Knowledge catalogue
Kimi K3 is now available for inference & training in @FireworksAI_HQ. Crazy how easy they make it to tune frontier open models like K3 using LoRA adapters. Best time to figure out how to own your inte
arXiv:2505.23378v3 Announce Type: replace Abstract: Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications. While mixed-effect models are comm
arXiv:2607.21665v1 Announce Type: new Abstract: Proactive service assurance in O-RAN requires predicting per-slice SLA violations before they occur. The prediction model must be auditable by operators
AI Security Institute: A joint preliminary evaluation by the UK's AISI and the US' CAISI finds Kimi K3 trails leading US frontier closed weight models on cyber capability — The UK Artificial Intellige
arXiv:2607.19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating more for reliable sour
arXiv:2607.19910v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly expected to automate visualization development by generating code directly from visual designs
arXiv:2607.19261v1 Announce Type: new Abstract: Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, examining them across magnifications, and integrating multi-scal
arXiv:2512.11899v2 Announce Type: replace Abstract: Large vision-language models (LVLMs) are vulnerable to typographic attacks, where misleading text inserted into an image can override visual underst
arXiv:2607.19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods ofte
arXiv:2607.19459v1 Announce Type: cross Abstract: Modeling galaxy-galaxy strong gravitational lenses to infer the brightness of the source galaxy and the mass distribution of the foreground galaxy is
arXiv:2607.13386v1 Announce Type: new Abstract: Building foundation models for medical imaging requires pooling data across institutions, yet privacy regulations prohibit centralized aggregation. Exis
Open models are already being used in the enterprise. Over 85% of the Fortune 500 companies already use Ollama to fulfill specific tasks. @jmorgan Why open models and Ollama? Ownership. Open models ar
arXiv:2607.13314v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) generate predictions on structured data via in-context learning, without task-specific estimation. We ask whether TFM
arXiv:2511.09483v3 Announce Type: replace Abstract: While multimodal large language models can describe visual content, their ability to generate executable procedures remains underexplored. CrochetBe
arXiv:2607.12454v1 Announce Type: new Abstract: Multivariate Time Series Anomaly Detection (MTSAD) is essential for reliability and safety in domains such as industrial process monitoring and financia
Generic AI models are not built for medicine. Doximity Ask, trained and served on Fireworks, outperformed GPT-5.6 Sol, Claude Fable 5, and OpenEvidence in a Stanford-Harvard clinical AI safety study.
arXiv:2510.12311v2 Announce Type: replace-cross Abstract: We develop interacting particle algorithms for learning latent variable models with energy-based priors. To do so, we leverage recent developm
arXiv:2607.12771v1 Announce Type: cross Abstract: Reaction mechanisms consist of the step-by-step sequences of elementary reactions that explain chemical transformations. Learning the mechanism logic
arXiv:2607.12104v1 Announce Type: cross Abstract: Machine learning models for system diagnostics rely on kernel execution traces to capture fine-grained system behavior, but collecting production trac
arXiv:2607.07951v1 Announce Type: new Abstract: Wildfire smoke events produce extreme PM_{2.5} concentrations that pose severe public health risks, yet forecasting rare, hazardous-level spikes remains
arXiv:2607.08056v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks. Recent research demonstrates that a
arXiv:2607.07128v1 Announce Type: new Abstract: Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple
arXiv:2607.06796v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing. Howe
arXiv:2510.09595v3 Announce Type: replace Abstract: Competitive programming problems are increasingly used to evaluate the coding capabilities of large language models (LLMs) due to their complexity a
arXiv:2510.13817v2 Announce Type: replace Abstract: The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountabili
arXiv:2607.06328v1 Announce Type: new Abstract: The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning un
arXiv:2607.05861v1 Announce Type: new Abstract: Large reasoning models (LRMs) improve language model capabilities by generating explicit thinking traces before final answers. In factuality-oriented qu
arXiv:2509.15206v3 Announce Type: replace Abstract: The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to l
arXiv:2509.23722v2 Announce Type: replace-cross Abstract: Pipeline parallelism is widely used to train large language models (LLMs). However, increasing heterogeneity in model architectures exacerbate
arXiv:2607.02961v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as pe
arXiv:2607.02711v1 Announce Type: new Abstract: Recent 3D foundation models, such as DUSt3R, MASt3R, VGGT, pi^3, and Depth Anything 3, provide strong feed-forward depth and pose estimates on pinhole i
arXiv:2606.14216v2 Announce Type: replace Abstract: Accurate and computationally efficient vehicle models are essential for motion planning of autonomous vehicles, where positional accuracy directly a
arXiv:2607.03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Prefer
arXiv:2607.04013v1 Announce Type: cross Abstract: Learning from few labeled examples is a central challenge in tabular machine learning, and it becomes the binding constraint in domains where labeling
Most models run on whatever inference engine they ship with. That's rarely the fastest option. We built our own, AGI-RUN. On a phone it beat every model's own native engine, and ran up to 9.9x faster
arXiv:2607.02269v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG). However, current evaluation protocols are l
arXiv:2607.01844v1 Announce Type: cross Abstract: This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes va
arXiv:2607.01444v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models offer inference speedups via selective activation but impose substantial memory requirements because the whole network
arXiv:2603.02112v2 Announce Type: replace-cross Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We id
arXiv:2603.06001v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasing
arXiv:2607.02214v1 Announce Type: new Abstract: Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires
arXiv:2512.11891v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, de
arXiv:2511.04500v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in high-stakes domains and as imitators of human behavior in the so
arXiv:2607.00310v1 Announce Type: cross Abstract: Foundation video diffusion models are increasingly viewed as world simulators for embodied agents, yet their pretraining on internet-scale generic vid
arXiv:2606.30899v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious beh
arXiv:2606.31808v1 Announce Type: new Abstract: Language model systems built around proprietary APIs often operate on a token-based cost model. This becomes prohibitively expensive in the context of l
arXiv:2606.31187v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard
arXiv:2606.31734v1 Announce Type: new Abstract: Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical c
arXiv:2606.31250v1 Announce Type: cross Abstract: Large language models (LLM) trained on web-scale corpora generate output that may infringe copyright, yet existing technical safeguards focus narrowly
arXiv:2606.31382v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have made significant strides in embodied intelligence by integrating the powerful representations of pre-trained Vi
arXiv:2606.30687v1 Announce Type: cross Abstract: Diffusion models are increasingly utilized for modeling molecular structures and conformational ensembles, yet the thermodynamic meaning of their lear
arXiv:2606.30852v1 Announce Type: new Abstract: Reasoning models spend different amounts of useful computation across instances, but it remains unclear when a learned stopping rule improves over simpl
arXiv:2606.31404v1 Announce Type: new Abstract: Human swarm intelligence demonstrates remarkable collective accuracy but faces scalability constraints in cost, coordination, and time. We investigate w
arXiv:2606.31672v1 Announce Type: cross Abstract: Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory an
arXiv:2606.31846v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and
arXiv:2606.28406v1 Announce Type: cross Abstract: Text-to-image and multimodal generative models are increasingly used to produce scientific figures such as mechanism diagrams, experimental-design sch
arXiv:2606.29685v1 Announce Type: new Abstract: How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm? Existing child safety evaluations
arXiv:2606.28551v1 Announce Type: cross Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchm
arXiv:2606.29522v1 Announce Type: cross Abstract: A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with
arXiv:2512.08505v2 Announce Type: replace Abstract: Conditional diffusion models frequently suffer from language-image misalignments. Due to the ambiguity of intermediate noise corrupted latents, asse