Knowledge catalogue
We’re excited and proud to share that Gartner has recognized Google as a Leader for the fourth year in a row in the 2026 Gartner® Magic Quadrant™ for Container Management, based on its Completeness of
arXiv:2609.27678v1 Announce Type: new Abstract: Contract inference requires multiple judgments about a shared document, but aggregate accuracy can conceal changes in the individual decisions. Repeated
Today, @FactoryAI joins the Specialized Intelligence Index with Legacy-Bench! The SII keeps growing, now with benchmarks testing how models handle the legacy software behind payroll, financial settlem
arXiv:2609.25369v1 Announce Type: new Abstract: Shared control often allocates robot authority based on confidence in inferred human intent, assuming reliable autonomous execution. When this assumptio
arXiv:2609.24927v1 Announce Type: new Abstract: Personal AI agents make recommendations and take actions on people's behalf in high-stakes economic contexts, e.g., buying a flight, choosing health ins
arXiv:2609.26796v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive LLMs by enabling non-autoregressive text gene
arXiv:2609.22410v1 Announce Type: new Abstract: Inferring 3D cellular properties from 2D microscopy is difficult when a reference instrument reports only population statistics rather than labels for i
arXiv:2609.25388v1 Announce Type: cross Abstract: A classical question in statistics is which observable quantities to condition on when drawing inferences about unobservable targets. For conformal pr
arXiv:2609.26100v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference through collaboration between a lightweight draft model and a target verifier. Existing
arXiv:2603.11984v2 Announce Type: replace Abstract: Diffusion-based visuomotor policies model complex action distributions through iterative denoising, but repeated inference adds latency to robotic c
arXiv:2609.24417v1 Announce Type: new Abstract: Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are
arXiv:2609.22913v1 Announce Type: new Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live sy
arXiv:2609.23212v1 Announce Type: cross Abstract: The Deck-of-cards-based Ordinal Regression (DOR) infers a value function from a ranking of reference alternatives in which the Decision Maker (DM) ins
arXiv:2609.22730v1 Announce Type: new Abstract: Robot manipulation tasks often involve hidden state information that cannot be directly observed and must be inferred through sequential physical intera
arXiv:2609.24066v1 Announce Type: new Abstract: Best-of-N is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and hig
arXiv:2609.23761v1 Announce Type: new Abstract: Internal voids are ubiquitous defects in manufactured structures, yet their characterization remains challenging because their geometry is hidden and ca
arXiv:2609.22335v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as foundational models for next-generation robotics. High VLA inference throughput is critical for me
arXiv:2609.23193v1 Announce Type: cross Abstract: As Large Language Model (LLM) APIs become increasingly integrated into privacy-sensitive workflows, ensuring inference-time privacy without compromisi
arXiv:2609.23286v1 Announce Type: new Abstract: 3D reconstruction from a lengthy video stream input poses a dilemma for feed-forward reconstruction models (FFRMs), that a whole-stream inference contex
arXiv:2609.22213v1 Announce Type: new Abstract: Temporal Knowledge Graph Question Answering (TKGQA) requires answer inference from evidence that is both structurally valid and temporally admissible. E
arXiv:2609.22158v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length,
arXiv:2609.23369v1 Announce Type: new Abstract: Generation-free world action models (WAMs) retain future-video prediction during training but act from internal video features at inference, leaving unc
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction ofte
arXiv:2601.21583v2 Announce Type: replace Abstract: Many learning problems require predicting sets of objects when the number of objects is not known beforehand. Examples include object detection, mol
arXiv:2609.21899v1 Announce Type: new Abstract: Best-of-n (BoN) sampling is a simple yet effective inference-time alignment method, but hard maximization provides only coarse control over the trade-of
arXiv:2609.21474v1 Announce Type: new Abstract: Fast-WAM shows that video-action co-training improves control without generating future video at inference, making the representation from a single vide
arXiv:2609.20970v1 Announce Type: new Abstract: Many physical properties relevant to robotic manipulation are hidden from vision. A sealed object, for example, may reveal little about its center of ma
arXiv:2609.21849v1 Announce Type: cross Abstract: On-device inference is booming, but the momentum is almost all in language models. Diffusion pipelines are memory hungry, latency-sensitive, and requi
Automated lint: 14 errors, 54840 warnings, 3 info
TL;DR: I run a mismatched Tesla V100-PCIE pair—one 16 GB card and one 32 GB card, 48 GB total—in a Proxmox/LXC-based local-inference lab. The practical winner so far is a recent CUDA build of llama.cp
Note: This writeup was put together with the help of AI. So I've got dual AMD MI50 32GB cards. If you know these cards, you know the story - AMD dropped official ROCm support for gfx906 after ROCm 5.7
arXiv:2609.20298v1 Announce Type: new Abstract: We present a learning algorithm for inferring threshold Boolean networks (TBNs) with a prescribed set of fixed points. The proposed method employs a cus
arXiv:2609.20104v1 Announce Type: new Abstract: We describe the architecture, training methodology and inference speedups of Granite 5.0 Turbo CTC, a 470 million parameter encoder-only model with an e
arXiv:2609.20734v1 Announce Type: new Abstract: Reasoning and agentic workloads increasingly demand efficient long-context inference. Yet full-attention decoding reads the growing history at every ste
arXiv:2609.19866v1 Announce Type: new Abstract: High annotation reproducibility does not necessarily imply that an LLM-inferred measure captures the construct it is intended to measure. We test this d
arXiv:2609.19610v1 Announce Type: new Abstract: Understanding humans over long horizons requires agents to infer not only what people need in the moment, but also how routines form, why they repeat, a
super pumped for this convo w/ @huntlovell and @allietheicon on all things langchain 🤝 jev Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, reports up to 200x faster infere
arXiv:2609.18849v1 Announce Type: cross Abstract: An agentic request spends substantial wall-clock time waiting for tools, and its KV cache holds GPU memory the whole time. Serving systems decide whet
arXiv:2609.18417v1 Announce Type: new Abstract: Multi-turn agent trajectories often contain redundant rounds (failed tool calls, parallel sub-queries, verification-only steps) that inflate both traini
arXiv:2608.27875v3 Announce Type: replace Abstract: Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the atten
arXiv:2609.18842v1 Announce Type: new Abstract: The scaling laws hold that a language model grows more capable with more parameters and more training data, and Mixture-of-Experts (MoE) architectures h
arXiv:2609.17890v1 Announce Type: new Abstract: Large reasoning models (LRMs) generate long chain-of-thought traces before answering, creating significant inference overhead. Pruning can reduce this c
arXiv:2609.18336v1 Announce Type: new Abstract: Muscle activity is fundamental to human movement, and understanding its patterns is critical for injury prevention and rehabilitation. Conventional musc
arXiv:2609.17895v1 Announce Type: new Abstract: We introduce TabPFN-3.5, our new flagship Tabular Foundation Model. It significantly outperforms its predecessor, TabPFN-3, and all existing baselines a
arXiv:2609.18227v1 Announce Type: new Abstract: Wildfire smoke detection from satellite imagery is critical for early warning and rapid response. For onboard satellite deployment, detection systems mu
arXiv:2609.16874v1 Announce Type: new Abstract: Beyond model inference, the decoding stage, which converts raw network outputs into task-level representations, constitutes a significant portion of the
arXiv:2609.16667v1 Announce Type: new Abstract: When a language model plays a character, the observed behavior reflects both the assigned persona and the default dispositions of the actor model itself
arXiv:2609.16501v1 Announce Type: cross Abstract: De-identified resume screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leak
arXiv:2609.16931v1 Announce Type: cross Abstract: We propose Low-Rank Quantile Surfaces (LRQS), a bivariate causal model in which, in the causal direction, an unknown monotone transformation of the co
arXiv:2609.16450v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a promising parallel decoding paradigm as an alternative to autoregressive generation through iterative
arXiv:2609.17241v1 Announce Type: new Abstract: While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates a
I've been working on something that started as the training backend for my Hierarchos architecture, but it has grown into a much broader project: https://github.com/necat101/Hierarchos-Native Hierarch
OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv
arXiv:2609.14570v1 Announce Type: cross Abstract: Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We stu
arXiv:2501.18060v2 Announce Type: replace-cross Abstract: Conformal inference provides a rigorous statistical framework for uncertainty quantification in machine learning, enabling well-calibrated pre
arXiv:2609.14237v1 Announce Type: cross Abstract: LLM serving systems increasingly disaggregate inference into finer-grained stages, with recent approaches separating attention from FFN or MoE executi
arXiv:2609.15189v1 Announce Type: new Abstract: Latent action models (LAMs) learn action representations from unlabeled videos by inferring latent actions from visual transitions and reconstructing fu
arXiv:2609.15028v1 Announce Type: new Abstract: In-context learning (ICL) enables models to infer tasks from demonstrations, but existing benchmarks generally lack matched text and image versions need
arXiv:2609.15106v1 Announce Type: new Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a latent
arXiv:2609.11939v1 Announce Type: cross Abstract: Traditional TinyML systems for edge devices achieve high accuracy by relying on fixed-depth models that require a constant number of multiply-accumula