Knowledge catalogue
arXiv:2610.05618v1 Announce Type: cross Abstract: Finding which variables cause which others in multivariate time series, and at what lags, is central to science and policy, yet existing methods force
arXiv:2610.06147v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong zero-shot transferability but remain vulnerable to target-domain shifts at inference time. Test-time adapta
arXiv:2610.05584v1 Announce Type: new Abstract: Extra inference compute is usually spent on sampling more reasoning chains. We study where inside an existing chain an additional continuation should be
arXiv:2512.05134v2 Announce Type: replace Abstract: Diffusion transformers require repeated denoiser evaluations, making image and video generation computationally expensive. We propose a training-fre
arXiv:2606.13894v3 Announce Type: replace-cross Abstract: AdamW is a default optimizer for deep learning, but its moment states add two parameter-sized buffers to training memory, increasing the cost
Hello llamas. I am posting this because I believe that, despite it being closed source models, the discussion will bring value to the local AI community. As many of you probably heard, GPT-6 Astra is
arXiv:2607.19234v2 Announce Type: replace Abstract: Time series classification is central to domains such as medical signal analysis, industrial monitoring, and sensor-based activity recognition, wher
arXiv:2605.06350v2 Announce Type: replace Abstract: LLM cascades, in which a cheap model defers to an expensive one on low-confidence queries, are widely used to reduce inference cost. Given a pool of
arXiv:2610.04326v1 Announce Type: new Abstract: Pretrained flow models are now widely used as generative priors in science and vision, where inference-time guidance enables test-time constraints witho
arXiv:2610.05458v1 Announce Type: new Abstract: Running the same language model on different graphics processing unit (GPU) vendors can produce different logits, even when the model weights and inputs
Introducing InferBench: A benchmark testing how well frontier LLMs infer a user's priorities from their instructions. We tested 12 LLMs across 20 scenarios with 2.8k conversations to see which models
arXiv:2610.04722v1 Announce Type: new Abstract: Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, maki
arXiv:2610.06002v1 Announce Type: cross Abstract: Diffusion models provide expressive priors over trajectories, but adapting these priors to test-time constraints requires maintaining feasibility and
arXiv:2509.22458v3 Announce Type: replace Abstract: Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace the classic NewtonRaphson (NR) solvers,
arXiv:2607.09082v2 Announce Type: replace Abstract: Training-free in-context segmentation enables new object categories to be introduced at inference time from a single annotated reference image, elim
Reflection AI Inc. today introduced Beam, an open-source large language model with 501 billion parameters. The launch comes a few months after the startup raised funding at a 25 billion valuation. Aro
arXiv:2610.06383v1 Announce Type: new Abstract: Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space
arXiv:2610.03984v1 Announce Type: cross Abstract: Autonomous coding agents solve repository issues by reading code, running commands, editing files, and submitting patches. Extra inference-time comput
arXiv:2610.05719v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models serve as unified policies for robotic manipulation, yet their expensive inference forces robots to pause between pol
arXiv:2610.03223v1 Announce Type: cross Abstract: Long-horizon LLM agents are typically trained with sparse outcome rewards, making trajectory-level objectives too coarse to distinguish the contributi
arXiv:2610.02369v1 Announce Type: cross Abstract: Human-computer interaction (HCI) is in the middle of a transition: large language models can now generate functional user interfaces (UIs) on demand f
arXiv:2610.03615v1 Announce Type: new Abstract: Recent advances in frontier models enable robot manipulation from only a few demonstrations, but high inference latency limits their use for real-time r
arXiv:2610.02462v1 Announce Type: cross Abstract: LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable
arXiv:2610.03390v1 Announce Type: cross Abstract: Few-step neural text-to-speech models often rely on short- ened diffusion or flow-matching schedules, or on distillation from pretrained multi-step te
arXiv:2610.02538v1 Announce Type: cross Abstract: Inference-time control steers a pretrained generative model towards a target distribution without retraining. We study tilted targets pi_0propto G_0,p
arXiv:2610.03474v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative training of medical image segmentation models without sharing raw patient data, yet existing approaches as
arXiv:2610.02377v1 Announce Type: cross Abstract: Sampling from the posterior is the central task of computational Bayesian inverse problems. The standard workhorse in Bayesian inference - Markov chai
arXiv:2610.03123v1 Announce Type: cross Abstract: Existing streaming vision-language models (VLMs) continuously perceive and reason over visual streams, but their computational pathways remain fixed t
arXiv:2610.02241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures allow frontier language models to scale to trillions of parameters, but their deployment is constrained by mass
arXiv:2610.03039v1 Announce Type: new Abstract: Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high infere
Following on from club-5060ti and club-rdna16, I’ve put together Infermeld: a small, open-source Linux companion kit for running one GGUF across an AMD GPU and an NVIDIA GPU, powered by llama.cpp. I’m
arXiv:2610.03101v1 Announce Type: cross Abstract: Clustering variables in causal graphs reduces the size of the graph and simplifies causal inference. However, arbitrary clustering can alter crucial c
arXiv:2610.03198v1 Announce Type: new Abstract: The memory footprint of the key-value (KV) cache constrains the practical use of long-context models, and it dominates cost when one prefilled context m
arXiv:2610.02559v1 Announce Type: new Abstract: As neural networks continue to grow in scale, model compression is becoming increasingly important for efficient inference under limited computational r
arXiv:2610.03259v1 Announce Type: new Abstract: We release PaMIR (Public Arrival-ordered Measurement for Inference in Risk), an open benchmark for credit-default prediction when labels are scarce and
arXiv:2602.10273v3 Announce Type: replace-cross Abstract: Reasoning ability in large language models is often attributed to distribution sharpening: concentrating output probability on high-likelihood
arXiv:2610.02968v1 Announce Type: new Abstract: Large language models (LLMs) can infer user preferences from interaction histories and reviews, yet the rationales they generate may not reflect the inf
arXiv:2610.02270v1 Announce Type: cross Abstract: Medical vision-language model (VLM) evaluation is sensitive to workflow design, prompting strategy, and benchmark construction, yet most studies treat
arXiv:2610.03027v1 Announce Type: cross Abstract: The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwidt
arXiv:2610.03052v1 Announce Type: new Abstract: Large language models (LLMs) contain broad knowledge, but they cannot access all of it reliably. We study this problem through knowledge accessibility,
arXiv:2610.03218v1 Announce Type: new Abstract: Microscaling (MX) formats are emerging as a hardware-supported approach to efficient training and inference. They combine low-precision elements with sh
arXiv:2512.04888v4 Announce Type: replace Abstract: Object detection constitutes the primary task within the domain of computer vision. It is utilized in numerous domains. Nonetheless, object detectio
In our #NeurIPS2026 paper “A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems (DS)” (preprint: https://arxiv.org/abs/2607.14937) we reduce a DS foundation model to
ggml-openvino: update to 2026.4.1, optimize performance, expand ops, improve device listing. (#29852) ggml-openvino : Qwen3.5 MoE perf (#312) Squash of ravi9#312: ggml-openvino: add detailed inference
arXiv:2610.00728v1 Announce Type: cross Abstract: Weather reanalysis products rely on computationally intensive numerical weather predictions followed by data assimilation that corrects the forecast t
arXiv:2610.00321v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting future tokens cheaply and verifying them with the target model in parallel
arXiv:2610.00296v1 Announce Type: cross Abstract: Token-level certainty is widely used as a proxy for correctness in LLM training and inference. However, the performance of certainty-based methods dep
arXiv:2610.00232v1 Announce Type: new Abstract: Fixed-size recurrent memory limits storage growth during inference, but successful recall depends on the task and training. We study a small DeltaNet va
Decision models in llama.cpp are now available The `/v1/systemone` endpoint is available in the latest llama builds. Use it to do Jev-style inference locally, efficiently and privately. Multiple open
arXiv:2610.01435v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong predictive performance through in-context learning, yet repeatedly conditioning on labeled data makes in
arXiv:2602.03006v3 Announce Type: replace Abstract: Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active d
arXiv:2601.22153v2 Announce Type: replace-cross Abstract: Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models. Although recent VLAs generalize well in static
arXiv:2610.00412v1 Announce Type: new Abstract: KV cache pruning reduces long-context inference memory usage by evicting less important key-value pairs. KVzip estimates importance through context reco
arXiv:2603.04349v2 Announce Type: replace Abstract: Understanding long videos is crucial for embodied intelligent agents, as their performance depends on effectively accumulating and using long-horizo
arXiv:2610.00498v1 Announce Type: cross Abstract: When minimizing the squared-error loss, the popular CP decomposition can be interpreted as parameter inference in a Gaussian model with a low-rank mea
arXiv:2610.01230v1 Announce Type: new Abstract: Efficient long-context inference is essential for large language models (LLMs), yet it poses a severe computational bottleneck. Hash-based retrieval off
arXiv:2610.01110v1 Announce Type: new Abstract: How much can test-time computation improve a language model, and at what cost? Test-time scaling is widely proposed as a substitute for larger models, b
💯💯💯: “If AI is going to produce trustworthy and genuinely novel insights in science, medicine and beyond, we need systems whose conclusions arise from an auditable process of evidence, inference and b
Cloudflare AI Gateway now supports native web search API integration in partnership with Ceramic.ai, Exa, and Linkup. Developers can now inject real-time web context into model inference calls via AI
arXiv:2610.00426v1 Announce Type: new Abstract: We introduce IrekoGPT, a post-hoc method for converting pretrained LLMs into slimmable models whose width can be adjusted at inference time. Building on