Knowledge catalogue
arXiv:2609.12225v1 Announce Type: cross Abstract: Out-of-Distribution (OOD) data poses a significant threat to machine learning models, often leading to model failure during deployment. All existing O
arXiv:2609.12353v1 Announce Type: new Abstract: Large language models trained recursively on their own or other models' outputs undergo model collapse, in which distributional tails and factual accura
arXiv:2609.11770v1 Announce Type: new Abstract: Large language models are superseded every few quarters; clinical evidence takes years. We asked whether medical research is keeping pace with the syste
arXiv:2609.05899v1 Announce Type: cross Abstract: Aligning large language models with human preferences remains a challenge, primarily due to the critical role of preference data quality in effective
arXiv:2609.05588v1 Announce Type: cross Abstract: World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video and action-labeled interaction.
arXiv:2609.06951v1 Announce Type: new Abstract: Activation steering promises modular control of language model behavior: a behavior such as politeness corresponds to a direction in a model's activatio
I am pleased to see that OpenAI’s new model is roughly on par with Gemini Flash and Opus 4.8 on prompt injection risk. Nice work! Evaluating and naming other labs turns out to be a great way to encour
It just seems every local 30b class model is just trying so hard to be the next Qwen that they all just kinda blend into a mass of code focused models. I really like how gemma 4 31b turned out with it
arXiv:2609.04699v1 Announce Type: new Abstract: Background. Large language models (LLMs) are being adopted in biomedical research at a rapid and accelerating pace, yet commercial services that host ma
arXiv:2609.04011v1 Announce Type: cross Abstract: Reliable transport models are essential when modelling and optimising many chemical engineering processes, yet, most models assume hand-picked constit
arXiv:2609.04166v1 Announce Type: new Abstract: Research and news coverage of language-model deception increasingly attributes human-like mental-state concepts to language models. Such claims can blur
arXiv:2603.18593v2 Announce Type: replace Abstract: We propose a method that represents language models by log-likelihood vectors over prompt-response pairs and constructs model maps for comparing the
arXiv:2609.02292v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: sele
arXiv:2609.00940v1 Announce Type: new Abstract: Solving problems through repeated attempts is a sequential modeling task: at each step, the solver receives feedback and decides how to revise their sol
arXiv:2608.30092v1 Announce Type: cross Abstract: We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bilingual English-Nepali text, using a custom single-
arXiv:2608.29928v1 Announce Type: new Abstract: State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechani
Fable 5.1 is our best model yet for coding, data analysis, computer use, design, presentations, Tag, and the hardest long-running agentic work. This model is a pleasure to work with, and I've been usi
arXiv:2608.30114v1 Announce Type: new Abstract: Brazilian Portuguese remains under-served by open language models, and the few that exist are difficult to reproduce and are often compared without meas
arXiv:2608.30530v1 Announce Type: new Abstract: VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility u
arXiv:2608.27518v1 Announce Type: new Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by ca
arXiv:2608.27033v1 Announce Type: new Abstract: We introduce Riemann-1.0, a fully causal autoregressive World Action Model for embodied intelligence. Riemann-1.0 jointly models multi-view visual obser
arXiv:2608.25927v1 Announce Type: cross Abstract: World models aim to simulate how complex environments evolve under actions and events, yet existing video-based world models primarily learn dynamics
arXiv:2608.24688v1 Announce Type: new Abstract: Precision oncology necessitates a longitudinal model of patient state that captures cancer evolution and treatment over time, integrating multimodal obs
The Qwen3.8‑Flash‑Next 176 B multimodal MoE model uses a hybrid Gated DeltaNet / Qwen Sparse Attention (QSA) architecture that compresses long‑context history and aggregates tokens into micro‑blocks f
arXiv:2608.24486v1 Announce Type: cross Abstract: Purpose: To quantify how evaluation annotations influence measured pulmonary embolism (PE) segmentation performance relative to model training changes
Hi everybody! Every now and then these days, we’re seeing really huge open-weight models popping up. But since not everybody has a DGX Station at home, I’m interested in really small models. It’s incr
arXiv:2608.19661v1 Announce Type: new Abstract: Large language models can turn a natural-language mission into a sequence of robot actions, but they do not have a sense of physics: they cannot judge h
Just got the setup dialed in yesterday. Getting really good results and is making 3.8 usage feel faster in hermes. I got Qwen to specifically use Ling tiny for simple tasks like context compression an
arXiv:2606.14870v2 Announce Type: replace-cross Abstract: Foundation models (FMs) trained on large datasets and fine-tuned on downstream tasks have emerged as a powerful paradigm in AI for science. In
From the screenshots: Hy4 is now live, labeled 'Expert-Level Model' + 'Use Tools to Solve Problems' Hy3 is tagged with 'New Upgrade,' positioned as a brand-new general-purpose model DeepSeek, focused
arXiv:2608.15652v1 Announce Type: new Abstract: The rapid proliferation of generative models raises the model attribution problem: given only an image, can we determine which model produced it? Existi
for those looking for something small AND powerful, there is a new 1B (they claim, it looks more like 1.7B ...) model that claims to beat qwen 3.5 0.8B & 2B and gemma 4 E2B on a range of benchmarks. t
arXiv:2608.13596v1 Announce Type: cross Abstract: Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales. We study an underexplored cross-sc
arXiv:2608.14490v1 Announce Type: new Abstract: We present a Test-time World-model Inference (Twin) system, in which a frontier coding agent writes an executable world model for completing continual l
arXiv:2608.13633v1 Announce Type: cross Abstract: Machine learning is now a central tool for solving inverse problems in particle physics and astronomy. Models are trained on simulation and deployed o
Qwen’s new Qwen‑3.8‑27B model has become the top‑trending model on Hugging Face. The release announcement thanks the community for its support and invites users to try the model and provide feedback.
So a bit of context, I am a cybersecurity senior analyst I am interested in LLMs for that field especially with MCPs to connect them to the tools or for writing scripts I started this field by doing a
arXiv:2608.13489v1 Announce Type: new Abstract: We present extbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction
arXiv:2303.08063v4 Announce Type: replace Abstract: For a considerable time, researchers have focused on developing a method that establishes a deep connection between the generative diffusion model a
Stumbled across this new vision model, SenseNova-Vision. It's a 7B MoT model, Apache 2.0 license, which is cool. The main idea is it treats pretty much all computer vision stuff as just one generation
arXiv:2608.10260v1 Announce Type: new Abstract: Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions d
The Qwen Team has released its flagship model, Qwen3.8‑2.4T‑A95B, on the Together AI platform (togethercompute) as of August 12 2026. This 2.4‑trillion‑parameter model is engineered for coding tasks a
I wanted to find out whether a huge text-only MoE could be given basic vision without retraining the language model itself. The short answer is yes. I froze DeepSeek V4 Flash and a 417M-parameter Moon
arXiv:2608.09703v1 Announce Type: new Abstract: Training a language model suite classically requires training each model separately and serving them independently. We improve both training and inferen
arXiv:2608.06526v1 Announce Type: new Abstract: Large language models can infer sensitive personal attributes, such as age, location, and occupation, from ordinary text, turning everyday writing into
arXiv:2608.07107v1 Announce Type: new Abstract: World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent ne
arXiv:2608.06792v1 Announce Type: cross Abstract: Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foun
arXiv:2401.07039v5 Announce Type: replace-cross Abstract: Mixed quantum states are the native description of many physically important quantum systems, making their generation a fundamental task in qu
arXiv:2608.06770v1 Announce Type: new Abstract: Controllable surgical world models can provide a generative foundation for surgical artificial intelligence and simulation by synthesizing realistic ins
DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's cloud. This model combines speed, efficiency, and frontier-level performance. Fast: 120+ output tps
LabyrinthBench measures the thing that actually kills long agent runs — whether a model can still use what it learned twenty turns ago — deterministically, with no LLM judge, on your own hardware, wit
arXiv:2608.00261v1 Announce Type: new Abstract: Do frontier vision-language models present a coherent Theory-of-Mind (ToM) profile across tasks, matching the same human reference group, or does that p
arXiv:2607.29613v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Vision-Language-Action (VLA) models has shown strong promise for robotic manipulation. Among RL methods,
arXiv:2511.21007v2 Announce Type: replace Abstract: Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Est
https://x.com/MiniMax_AI/status/2083006198828417501?s=20 Quote from their article: Today, we're launching MiniMax H3, a general-purpose multimodal generation model. H3 understands unified context acro
arXiv:2607.27201v1 Announce Type: new Abstract: World models enable a predictive substrate for planning and action, yet existing formulations merely answer a physical question: what/where it is, and h
arXiv:2607.24371v1 Announce Type: cross Abstract: Healthcare interoperability requires AI systems to produce structured outputs conforming to standardized schemas including ICD-10 for diagnostic codin
arXiv:2607.22555v1 Announce Type: new Abstract: Medical diagnosis is a multi-stage process: extract facts, consult knowledge, generate a differential analysis, and select the best diagnosis with expla
arXiv:2607.23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response. Recent works show the ini
arXiv:2507.05515v4 Announce Type: replace Abstract: Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grai