Knowledge catalogue
arXiv:2608.16844v1 Announce Type: cross Abstract: The quadratic cost of attention-based sequence models for long contexts has motivated a growing line of research on memory-based models that can compr
arXiv:2608.14929v1 Announce Type: new Abstract: Open-weight language models are fine-tuned, quantized, pruned, and merged, yet their provenance is often undocumented. We study data-free white-box line
arXiv:2608.14051v1 Announce Type: new Abstract: Deep learning models trained on datasets with spurious correlations can achieve high average accuracy whilst relying on shortcut features that do not ge
arXiv:2608.13628v1 Announce Type: new Abstract: Random vector functional link (RVFL) networks are lightweight and fast neural models that offer efficient training and strong generalization through ran
arXiv:2608.12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions. The relational model asked which records match a predicate; the vector model asked which ve
arXiv:2608.12904v1 Announce Type: new Abstract: Clinical intelligence requires estimating a patient's underlying condition from incomplete observations rather than learning isolated mappings from scan
Qwen3.8-27B is available on @ollama ！Any harness you run, the model always delivers. Let's code together, and show us what you build.😎 Qwen 3.8 27B is now available on Ollama. It's one of the best ope
The Information: DeepSeek launches V4-Pro, its most advanced model that rivals Kimi K3 on some benchmarks but is priced much lower, at 0.435/1M input and 0.87/1M output tokens — Chinese AI developer D
arXiv:2608.10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured
arXiv:2602.13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences. Progress is limited by a data
arXiv:2608.08689v1 Announce Type: new Abstract: The state evolution of a complex system arises jointly from object laws, relational propagation, domain conservation, and unmodeled error. Forcing all s
arXiv:2606.14574v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks
arXiv:2608.07786v1 Announce Type: new Abstract: Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships t
arXiv:2608.06898v1 Announce Type: cross Abstract: Researchers who seek to build social robot applications on foundation models are faced with a difficult question: how should we pick a model? Public l
Introducing Muse Glimmer, an open-weight 30B-parameter model optimized for local, always-on agent workflows. Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared w
arXiv:2608.06968v1 Announce Type: cross Abstract: Language-model agents act on state encodings of their environment, yet these are treated as interchangeable interfaces. Using pretrained language mode
arXiv:2505.16170v4 Announce Type: replace Abstract: We study the internal mechanisms that govern when LLMs choose to retract wrong answers, i.e., spontaneously and immediately acknowledge errors in th
arXiv:2608.07267v1 Announce Type: new Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies t
arXiv:2601.04098v2 Announce Type: replace-cross Abstract: Transformer language models systematically prefer tokens at specific input positions regardless of semantic relevance---a phenomenon known as
OpenAI says it is pausing 'internal activities' around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows i
Reuters: Sources: Alibaba plans to ask heavy commercial users of its next Qwen open model for a share of revenue; Moonshot's Kimi K3 requires up to a 30% revenue share — Chinese technology giant Aliba
arXiv:2608.03437v1 Announce Type: new Abstract: While human evaluation is the gold standard in many NLP tasks, it suffers from prohibitive costs and poor scalability. When identifying top-performing m
I‘m doing a research proposal at my company about running local LLMs to replace daily coding models. Qwen 3.6 27B (or 3.8 potentially) is widely seen as the best model in that 20-60GB space, is that s
I really like to use this one SQL benchmark when testing new models. I had another post some time ago with my benchmarks, but I decided to post a new one because of how well Deepseek did. I like the b
arXiv:2608.00932v1 Announce Type: new Abstract: The integration of artificial intelligence into medical question-answering systems has advanced rapidly; however, research remains predominantly focused
arXiv:2509.17920v2 Announce Type: replace Abstract: Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptabil
arXiv:2607.17977v2 Announce Type: replace Abstract: We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and p
arXiv:2607.29240v1 Announce Type: cross Abstract: In vision--language models, commonsense-driven hallucination (CDH) occurs when a model's commonsense prior overrides clear visual evidence of an atypi
Another day and another full frontier model running on your computer. Been teething DeepSeek V4 Flash on over 60 employees at The Zero Human Company for a few hours and it is stunning. Between Kimi K3
DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the model's agentic capabilities: ollama run deepseek-v4-flash:0731-cloud Use it with Claude Code: ollama
arXiv:2607.28568v1 Announce Type: new Abstract: Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a
arXiv:2607.27539v1 Announce Type: cross Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record. Addressable influence can be removed by algebraic
arXiv:2607.27940v1 Announce Type: cross Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint
arXiv:2607.26428v1 Announce Type: new Abstract: We study generative modeling of spatial point processes (SPP), where both the number of points and their spatial configuration are governed by a joint d
arXiv:2607.25479v1 Announce Type: cross Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text
arXiv:2607.25948v1 Announce Type: cross Abstract: Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-lang
arXiv:2602.16579v2 Announce Type: replace-cross Abstract: Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer
Alibaba has released Qwen Audio 3.0 Realtime, with the Plus variant debuting as the new #1 model on the Artificial Analysis Speech to Speech Index at 84.1%, ahead of GPT-Realtime-2.1 High at 79.1% Rel
arXiv:2607.22769v1 Announce Type: cross Abstract: The training efficacy of large language models (LLMs) is fundamentally constrained by the quality and composition of training data. Existing dynamic d
arXiv:2607.23899v1 Announce Type: cross Abstract: This exploratory study examines whether a large multimodal language model, GPT-5.1, can serve as the high-level controller of a physical mobile robot
arXiv:2607.22847v1 Announce Type: new Abstract: Human gaze does more than point to visual targets; it serves as a subtle indicator of social intent within static images, whereas standard models typica
arXiv:2607.24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stu
arXiv:2601.05680v2 Announce Type: replace-cross Abstract: While Transformer-based autoregressive models excel in data generation, their token discretization strategy inherently limits their precision
Interesting. Grok 4.6 releases around August 7. This will be the 1.5T model with significantly improved SFT & RL. Grok 4.7 will be the 2.1T model released a few weeks later. This will be better than 4
arXiv:2603.09255v2 Announce Type: replace-cross Abstract: Deep learning and computer vision techniques have become increasingly important in the development of self-driving cars. These techniques play
arXiv:2607.23580v1 Announce Type: new Abstract: Existing vector-sketch models treat recognition and generation as separate tasks, leaving a gap for streaming interfaces that must understand a drawing
arXiv:2607.23474v1 Announce Type: new Abstract: This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions
arXiv:2607.22067v1 Announce Type: new Abstract: The integration of large language models (LLMs) into the nuclear power industry requires outputs grounded in domain-specific knowledge. This study evalu
arXiv:2607.22101v1 Announce Type: new Abstract: Diffusion models have recently achieved remarkable success in high-fidelity image synthesis, yet their application to visual text generation and editing
Kimi K3 is now available on Ollama’s cloud. To use it with Claude Code, run: ollama launch claude --model kimi-k3:cloud Currently Kimi K3 requires a Pro or Max subscription, and consumes extra usage c
arXiv:2607.21655v1 Announce Type: cross Abstract: Robotic learning takes place in dynamic environments with large behavior spaces. A terminal success signal only tells the robot whether the task is co
arXiv:2607.09424v3 Announce Type: replace-cross Abstract: We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English
Anthropic: Anthropic launches Claude Opus 5, which it says comes close to Fable 5 performance at half the price; it is the new default model on Claude Max — Claude Opus 5 is available today. It's a th
arXiv:2607.20433v1 Announce Type: cross Abstract: While language models remain frozen at their training state, the world evolves continuously. Knowledge editing has emerged as a key alternative to ful
Opus 5 is a great model for coding, data analysis, design, biology, knowledge work. More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt inject
arXiv:2602.10226v2 Announce Type: replace-cross Abstract: Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyper
arXiv:2501.18897v4 Announce Type: replace-cross Abstract: Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty qua
arXiv:2508.14268v2 Announce Type: replace-cross Abstract: Feature selection and importance estimation in a model-agnostic setting is an ongoing challenge of significant interest. Wrapper methods are c
arXiv:2607.19343v1 Announce Type: new Abstract: Video models absorb rich priors over how the visual world moves, interacts, and responds to contact, making them promising substrates for robotic world
arXiv:2607.20058v1 Announce Type: new Abstract: Large language models can answer scientific questions, yet a correct output does not reveal whether the model represents or uses the governing physics.