Knowledge catalogue
arXiv:2512.16245v2 Announce Type: replace Abstract: Merging large language models (LLMs) is a practical way to compose capabilities from multiple fine-tuned checkpoints without retraining. Yet standar
arXiv:2610.15634v1 Announce Type: new Abstract: Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribu
NVIDIA Nemotron 3.5 Super VL is now available on Ollama This model combines reasoning and visual understanding across a range of agent workflows. On a single GPU, this model delivers up to 5x higher t
arXiv:2610.14180v1 Announce Type: new Abstract: Organisations that want language-model agents for security work face a choice between open-weight models, which they can run and audit themselves, and f
arXiv:2610.17333v1 Announce Type: cross Abstract: Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, w
arXiv:2610.17114v1 Announce Type: new Abstract: Frontier large language models (LLMs) now reason about space well enough to program robots, yet the world models behind robot policies are implicit, hel
arXiv:2610.17903v1 Announce Type: new Abstract: Vision-Language Models (VLMs) and world models have demonstrated strong capabilities in semantic understanding and future scene evolution for autonomous
arXiv:2610.17234v1 Announce Type: cross Abstract: Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignm
arXiv:2610.10203v1 Announce Type: new Abstract: Model organisms of alignment-relevant behaviors (e.g., backdoors, sycophancy, spurious correlations) have emerged as a key tool for evaluating whitebox
recently saw a bunch of open decision models pop out of nowhere in the last two weeks (laya, liquid's d1, cloudflare's clef-flash, interfaze's lev), so I wanted to see how far apart they actually are
arXiv:2610.07559v1 Announce Type: new Abstract: Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with
arXiv:2507.18104v3 Announce Type: replace Abstract: Brain encoding models predict time-resolved neural activity from computational representations of ongoing experience, providing a principled framewo
arXiv:2610.06744v1 Announce Type: cross Abstract: ufakzeka-karar is an open Turkish decision model with 182,494,466 parameters. Given a Turkish text and questions of a fixed answer type (a choice, a l
arXiv:2610.02840v1 Announce Type: cross Abstract: World action models jointly learn to forecast world dynamics and predict robot actions, such that the learned internal world dynamics guide accurate a
arXiv:2610.02304v1 Announce Type: cross Abstract: Existing Simulink benchmarks mainly evaluate whether generated models compile, execute, or resemble a reference model. These criteria do not establish
arXiv:2610.01847v1 Announce Type: cross Abstract: Model specifications define how large language models (LLMs) should behave, guiding alignment training, inference-time behavior, and evaluation. Yet t
arXiv:2610.01165v1 Announce Type: new Abstract: Layer interventions are widely used to probe the internal organization of language models, yet most analyses examine a single training checkpoint even t
arXiv:2609.38878v1 Announce Type: cross Abstract: A large audio language model (LALM) turns a minute of speech into 750-1,500 tokens and prefills every one. Image-token pruning often cuts after the la
arXiv:2609.40117v1 Announce Type: new Abstract: Time-series forecasting models achieve strong benchmark performance but exhibit severe systematic bias in industrial deployments. This train--deploy gap
arXiv:2609.39124v1 Announce Type: new Abstract: Generative models for tabular data are typically trained separately for each dataset, limiting knowledge transfer and requiring the storage of many spec
arXiv:2609.36097v1 Announce Type: cross Abstract: Using predictive models to explain cognition requires more than accurate behavioral predictions. Input ablations offer an appealing route: remove info
arXiv:2609.37076v1 Announce Type: new Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this iss
arXiv:2609.33158v1 Announce Type: new Abstract: Progress in AI-based retinal image analysis has advanced with foundation models, yet evaluating their reliability remains challenging. Performance repor
arXiv:2609.31394v1 Announce Type: cross Abstract: World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A central challenge is to integrate
arXiv:2609.31181v1 Announce Type: new Abstract: Black-box model identification works by scoring a model's response to natural-language prompts. One line of work feeds models a degenerate input -- thei
For instance whenever a model comes out, what’s the best engine to run it, the best harness and absolute minimum you need to get same or near same re results that the benchmark of that model claims. A
arXiv:2609.22949v1 Announce Type: cross Abstract: Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent
arXiv:2609.22241v1 Announce Type: new Abstract: We present H2LooP Telecom Model v1, a domain-specialized large language models fine-tuned for the telecommunications industry. We release two domain-ada
arXiv:2609.17542v1 Announce Type: new Abstract: Large language model services increasingly route each query to one of several models of differing capability, using a cheap estimate of query complexity
Hi Ollama Team, I’m writing regarding the announced retirement of GLM-5.1 from Ollama Cloud on 25 September 2026. I wanted to provide some fairly detailed technical feedback because GLM-5.1 is not sim
arXiv:2609.15801v1 Announce Type: new Abstract: We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain
arXiv:2603.27909v2 Announce Type: replace-cross Abstract: Car-following behavior is fundamental to traffic flow theory, yet traditional models often fail to capture the stochasticity of naturalistic d
arXiv:2609.11875v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models have improved robotic manipulation, yet observation-to-action learning remains limited by a funda
CancerBench: the frontier model cancer cure benchmark. AI lab CEOs keep talking about curing cancer, so I made a benchmark. One metric: how many types of cancer has your model cured? All models are cu
Quick setup on linux: STEP 0: install/download llama.cpp, Freecad, your favourite gguf model - possibly with multimedia image reading capabilities (I've used Qwen3.8-27B-UD-Q4_K_M and relative mmproj-
arXiv:2609.01861v1 Announce Type: new Abstract: The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an opti
arXiv:2609.02322v1 Announce Type: cross Abstract: The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at al
arXiv:2505.22156v4 Announce Type: replace Abstract: Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper sem
arXiv:2609.01090v1 Announce Type: new Abstract: Scientific knowledge about AI models is produced faster than the community can organize it. Every few months a new foundation model reshapes the field a
arXiv:2608.30188v1 Announce Type: new Abstract: Large Language Models (LLMs) show great potential as clinical agents, yet existing benchmarks reduce clinical workflows to static predictions or unconst
arXiv:2608.28995v1 Announce Type: cross Abstract: World models let robots imagine possible futures, but exploiting this capability for real-time control is bottlenecked by a representation misalignmen
arXiv:2607.16325v2 Announce Type: replace Abstract: Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meani
arXiv:2608.25275v1 Announce Type: cross Abstract: Learned traffic-behavior models are commonly trained separately for each intersection, creating model portfolios that cannot share evidence across sit
Luz Ding / Bloomberg: Alibaba releases Qwen3.8-Flash, an open-weight, 125B-parameter model built on its next-gen Qwen 4 architecture, saying it rivals Opus 4.6 and V4-Flash — Alibaba Group Holding Ltd
arXiv:2608.24068v1 Announce Type: new Abstract: Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, m
arXiv:2608.22552v1 Announce Type: cross Abstract: Decentralized federated learning (DFL) is a promising paradigm for autonomous nodes to collaboratively train AI models without relying on a central se
arXiv:2608.20974v1 Announce Type: cross Abstract: Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent featur
Spent way too long confused about why an 8B at Q4_K_M, about 4.9GB on disk, would OOM on a 12GB card. The weights fit twice over. The answer is the KV cache, and the math is simple enough that you can
It’s never been easier to start an AI-powered startup on Google Cloud. You grab an API key from Google AI Studio at breakfast, paste it into Antigravity, and by lunch you’ll have a nascent prototype o
arXiv:2608.18591v1 Announce Type: new Abstract: Uniformly allocating inference reasoning budgets to LLMs is expensive and prone to over-thinking penalties; especially in document tasks where visual la
arXiv:2608.15428v1 Announce Type: cross Abstract: Multiple-choice benchmarks are graded on whether a model picks the right option, not on whether it needed the question. Measuring that gap takes care:
arXiv:2608.16620v1 Announce Type: cross Abstract: Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Exper
Written by: Alex Tselevich, Michael Maturi Introduction Adversarial misuse of AI has increased the risk of data theft and extortion events, because when proprietary source code is exposed, defenders m
arXiv:2608.15255v1 Announce Type: new Abstract: Domain modeling plays an essential role in domain-driven design, capturing essential entities and their relationships within a specific domain. Despite
arXiv:2608.13951v1 Announce Type: new Abstract: Scaling agent capability has largely focused on improving the model, yet an interactive agent acts through a runtime harness that mediates context, tool
arXiv:2608.14399v1 Announce Type: cross Abstract: Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermedia
arXiv:2608.11210v1 Announce Type: new Abstract: Bayesian calibration of process-based models requires a prior distribution for each model parameter. Despite decades of methodological work, researchers
arXiv:2608.09604v1 Announce Type: cross Abstract: Over the past decade, microfacet-based BRDF models have formed the foundation of real-time rendering pipelines. Despite their widespread use, they oft
arXiv:2608.08069v1 Announce Type: cross Abstract: Foundation models are increasingly reused as software components, making model selection a critical software-engineering decision. Current model hubs
Meta Platforms Inc. today released Muse Glimmer, an open-source language model that can run on personal computers. The company also published a lengthy essay penned by Chief Executive Officer Mark Zuc