Knowledge catalogue
Flo Health leveraged Databricks AI Runtime to create open‑source language models that prioritize both safety and practical utility. By integrating Databricks’ scalable training infrastructure with rob
arXiv:2610.12970v1 Announce Type: cross Abstract: The increasing demand for GPU-accelerated machine learning inference has exposed limitations in centralized GPU infrastructures, including high cost,
gguf's: https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf 'MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 35B-A3B variant, with 35B-A3B being the first MoE model in
arXiv:2610.11362v1 Announce Type: cross Abstract: Binary diffusion models typically require a large number of function evaluations (NFEs) to generate high-quality samples, making practical inference c
arXiv:2610.11765v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly ship with explicit 'thinking modes', yet their counterpart, 'no-thinking', has received far less attention. We
arXiv:2610.10368v1 Announce Type: cross Abstract: Adaptive computation aims to improve language-model inference by tailoring execution to each input. For layer programs, oracle evaluations use known a
arXiv:2610.07816v1 Announce Type: new Abstract: Small language models (SLMs) are attractive as local agent controllers because they reduce remote inference, latency, and deployment footprint, yet stru
'It's well worth spending the money on tokens if the business is getting the benefit.' — IBM Cloud GM Alan Peacock We're scaling open-source inference with @IBM + @nvidia on a dedicated B300 cluster o
arXiv:2610.08463v1 Announce Type: new Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an en
Disclosure: This unit was provided free of charge by Orange Pi for testing. No editorial review, no preconditions, no script. All data, bottlenecks, and thermal behavior are reported directly from har
arXiv:2610.04093v1 Announce Type: new Abstract: Deep neural networks continue to grow in parameter count, driving up training and inference cost on GPUs. Sparse neural networks and Dynamic Sparse Trai
arXiv:2610.03817v1 Announce Type: cross Abstract: Purpose: To evaluate the performance-feasibility tradeoffs of foundation models (FMs) and task-specific convolutional neural networks (CNNs) trained f
arXiv:2610.06751v1 Announce Type: new Abstract: Matrix completion underlies problems from tabular imputation to causal inference, yet existing tabular foundation models treat it as entry-by-entry pred
arXiv:2610.04537v1 Announce Type: new Abstract: On-device assistants run GPU-based LLM inference alongside CPU retrieval on unified-memory systems. Under a saturated local-retrieval workload, four con
arXiv:2610.04912v1 Announce Type: cross Abstract: Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the comp
arXiv:2505.18757v3 Announce Type: replace Abstract: Visual token pruning, which aims to compress and prune redundant visual tokens, plays a critical role in efficient inference with large vision-langu
arXiv:2610.02831v1 Announce Type: new Abstract: Vision-language models (VLMs) are powerful listwise rerankers for multimodal retrieval, but high inference costs restrict them to evaluating small local
arXiv:2610.02882v1 Announce Type: cross Abstract: Large-scale foundation models achieve strong performance across diverse tasks, but their size makes inference costly, largely due to dense matrix mult
arXiv:2610.02626v1 Announce Type: new Abstract: Vision-language-action (VLA) models increasingly incorporate intermediate reasoning to improve robotic manipulation, yet existing approaches primarily r
arXiv:2610.01034v1 Announce Type: cross Abstract: Bayesian inference increasingly uses informative but implicit priors represented only by samples, such as historical ensembles, simulator outputs, and
arXiv:2610.01785v1 Announce Type: cross Abstract: Processing long videos with Vision-Language Models (VLMs) is bottlenecked by the quadratic cost of visual tokens, making long-form inference prohibiti
arXiv:2609.39329v1 Announce Type: new Abstract: Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compressio
arXiv:2609.37791v1 Announce Type: new Abstract: Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal
arXiv:2609.32350v1 Announce Type: new Abstract: Predictive coding (PC) is a local, energy-based alternative to backpropagation (BP) whose iterative inference dynamics make it attractive for implementa
arXiv:2609.32956v1 Announce Type: new Abstract: Prior information for real-world physical quantities is most elegantly expressed via partial differential equations (PDEs). In this paper, we propose a
arXiv:2609.33965v1 Announce Type: cross Abstract: We describe a methodology for estimating the per-token energy cost of cloud-hosted large language model (LLM) inference, separating between input (pre
arXiv:2609.30566v1 Announce Type: new Abstract: We present a new inference-time sampler for diffusion models that gives a pretrained model a capability it was never trained for: constructing the atlas
arXiv:2609.30747v1 Announce Type: cross Abstract: As artificial intelligence (AI) becomes embedded in everyday life, its environmental footprint, particularly water consumption remains largely invisib
arXiv:2609.31360v1 Announce Type: new Abstract: Inference in LLMs is conventionally a fixed-depth, fixed-order forward pass through every layer, regardless of how difficult the input is. The human bra
The availability of resources for AI workloads can be challenging across the industry, especially accelerators. This can slow your AI workload deployment if it’s built around a specific type of accele
arXiv:2609.25085v1 Announce Type: cross Abstract: Data assimilation aims to infer the state of complex dynamical systems based on observational data. However, accurate inference of the multimodal post
arXiv:2609.22471v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are increasingly deployed alongside Speculative Decoding (SD) to accelerate inference, but combining the two is challe
arXiv:2602.13718v2 Announce Type: replace Abstract: Generative policies for robotic manipulation must balance action accuracy with inference latency. We present HybridFlow, a three-stage policy infere
arXiv:2609.23404v1 Announce Type: new Abstract: Point cloud completion aims to infer a complete 3D shape from a partial point cloud and serves as a fundamental building block for downstream tasks such
When running modern AI workloads, there’s often a conflict between performance and cost. Workloads like large language models (LLMs) load massive files, and may serve thousands of AI agents that need
arXiv:2609.20709v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot policy learning by incorporating future dynamics, yet explicitly generating future videos at inference introduc
arXiv:2609.19729v1 Announce Type: new Abstract: Autoregressive (AR) video generation degrades over long horizons due to an overlooked train-inference discrepancy we term KV eviction mismatch: models t
arXiv:2609.17064v1 Announce Type: new Abstract: Assistive autonomous systems must anticipate human goals before an observed behavior is complete. This article formulates anticipation as goal inference
arXiv:2609.13846v1 Announce Type: cross Abstract: Delayed Tensor Parallelism (DTP) removes the blocking all-reduce of tensor-parallel Transformer inference. Every device adds its own partial output to
arXiv:2609.14717v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept sever
arXiv:2609.15504v1 Announce Type: cross Abstract: Orthrus is a hybrid autoregressive-diffusion architecture that accelerates autoregressive language-model inference by generating multiple tokens in pa
arXiv:2609.11961v1 Announce Type: new Abstract: Stress is a pervasive determinant of mental health and a key target for mobile health interventions. On-device language models (ODLMs) offer privacy-pre
arXiv:2607.09835v2 Announce Type: replace Abstract: The recently introduced YOLO26 architecture incorporates NMS-free end-to-end inference and is optimized for deployment on resource-constrained CPU-b
arXiv:2609.10346v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existing
arXiv:2609.09254v1 Announce Type: new Abstract: Field-programmable gate arrays (FPGAs) enable efficient neural-network inference, but most deployment flows either accelerate multiply-accumulate operat
arXiv:2609.07483v1 Announce Type: new Abstract: Modus Tollens (MT) is a classical logical inference rule, while counterfactuals are hypothetical statements that are contrary to facts, and counterfactu
arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods handle one concept at a
Confirmed by my weekly Hermes analytics. Estimated at roughly 50% cut in weekly and session limits. Which cloud inference plans are you all migrating to? (I understand that local inference is preferre
arXiv:2609.04775v1 Announce Type: new Abstract: Industrial anomaly detection faces two engineering bottlenecks: memory bank construction latency and inference efficiency. Traditional sampling algorith
arXiv:2609.02958v1 Announce Type: cross Abstract: Sensor-intensive environments enable many intelligent services by inferring user applications from heterogeneous data streams. However, not all applic
arXiv:2609.03235v1 Announce Type: new Abstract: Large language models (LLMs) face severe memory bottlenecks in long-context inference due to the linearly growing size of key-value (KV) caches. Existin
arXiv:2609.03602v1 Announce Type: new Abstract: World models (WMs) have demonstrated strong potential for end-to-end autonomous driving by learning predictive representations of future scene dynamics.
arXiv:2609.01798v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed on mobile devices, making energy efficiency a key deployment constraint, yet the energy impact of
arXiv:2609.02006v1 Announce Type: cross Abstract: A compressed student has two shapes that need not agree: the weight it deploys at inference and the weight family its training can reach. We show that
arXiv:2609.00374v1 Announce Type: cross Abstract: Test-time adaptation (TTA) typically assumes that model parameters can be updated at inference time. This assumption is restrictive for inference-only
Open source is becoming the default way enterprises build with AI. Not just which model runs, but where it runs. Today we're partnering with @Equinix and @nvidia on Equinix Inference Exchange: our ope
arXiv:2609.00071v1 Announce Type: new Abstract: Prediction error is widely used to evaluate nuisance-function estimators in causal inference, but its relationship with causal estimator performance may
arXiv:2512.23765v2 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens and a stronger
arXiv:2608.29768v1 Announce Type: new Abstract: Deploying robot policies in the physical world requires satisfying two fundamental desiderata: reliability and smooth real-time execution. However, depl
arXiv:2608.30310v1 Announce Type: cross Abstract: Hybrid large language models interleave full-attention layers with linear-attention layers to reduce the cost of long-context inference. This structur