Knowledge catalogue
arXiv:2609.30446v1 Announce Type: new Abstract: This paper presents a novel approach to infer protein topology using the state-of-the-art graph neural network (GNN), SchNet. The model is trained on th
https://preview.redd.it/23cumykhabsh1.png?width=944&format=png&auto=webp&s=0b1d1c437fc845169f521b31793e2b1325dab0dd Reminder that you can put Qwen 3.8 27B as a subagent and its a workhorse. Pic: using
Six months ago, a result like this was unthinkable. But now we can say it loud and clear: local models are at the cutting edge, and the gap of just a few months has been confirmed. Personally, I use Q
I benchmarked Qwen3-VL 8B Instruct (Q4_K_M, Ollama, M5 24GB, ~30s/doc) against Claude Opus 5.5, Sonnet 5 and GPT-5.6 Terra on: - receipts: CORD (Indonesia) and SROIE (Malaysia), 30 each - 20 scanned 1
arXiv:2609.30576v1 Announce Type: new Abstract: Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation
arXiv:2609.31376v1 Announce Type: cross Abstract: Congenital heart disease (CHD) is the most common birth defect, yet a large fraction of cases remain undetected on prenatal ultrasound, in part becaus
arXiv:2609.30722v1 Announce Type: cross Abstract: Existing roadside traffic datasets support perception, forecasting, and visual question answering, but they do not evaluate counterfactual video gener
arXiv:2609.31002v1 Announce Type: new Abstract: Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but al
Ethan Mollick invited readers to discuss the distinctions between **pure large language models (LLMs)**, **multimodal LLMs** that process multiple data types (e.g., text, images), and **multimodal LLM
Spent the whole day today trying to create this random transformation video. In total, I generated around 180 videos. A few initial images were generated with Krea2, and later all edits were done with
Hi! I'm the author of MoEspresso, which is my way of putting my own ideas about inference engines to the test. A lot of the fun has been trying different design choices, measuring what happens, and fi
Just made this post for those who missed it : https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b UkisAI released their updated Qwen 27B (tuned for token efficiency). I grabbed the IQ4_XS quant to tes
I wish Qwen also released dataset and method to fully train a model ourselves but it is what it is. However, I come here with my stupid question because someone can answer it better. And will the mode
arXiv:2609.28504v1 Announce Type: cross Abstract: Scientific progress is a key driver of economic growth and prosperity. There is great excitement - but also concerns - about the impacts of AI on scie
arXiv:2603.11133v2 Announce Type: replace Abstract: Sequence modeling tasks can involve intrinsic higher-order dependencies, while standard self-attention assigns scores to token pairs and does not ex
arXiv:2609.29069v1 Announce Type: new Abstract: We introduce BranchShine-CR, a 25M-parameter model for multilingual transcription into the International Phonetic Alphabet (IPA). It combines log-mel fe
arXiv:2609.08646v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed with hierarchical instructions, yet they remain vulnerable to conflicts in which user directi
arXiv:2609.29225v1 Announce Type: new Abstract: Lip synchronization aims to generate visual lip dynamics that align precisely with speech audio. Despite the high generation quality of diffusion models
arXiv:2609.30055v1 Announce Type: cross Abstract: In the Era by Eon benchmark, each question states the rules for its answer, and code computes the answer from a generated company's data. When agents
arXiv:2609.29861v1 Announce Type: new Abstract: We investigate whether GPT-6-Astra, a general-purpose foundation model, can navigate unfamiliar environments using its own perception, reasoning, and de
arXiv:2609.29328v1 Announce Type: new Abstract: Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnost
arXiv:2609.30147v1 Announce Type: new Abstract: Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge o
arXiv:2601.06676v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based deep research agents perform multi-step reasoning, web exploration, and long-form report generation. In these
We hosted Kev 4B (Jared Palmer's Apache-2.0 fine-tune of Qwen3.5-4B) and ran it side by side with Jev on the same endpoint to see how it compares. We built a fresh set of 362 items published after bot
arXiv:2609.29101v1 Announce Type: new Abstract: Medical Named Entity Recognition (NER) for low-resource languages remains a challenging task due to high linguistic variability and a scarcity of domain
arXiv:2609.29802v1 Announce Type: new Abstract: Scientific ideation is increasingly mediated by large language models, but current ideation systems are usually trained and evaluated on immediately jud
I finally got around to upgrade the GPU's. First a word of warning, when upgrading GPU's on P520 you have to be extra careful not to slot the card on any angle other than straight when installing or w
arXiv:2609.28851v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong visual reasoning performance, yet subtle changes from routine image capture and processing can alter their
arXiv:2609.29908v1 Announce Type: cross Abstract: Neural models can learn to generate various solutions to the inverse kinematics problem from data, but are usually limited to a single robot. We prese
arXiv:2609.30130v1 Announce Type: cross Abstract: Current vision-language models (VLMs) excel at visual content understanding and text-based reasoning, yet their structure limits the advancement of in
arXiv:2609.28539v1 Announce Type: new Abstract: Gaussian head avatars typically model intrinsic facial appearance as temporally static, omitting subtle cardiac-induced skin-color variation. We propose
arXiv:2609.30094v1 Announce Type: new Abstract: Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sen
arXiv:2402.10149v3 Announce Type: cross Abstract: In collider experiments, the kinematic reconstruction of heavy, short-lived particles is vital for precision tests of the Standard Model and in search
arXiv:2609.29935v1 Announce Type: cross Abstract: We study the detection of LLM-generated text under editing and contamination. Modeling human and machine text as finite-order Markov processes with Hu
arXiv:2609.29543v1 Announce Type: new Abstract: Agent skills bundle procedural guidance with execution conditions governing authority, user consent, and live environment state. When model capabilities
arXiv:2609.30071v1 Announce Type: new Abstract: The English Resource Grammar (ERG) is a hand-written computational grammar of English. Given a sentence, its processor, ACE, produces a formal meaning r
arXiv:2609.28560v1 Announce Type: cross Abstract: Evaluating a stochastic large language model is costly: benchmark scores estimate expected performance from randomized rollouts, yet uniform repetitio
arXiv:2609.29169v1 Announce Type: cross Abstract: We introduce Spot, Separate, and Enhance (SSE), the first multimodal, user-guided generative model for audio remixing and enhancement. SSE enhances vi
arXiv:2609.29465v1 Announce Type: new Abstract: Large language model based coding agents have made substantial progress on repository-level software engineering tasks. Existing repository benchmarks,
arXiv:2507.00938v4 Announce Type: replace-cross Abstract: Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsin
Entire database engineering careers have been spent on a single question: How do you scale an OLTP workload without compromising the system of record that owns the data? Exadata answered the question
arXiv:2609.27615v1 Announce Type: new Abstract: In multimodal emotion recognition (MER), human affective states are inferred by integrating complementary cues from multiple modalities. In audio-text M
arXiv:2609.28090v1 Announce Type: cross Abstract: Backtest auditing is a calibration problem: high flaw recall is not useful when the model falsely flags matched clean strategies. We build a 96-item p
arXiv:2609.26905v1 Announce Type: cross Abstract: Stacking heterogeneous vision backbones (CNNs, ViTs, and hybrids) is the de facto recipe for accuracy, calibration, and robustness, yet two coupled pa
arXiv:2609.27165v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to measure public value orientations from long social media posts, yet such posts often mix backgro
arXiv:2609.27069v1 Announce Type: cross Abstract: Graph neural networks dominate recent work on microservice root-cause analysis, yet recent results question whether the graph contributes. Those resul
arXiv:2609.28150v1 Announce Type: new Abstract: Closed-loop revision is increasingly used in large language model (LLM) applications, but failures may reflect incomplete feedback or ineffective respon
Latin America’s small and medium-sized businesses are the heartbeat of the region's economy — accounting for more than 60% of total employment in the region, according to United Nations estimates. And
arXiv:2609.28086v1 Announce Type: cross Abstract: We propose LAYERSCOPE, a label-free, layerwise framework that aims to characterize a model's learned representations in video and multimodal settings.
arXiv:2609.27637v1 Announce Type: cross Abstract: Traffic flow forecasting is essential to intelligent transportation systems. Large-scale traffic forecasting requires jointly modeling local spatial d
arXiv:2609.27747v1 Announce Type: cross Abstract: Vision-language-action models (VLA) promise human-steerable autonomous driving, but their training is bottlenecked by the scarcity of frames paired wi
arXiv:2609.28431v1 Announce Type: new Abstract: Dexterous manipulation demands long-term foresight and rapid reactive control. Vision-Language-Action (VLA) models, while proficient in high-level reaso
I'm about to buy a Mac Studio mainly for running LLMs locally and I'm stuck between two configs: M5 Ultra (30/64) with 96GB: 1.2 TB/s bandwidth, roughly 1.7x faster generation and much faster prefill
arXiv:2609.28399v1 Announce Type: new Abstract: Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We
arXiv:2609.26841v1 Announce Type: cross Abstract: High-capacity neural network models have achieved state-of-the-art performance across diverse classification tasks, yet they frequently operate as bla
arXiv:2609.28286v1 Announce Type: new Abstract: Estimating the Planetary Boundary Layer Height (PBLH) from satellite observations is a challenging regression problem due to the indirect relationship b
A while ago I posted 15 tok/s output and 100-120 tok/s prompt processing with the IQ3_XXS quant on a 12GB RTX 5070 using llama.cpp. Since then I built my own inference engine for this one model and th
arXiv:2609.28064v1 Announce Type: new Abstract: Driving world-action models improve planning by coupling multimodal reasoning with future prediction, but their growing inference cost increasingly conf
arXiv:2609.27904v1 Announce Type: new Abstract: As information technology advances, digital content has become widely adopted across diverse fields such as news broadcasting, entertainment, commerce,
arXiv:2609.27321v1 Announce Type: new Abstract: Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training r