Knowledge catalogue
arXiv:2608.20187v1 Announce Type: cross Abstract: Practitioners inferring causality from observational data usually rely on a single method and treat its output as causal truth. Recent tools select an
arXiv:2608.19914v1 Announce Type: new Abstract: Network topology inference from graph signals is central to graph signal processing with applications in neuroscience, sensor, and social networks. In p
arXiv:2608.19971v1 Announce Type: new Abstract: Multimodal sentiment analysis aims to infer affective states by integrating language, visual, and acoustic cues. However, real-world multimodal inputs a
arXiv:2608.19825v1 Announce Type: cross Abstract: Medical image captioning is a technique that accelerates early-stage diagnostic workflows and enhances the interpretability of medical diagnostic AI s
arXiv:2608.19748v1 Announce Type: cross Abstract: Inference-time selection methods, such as Best-of-N, improve generation by sampling a pool of candidates and selecting the top-ranked completion accor
arXiv:2608.18780v1 Announce Type: new Abstract: Non-Intrusive Load Monitoring (NILM) systems estimate individual appliance energy consumption from a single aggregate meter, without requiring separate
arXiv:2608.18498v1 Announce Type: new Abstract: Modeling object dynamics from limited visual observations is a fundamental problem for enabling accurate motion trajectory prediction in embodied intera
arXiv:2608.18147v1 Announce Type: cross Abstract: Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input wh
Four days ago I released a hyper-optimized Qwen3.8-27B inference engine for an RTX 3090 (82 tps single request, 672 peak). Since then it went to ~114, then ~138 tps single-user with DFlash2 drafting a
arXiv:2608.19078v1 Announce Type: new Abstract: Foundation models are increasingly adapted for downstream medical imaging tasks, yet the influence of the chosen adaptation strategy on subgroup fairnes
arXiv:2608.17352v1 Announce Type: new Abstract: Distributed Denial-of-Service (DDoS) attacks threaten network availability, requiring a cognitive detection process that senses traffic, infers intent,
arXiv:2608.18004v1 Announce Type: new Abstract: Probabilistic modeling of physical fields benefits from both a data-driven prior and known physical structure such as the governing equations. Energy-ba
arXiv:2509.00203v3 Announce Type: replace Abstract: Parameterized partial differential equations (PDEs) underpin the mathematical modeling of complex systems in diverse domains, including engineering,
Edit: Title says 134 tps, it's actually 138 -- keep in mind my 3090 is power limited to 250w. Three days ago I released a hyper-optimized Qwen3.8-27B inference engine for an RTX 3090 (82 tps single re
arXiv:2602.01115v3 Announce Type: replace-cross Abstract: Diffusion-based visuomotor policies excel at modeling action distributions but are inference-inefficient, since recursively denoising from noi
arXiv:2608.17414v1 Announce Type: new Abstract: Chart editing requires inferring and modifying visualization code from a reference chart image based on an editing instruction, challenging fine-grained
arXiv:2608.18021v1 Announce Type: new Abstract: WEASEL 2.0 is a dictionary-based time series classifier that combines dilated sliding windows with a randomised hyperparameter ensemble and a fixed-size
Thoughts About Scaling Law Scaling, but not only of parameters. Every model release now ends with the same question: how many parameters? It isn't a question that can be answered on its own. Parameter
arXiv:2608.17957v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) increasingly rely on in-context learning, where a model receives labelled examples at inference time and predicts label
arXiv:2608.15117v1 Announce Type: new Abstract: Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step
Brex’s summer benchmark shows how quickly the infrastructure behind the agent economy is growing. 14 of the 25 fastest-growing software vendors serve teams building AI products, and Together AI ranks
arXiv:2608.15454v1 Announce Type: new Abstract: Byte-level hierarchical language models (LMs) have recently emerged as a robust alternative to their popular counterparts that use subword tokenization.
arXiv:2608.15645v1 Announce Type: new Abstract: Transporting a causal conclusion from a source study population to a target one is a fundamental problem in causal inference. The theory of transportabi
arXiv:2501.18898v4 Announce Type: replace Abstract: Generating full-body human gestures based on speech signals remains challenges on quality and speed. Existing approaches model different body region
arXiv:2608.15520v1 Announce Type: new Abstract: A multimodal system may begin inference holding only some of its inputs and may acquire the rest at a cost. With adaptive acquisition, the policy determ
arXiv:2511.21317v2 Announce Type: replace Abstract: The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly
arXiv:2608.15783v1 Announce Type: cross Abstract: In transfer-learning settings, a model derived from abundant surrogate labels may be deployed in a target population where gold-standard outcomes are
arXiv:2608.15922v1 Announce Type: cross Abstract: We show that the natural-gradient stationary condition of variational inference has an edge-local form on a Forney-style factor graph. We start from t
arXiv:2608.14727v1 Announce Type: new Abstract: Fabric inspection in the garment industries of low-income economies remains largely manual, and commercial vision systems are priced beyond most small a
arXiv:2608.16038v1 Announce Type: cross Abstract: Post-hoc Graph Neural Network (GNN) explainers commonly follow a Perturb-Query paradigm, inferring the importance of graph elements based on queried p
arXiv:2608.14650v1 Announce Type: new Abstract: Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation. We study a n
arXiv:2608.15924v1 Announce Type: new Abstract: Cloud-side inference gives imitation-learning policies access to greater computational resources, but communication and computation delays can degrade c
arXiv:2608.16786v1 Announce Type: new Abstract: Inference-time quality-enhancement methods are an effective and widely adopted means of improving diffusion models without expensive retraining. We stud
arXiv:2507.12399v3 Announce Type: replace Abstract: Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied
NVIDIA cuML and cuVS now support multi‑GPU all‑neighbors kNN graph construction in UMAP, enabling end‑to‑end scaling of the dimensionality reduction algorithm to hundreds of billions of vectors. The i
arXiv:2604.04120v2 Announce Type: replace Abstract: Long chain-of-thought (Long-CoT) reasoning models have motivated a growing body of work on compressing reasoning traces to reduce inference cost, ye
arXiv:2508.09105v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and conte
arXiv:2608.16856v1 Announce Type: cross Abstract: Decentralized lending lacks a credit bureau: a borrower's capacity to repay must be inferred entirely from public on-chain activity, without income ve
arXiv:2608.14036v1 Announce Type: new Abstract: Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge. However,
I'm back. Yesterday I released the first version of hyper-optimized Qwen3.8-27B inference engine for a RTX 3090, reaching 82 tps on single request and 672 peak. Over the last 24 hours I've been explor
arXiv:2608.14004v1 Announce Type: new Abstract: In-context learning is commonly formalized as inference from examples of a function. Partial orders instead combine transitivity, antisymmetry, and inco
arXiv:2608.14070v1 Announce Type: new Abstract: Video virtual try-on is a highly constrained editing task requiring the precise replacement of a target person's clothing while strictly preserving the
arXiv:2608.14254v1 Announce Type: cross Abstract: Fugitive emissions from waste sites increasingly expose communities to toxic and odorous gases, yet public-health responses remain largely retrospecti
arXiv:2608.14420v1 Announce Type: new Abstract: Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at infe
arXiv:2602.15572v3 Announce Type: replace Abstract: Agent-based modelling (ABM) is a widespread approach to simulate complex systems. Advancements in computational processing and storage have facilita
arXiv:2608.14349v1 Announce Type: new Abstract: We present a training-free method for multi-modal trajectory prediction that achieves comparable accuracy to a 57M-parameter transformer while requiring
arXiv:2607.16298v2 Announce Type: replace Abstract: Feature-suppression evaluations infer model reliance on shape or texture from the accuracy loss caused by attenuating each type of information. Such
arXiv:2608.14148v1 Announce Type: new Abstract: We introduce editable state-conditioned visual instance binding, a multi-turn localization setting in which several support-defined instances are introd
arXiv:2608.13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal inference. We study a different possibility: stable mi
arXiv:2608.14079v1 Announce Type: new Abstract: Silicon sampling can produce surprisingly good population estimates at times. Does doing it fast attenuate such fidelity? In this study, we extend and a
arXiv:2608.13621v1 Announce Type: new Abstract: A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emi
Fantastic initiative by @nvidia. “Circular financing” is thrown around as a pseudo intellectual gotcha, while everyone in the AI infrastructure business is witnessing demand curves that are so rapidly
I’m running Ollama on an M4 Pro Mac with 48 GB unified memory and testing local coding models for repository work. Direct Ollama inference is fine. Qwen3.8 27B-MLX runs well enough for me, and the loc
Hi, After a long night of optimizations, I believe I have made the fastest inference engine for Qwen3.6-28B on a 3090. Quick metrics: - 250w power capped - Up to 195k context (ships with 150k for safe
My local inference build, with: ASUS WS C422 PRO/SE 10-core Xeon W-2255 64GB ECC RAM 64GB VRAM Pimped case with TurboLEDz indicating the frequencies of the 10 xeon cores. Running llama.cpp with SYCL b
Megathread to help with the influx of duplicate / similar posts around the release of the Qwen 3.8 27B release. Quants Fine-Tunes & Abliterations Chat Templates Inference Server Support & Configuratio
arXiv:2608.12388v1 Announce Type: cross Abstract: The emergence of orientation selectivity in the primary visual cortex (V1) remains a central question in computational neuroscience. Shirazi's Bayes-M
arXiv:2608.12869v1 Announce Type: cross Abstract: Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure
arXiv:2608.12398v1 Announce Type: cross Abstract: We propose IM-LEPP (Integrated Multimodal Latent Energy-based Predictive Processing), a hierarchical, energy-based model of multimodal cognition that
arXiv:2608.12835v1 Announce Type: new Abstract: Unmanned Aerial Vehicle Vision-Language Navigation (UAV-VLN) requires agents to follow language instructions, infer spatial structure from sparse multi-