Knowledge catalogue
Hi all! After all the jev hype I wanted to try by myself and got qwen3.8 27b to mix-and-match open implementations on top of ninfer, and to be honest I'm quite impressed with the results, latency is n
arXiv:2609.21749v1 Announce Type: new Abstract: Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, while skill optimization further
Grok 4.7 xHigh is now at the top with just ONE point away from Claude Fable 5.1 Max on Artificial Analysis’ AA-Briefcase benchmark Claude Fable 5.1 Max — 59% Grok 4.7 xHigh — 58% Just a 1-point differ
arXiv:2609.20825v1 Announce Type: new Abstract: Clinical predictive models often rely on structured Electronic Health Record data, such as time-series and procedure codes. While recent approaches have
arXiv:2609.21379v1 Announce Type: new Abstract: Accurate traffic forecasting requires both understanding scene dynamics and synthesizing realistic future observations. Recent diffusion-based video gen
been working on this thing called OpenComms for a bit. basically i keep multiple coding agents open at once, usually stuff like a lead, builder, reviewer etc, and i got sick of copying messages betwee
arXiv:2609.20850v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easil
arXiv:2609.20945v1 Announce Type: new Abstract: Undesired information such as harmful content and private data propagates through Multilingual Large Language Models (LLMs) via direct training and indi
arXiv:2609.21392v1 Announce Type: new Abstract: Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather
arXiv:2609.22069v1 Announce Type: new Abstract: Reference-to-video (R2V) generation is evolving toward increasingly general and versatile reference control, giving rise to the emerging paradigm of omn
arXiv:2609.21561v1 Announce Type: cross Abstract: On-policy self-distillation provides dense, token-level supervision by conditioning a model on privileged information and distilling the resulting tea
arXiv:2609.21626v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized different
arXiv:2609.21673v1 Announce Type: new Abstract: Probabilistic Graphical Models (PGMs), especially Bayesian Networks (BNs), expose directed structure and probabilistic parameters, making them natural s
Qwen-Image-2.1 × @HuggingApps: live demo on Spaces! 🖼 One single checkpoint for generation and editing. Try it in your browser, no setup needed. 👇 Qwen Image 2.1 is here! 🖼️ A 7B params native image g
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:2609.21636v1 Announce Type: cross Abstract: Recent work applies human psychometric questionnaires to large language models to elicit moral and value profiles, but it is not clear whether these i
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:2609.21139v1 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:2510.02259v2 Announce Type: replace Abstract: Computational simulations play a central role in scientific discovery, and machine learning (ML) has emerged as a promising alternative to tradition
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
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
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
Claude not having an image generator is a gap in agentic projects that involve knowledge work. It is quite good at using code to draw or model objects, but image generators from Google and OpenAI give
Released: Update your ComfyUI for workflow Weights: https://huggingface.co/Comfy-Org/Qwen-Image-2.1/tree/main Variety of Examples https://youtube.com/watch?v=tP_gGGJzEqg&feature=youtu.be https://model
I am trying to learn more about long-term memory and how people are handling that nowadays. Historically, I have used a mixture of paid cloud AI services (ChatGPT, Gemini, OpenRouter API) and my own l
Play it right in your browser, no download. Some of the GLB’s are messy, but overall I’ve enjoyed playing with it, and the last iteration made was the gun/weapon placement. Contributors are welcome, w
LlamaIndex 发布了一个面向 AI Agent 的文档解析评测基准「ParseBench」 @llama_index 100 种解析方法参与评测（vlm - 67、专用解析器 - 33），2000 页真实企业文档（人工两轮校验），169011 条确定性规则，完全不用 LLM 当裁判，可复现。评测五个维度取无加权平均：表格结构、图表抽取、内容忠实度、格式语义、视觉定位。 https://ww
I’m one of the co-founders of NYX AI. It’s a Windows app that connects to local models through Ollama/lm studio or supported cloud providers, giving AI tools to work with documents, previews, spreadsh
Note: This writeup was put together with the help of AI. So I've got dual AMD MI50 32GB cards. If you know these cards, you know the story - AMD dropped official ROCm support for gfx906 after ROCm 5.7
6 billion tokens for $65 Is it as good as Astra and Fable at hard stuff? No of course not. But you don't always need a genius and can just call one for advice when you do. Extrapolate where this is go
Anthropic PBC has opened a wet lab, a facility dedicated to biology research, in the San Francisco Bay Area. Reuters reported today that the company will use robots to automate certain scientific task
arXiv:2609.19325v1 Announce Type: cross Abstract: Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket re
I have this idea I'd like feedback on. most camera footage for training, is sunny daytime, because that's what cameras record most of the time. The edge cases models actually struggles with, like nigh
vocab : add ufakzeka pre-tokenizer (#29033) vocab : add ufakzeka pre-tokenizer vocab : move ufakzeka to the models list and regenerate the hash mapping Website: https://llama.app Attestations: https:/
arXiv:2609.20223v1 Announce Type: new Abstract: We study weakly supervised incremental telecom fraud detection from raw telephone audio, where training provides only conversation-level labels and pred
arXiv:2609.19842v1 Announce Type: new Abstract: Effective EEG decoding requires representations that preserve organization among channels, local waveform dynamics, and long-range temporal context. Exi
arXiv:2609.20027v1 Announce Type: new Abstract: Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, un
arXiv:2609.19789v1 Announce Type: new Abstract: Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial i
So I know that Ollama is built on top of llama.cpp, I decided to run a model on both and applied settings on llama.cpp like flash attention and q8/q4 kv cache. On Ollama (using the Python package) I w
arXiv:2609.20676v1 Announce Type: new Abstract: Causal discovery from observational data is fundamental to statistics and machine learning, yet determining causal direction without interventions neces
arXiv:2609.20198v1 Announce Type: new Abstract: Financial sentiment measures are widely used in empirical finance, but it remains unclear whether general-purpose large language models (LLMs) improve o
arXiv:2609.20067v1 Announce Type: new Abstract: Deep learning models for multi-modal breast cancer diagnosis achieve high predictive accuracy but remain clinically unacceptable without actionable, cou
arXiv:2609.19559v1 Announce Type: new Abstract: Heterogeneous federated learning requires clients with diverse computational capacities to collaboratively train a global model, where each client train
arXiv:2507.10059v2 Announce Type: replace Abstract: Large Language Models have achieved remarkable performance across a large number of tasks, but face critical deployment and usage barriers due to su
arXiv:2609.20508v1 Announce Type: new Abstract: E-commerce livestreams have emerged as an important channel for presenting products to online consumers, containing multiple products whose information
arXiv:2502.17003v2 Announce Type: replace-cross Abstract: Transfer-based adversarial attacks rely on surrogate models to craft perturbations, yet often overfit the surrogate's decision boundary. To ad
arXiv:2609.19944v1 Announce Type: new Abstract: Large language models (LLMs) have been applied to causal discovery, but candidate-graph generation rarely treats premature omission of potentially relev
MiniMax has released the source code for MiniMax Code’s terminal agent: https://github.com/MiniMax-AI/minimax-code https://preview.redd.it/st9izmm8zaqh1.png?width=3016&format=png&auto=webp&s=5853bc316
arXiv:2609.20323v1 Announce Type: new Abstract: Three-dimensional reconstruction from unorganized point clouds remains a challenging problem in computer vision, geometric modeling, and computer-aided
arXiv:2609.20578v1 Announce Type: cross Abstract: Connected-vehicle safety evaluations rely on coupled traffic and network simulations, but standard channel models ignore radio resource competition in
arXiv:2609.20816v1 Announce Type: cross Abstract: Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and edi
arXiv:2609.19985v1 Announce Type: cross Abstract: Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis
arXiv:2609.19983v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data, but training and inference on large graphs are often bottl
arXiv:2609.19636v1 Announce Type: new Abstract: Reinforcement learning now trains language-model agents that act over dozens of steps in live environments. The gains are large, and they are read as be
Say it with me. “OpenAI is terrible at cybersecurity.” This is crazy. In late July, 'three guys with Claude and Codex subscriptions' were able to use Opus 5 to access OAI auth tokens and gain write ac
arXiv:2609.19483v1 Announce Type: new Abstract: Text-based person retrieval under a sim-to-real gap (synthetic training data, a real-image gallery) is usually tackled with costly fine-tuned cross-enco
Ternary Bonsai 2 27B Tried it out and was excited. Gave it a prompt 'create a 3d little planet globe where I (player can walk around) and it has all these biomes to explore, the globe doesn't have to
arXiv:2609.19924v1 Announce Type: cross Abstract: Large Language Models (LLMs) transform vast collections of unstructured text into semantic patterns used for language generation and reasoning tasks.
arXiv:2609.19167v1 Announce Type: new Abstract: As AI systems evolve into personalized digital companions, a central capability is reasoning over a user's long-term personal history: not merely storin
arXiv:2609.19878v1 Announce Type: cross Abstract: Multimodal reasoning requires models to draw on information from multiple modalities throughout the reasoning process. Yet existing methods often conc