender systems. Maximizing its throughput requires navigating a deeply layered hiera
arXiv:2609.16061v1 Announce Type: cross Abstract: Span-level masked language modeling (MLM) has shown to be advantageous to pre-trained language models over the original single-token MLM, as entities/
arXiv:2609.15740v1 Announce Type: cross Abstract: Brain signal analysis is essential for both neuroscience research and clinical diagnostics, yet current approaches face critical limitations. End-to-e
arXiv:2609.13149v1 Announce Type: cross Abstract: For local large language model agents, active context is a scarce resource: memory capacity, prefill latency, cache growth, and service objectives all
Google LLC is trying to address the latency problem associated with voice-based artificial intelligence agents with the launch of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking today. They’re b
arXiv:2603.29396v2 Announce Type: replace Abstract: Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appr
arXiv:2609.13200v1 Announce Type: cross Abstract: Compact transistor models are the mathematical backbone of circuit simulation. However, at advanced nodes such as 3nm, transport physics becomes too c
arXiv:2609.13647v1 Announce Type: new Abstract: The rapid development of unmanned aerial vehicle (UAV) technology has made aerial-image object detection increasingly important for natural-resource mon
arXiv:2609.12075v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models show high robotic manipulation capabilities via a two-stage design: a Vision-Language Model (VLM) stage followed b
I'm currently using Qwen3.5 4B as the brain of my local AI assistant because my hardware is relatively limited. One thing I really like about it is the speed. On my system, I'm getting around 40–50 to
It’s always bothered me that after fine-tuning a model for a project, there isn’t a particularly easy way to host it without either running it locally and keeping a GPU on 24/7 or paying for an entire
arXiv:2609.11725v1 Announce Type: cross Abstract: Text-to-speech (TTS) models commonly address text--speech alignment by expanding phone-level encoder states to frame-level decoder inputs using predic
https://huggingface.co/HermiHg/Qwen3.8-27B-DFlash2-Q2_K_S-MIX-GGUF I used this draft model with https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF with the IQ3_XXS with 128k context and I saw
Hi everyone, I was interested in learning LoRA fine-tuning, and ended up building CodeFinetuner over the past few months, a full pipeline that fine-tunes a small code autocomplete model (e.g. Qwen2.5-
arXiv:2609.09575v1 Announce Type: new Abstract: Topic models summarize large text corpora, but top-ranked words often provide only a limited representation of topic semantics. Sparse autoencoders (SAE
arXiv:2609.10495v1 Announce Type: new Abstract: In real-time colonoscopy, ground-truth annotations are unavailable at inference, so polyp segmentation models can fail silently. We propose Referee-Base
arXiv:2609.09941v1 Announce Type: new Abstract: Generalist robot policies have demonstrated strong generalization across robotic manipulation tasks, yet their success rates remain limited in com- plex
arXiv:2609.07309v1 Announce Type: cross Abstract: Robustness evaluation of large language models (LLMs) remains a critical challenge, particularly in assessing their sensitivity to perturbations in in
so i saw that openui.com released OUI-1, a model fine-tuned on DiffusionGemma. the training dataset uses OpenUI-Lang, a custom DSL (domain-specific language), instead of plain HTML, Markdown, or React
arXiv:2609.05721v1 Announce Type: new Abstract: Understanding whether language-model embeddings encode structured real-world information is important for both representation analysis and information r
arXiv:2609.10305v1 Announce Type: new Abstract: Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transform
arXiv:2609.07154v1 Announce Type: new Abstract: We describe our entry to the EgoLongQA track of the Wearable-AI Challenge in ECCV 2026, which placed first in the <=2B parameter division with 0.8279 on
arXiv:2609.06656v1 Announce Type: new Abstract: Modern power systems are growing increasingly complex as they integrate diverse generation sources to meet rising demand, making accurate load forecasti
arXiv:2609.05881v1 Announce Type: cross Abstract: Developers increasingly run large language models locally by pulling quantized GGUF artifacts from public registries, yet nothing in the distribution
arXiv:2609.06302v1 Announce Type: new Abstract: Embodied visual tracking requires a robot not only to react to the current view, but to choose actions that preserve or recover future evidence of a mov
arXiv:2609.07051v1 Announce Type: new Abstract: World models increasingly serve as the predictive core of model-based reinforcement learning agents, enabling them to simulate future dynamics and reaso
We have just raised 3B€ to accelerate our R&D. We are scaling up our training and inference compute to build future generations of our models, and expanding our Science team across all our offices --
Hi! Today I'm releasing MageTrail, a Danbooru/E621 proof of concept Full-Finetune of Microsoft's MageFlow 4B T2I model, using a diversity maximized condensed 41k images dataset (originally made by Lod
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
arXiv:2606.16583v2 Announce Type: replace Abstract: Safe deployment of clinical vision-language models (VLMs) requires reliable uncertainty estimation (UE): a signal indicating when predictions should
arXiv:2609.01675v1 Announce Type: cross Abstract: Accurate large-scale wildfire spread modelling requires models that capture both the environmental conditions associated with fire occurrence and the
arXiv:2609.00891v1 Announce Type: new Abstract: Sharing context between LLMs in a multi-model system requires the receiving model to prefill the shared prefix because KV caches are model-specific. Rec
arXiv:2609.00463v1 Announce Type: new Abstract: This work examines recent byte-level models and their failure to perfectly manipulate characters. State-of-the-art byte-level models use a hierarchical
arXiv:2601.14603v2 Announce Type: replace Abstract: Optimizer design plays a central role in efficient language model pretraining, directly affecting optimization dynamics, convergence speed, and comp
arXiv:2608.29034v1 Announce Type: cross Abstract: A wide range of methods have been proposed for interpreting language models, delivering important insights into their inner workings. However, differe
I was browsing HF for small LLMs and run into this model. It does not seem to be a fine tune - the model has its own architecture. https://huggingface.co/XHToken/Spark-X2.5-1.7B https://huggingface.co
arXiv:2608.29420v1 Announce Type: new Abstract: Frontier-model leaderboards now rank systems based on economic benchmarks, tests of how well models carry out professional tasks from software engineeri
arXiv:2601.16753v2 Announce Type: replace-cross Abstract: Longitudinal information in radiology reports refers to the sequential tracking of findings across multiple examinations over time, which is c
Data pipelines are the backbone of the modern enterprise, yet a barrier to entry exists for orchestrating them, making this critical capability unavailable to many data professionals. Following our an
arXiv:2608.27816v1 Announce Type: new Abstract: Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degr
You guys remember sesame AI? With their really good AI voice model? Obviously ChatGPT has their voice model that’s also really good. Is there any smaller local variant that runs on like consumer grade
arXiv:2608.27051v1 Announce Type: new Abstract: Detecting the fetal abdominal circumference standard plane in low-cost obstetric blind sweeps is a highly imbalanced frame-classification problem: posit
arXiv:2608.27233v1 Announce Type: new Abstract: Human Activity Recognition (HAR) using inertial measurement units (IMUs) enables a wide range of applications, yet the field still lacks a unified model
arXiv:2608.27370v1 Announce Type: new Abstract: Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of the academic and open-source communit
arXiv:2608.26649v1 Announce Type: new Abstract: Objective: Model-based closed-loop neural stimulation holds promise for therapeutic applications ranging from Parkinson's disease to sensory restoration
Hey everyone, I am the co-founder of Tontaube. My brother and I just released TontaubeV1, a 2.9B-parameter open-weight TTS model focused on expressive speech, long-form generation, and low-latency loc
arXiv:2608.26090v1 Announce Type: cross Abstract: We present a first application of sparse-autoencoder-based mechanistic interpretability to particle physics. Studying a neutrino foundation model pret
arXiv:2608.26088v1 Announce Type: cross Abstract: Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic vulnerability, demands high-fideli
A high-performance 125B model now running locally on just 75GB RAM! Thank you @UnslothAI for the day-0 support.🥳 Qwen3.8-Flash can now be run locally! 🔥 The 125B MoE model outperforms Claude-Opus-4.6
arXiv:2608.23922v1 Announce Type: new Abstract: Data mixing is a central design problem in large language model pretraining: given a fixed token budget, practitioners must decide how much data to allo
arXiv:2608.23809v1 Announce Type: cross Abstract: Multilingual language models can solve the same mathematical problem in different languages, but it remains unclear whether they rely on shared featur
Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token ef
The mystery model Ox Alpha is now available in @AutoClawAIer by @Zai_org It's official name is GLM-5.3-Flash, a next-generation multimodal model for vision-language understanding, code generation, and
With hopes of a Qwen3.8-35B-A3B release now mostly dashed, many people including myself are looking at fine-tunes and other variants of Qwen3.6-35B-A3B to run on VRAM-limited hardware. I decided to tr