Knowledge catalogue
arXiv:2609.26624v1 Announce Type: cross Abstract: Sparse Gaussian processes achieve O(N) inference by replacing the kernel with an appropriate expansion in a fixed basis {phi_j} on the input space. Gi
arXiv:2609.26457v1 Announce Type: cross Abstract: AI agents are beginning to automate research and development across the AI stack, from improving training efficiency to optimizing inference. A natura
arXiv:2609.24847v1 Announce Type: cross Abstract: LLM inference on edge devices is constrained by computational and memory resources, making efficient autoregressive decoding challenging. Speculative
arXiv:2511.02769v2 Announce Type: replace Abstract: Many molecular Transformers lack probabilistic latent variables for posterior inference and latent interpolation. We introduce STAR-VAE, a SELFIES-e
arXiv:2609.26487v1 Announce Type: new Abstract: Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show wh
arXiv:2603.02266v2 Announce Type: replace-cross Abstract: Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-Lan
arXiv:2601.12538v2 Announce Type: replace-cross Abstract: Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) de
arXiv:2609.24150v1 Announce Type: new Abstract: Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to generate multiple candidate tokens that are
arXiv:2609.22100v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce dis
arXiv:2609.22951v1 Announce Type: cross Abstract: Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models
arXiv:2609.23478v1 Announce Type: new Abstract: Latent action models infer a code for the transition between two frames of action-free video. Recent methods regularise this code to compose additively
arXiv:2609.24595v1 Announce Type: new Abstract: Neural Cellular Automata (NCAs) are a new type of neural network architecture which enable accurate and robust inference at extremely small model sizes.
arXiv:2310.00436v2 Announce Type: replace Abstract: Authorship identification uses patterns in writing to infer who wrote a text, but those patterns also reflect topic, genre, and register. This surve
arXiv:2609.22162v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves the factuality of large language models (LLMs) and vision-language models (VLMs) by grounding generation i
arXiv:2609.22884v1 Announce Type: new Abstract: Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling
arXiv:2506.12576v3 Announce Type: replace Abstract: Sparse autoencoders (SAEs) can enable inference-time topic steering by modifying latent feature activations, but existing steering methods often fai
arXiv:2609.24112v1 Announce Type: cross Abstract: Causal Bayesian Optimization (CBO) combines causal inference with Bayesian optimization to enable sample-efficient intervention selection in systems w
arXiv:2609.22131v1 Announce Type: new Abstract: Structured pruning is a promising approach for reducing the substantial inference costs of Large Language Models (LLMs) while maintaining hardware effic
arXiv:2609.22697v1 Announce Type: new Abstract: Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated s
arXiv:2609.24625v1 Announce Type: cross Abstract: How should natural language processing models be selected and adapted for global health literature in environments where annotated data and computatio
arXiv:2609.23668v1 Announce Type: cross Abstract: Inferring network topology from noisy node observations is a central problem in graph signal processing. In this paper, we consider Laplacian-constrai
arXiv:2609.24433v1 Announce Type: new Abstract: Low-bit vision-language-action inference must reduce observation-to-action latency while preserving robot behavior. We present FoldQuantVLA, a post-trai
arXiv:2609.24197v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates large language model inference by having a lightweight draft model predict future tokens for verification by
Following a successful private preview, we’re thrilled to open DigitalOcean Managed Agents to everyone. Teams can now deploy their preferred agent harness (like OpenCode, Codex CLI) or bring their own
arXiv:2609.23085v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectori
arXiv:2609.24547v1 Announce Type: new Abstract: Real-time embodied companion interaction requires a robot to infer user intent from streaming speech, generate timely responses, and execute expressive,
arXiv:2609.24391v1 Announce Type: new Abstract: Voice-controlled interaction in industrial settings is hampered by acoustic noise, which severely degrades audio-only speech recognition. Audio-visual s
arXiv:2609.22237v1 Announce Type: new Abstract: Merging low-rank adapters (LoRAs) promises to eliminate the overhead of swapping task-specific weights at inference time. However, existing merging meth
arXiv:2609.23587v1 Announce Type: new Abstract: Large reasoning models (LRMs) incur high inference costs, often mitigated by efficiency techniques like quantization and pruning. However, the impact of
arXiv:2410.17021v2 Announce Type: replace Abstract: Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. Ho
arXiv:2609.22098v1 Announce Type: new Abstract: Speculative decoding accelerates language-model inference by letting a cheap drafter propose tokens that the target model verifies in parallel. Recent b
arXiv:2609.21214v1 Announce Type: new Abstract: Cognitive diagnosis infers students' concept mastery from response logs. However, students' responses are not determined by mastery alone: non-cognitive
arXiv:2609.21672v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeabl
arXiv:2609.21694v1 Announce Type: cross Abstract: Context: We developed a probabilistic machine learning method with the aim of performing the O(10)-way classification of low- and high-resolution spec
Having a blast with Qwen Image 2.1 on my M2 Macbook Pro with 32GB RAM, even though it takes 16 minutes to complete the recommended number of iterations with the resolution reduced to 1024x1024. And th
I tried putting up with it the last week or two but it's become unusable. I've tried GLM 5.3 & 5.3 Flash, GLM 5.2, and Deepseek V4.1 The inference and pp speeds have become unbelievably slow, I just c
arXiv:2609.21554v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have revolutionized artificial intelligence and how human interact with AIs. Despite impressive advancem
arXiv:2609.22040v1 Announce Type: new Abstract: Current Vision-Language-Action (VLA) models for autonomous driving operate primarily through feedforward inference across the perception--reasoning--pla
arXiv:2609.20971v1 Announce Type: new Abstract: Long-context large language model inference is increasingly limited by prefill, where dense self-attention processes the entire prompt before generation
arXiv:2609.21827v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting multiple tokens in parallel, with tree-based methods further improving efficiency through hie
arXiv:2609.22060v1 Announce Type: new Abstract: Traffic sign recognition (TSR) is an important perception task for autonomous driving and advanced driver-assistance systems, where a system must both l
arXiv:2609.21450v1 Announce Type: new Abstract: Post-training weight-activation quantization reduces the memory and inference costs of large language models, but aggressive W4A4 quantization remains d
arXiv:2609.21412v1 Announce Type: new Abstract: Medical image segmenters often get worse when sites, scanner vendors, or protocols change. Continual test-time adaptation (CTTA) addresses this problem
RTX 5090 random black screen + 100% fans + hard lock; sometimes no POST until AC power is removed — gaming, ComfyUI and Ollama I am looking for help diagnosing a very intermittent but increasingly fre
TL;DR: Local agent loop, ~21 days, one RTX 3090. Task was pretty much 'build a CUDA inference engine for optimized for yourself on this GPU arch.' Got working kernels and benches, not a win over llama
Although I do not completely understand what the big deal is with Jev, it reminded me of something I implemented in mt_llm (which is build around the great llama.cpp) a while back to use a relatively
Okay, this one seems probably really odd (or maybe not), but most harnesses operate within token spaces. That is, every tool output, even batching of tool outputs, go back up into inference calls. Lea
Meet Inco Splash, open-source inference engine, built around the model and around Apple silicon. Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents. Req
arXiv:2609.20761v1 Announce Type: cross Abstract: World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world states and robot actions, enabling the p
arXiv:2609.19965v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly applied to legal and criminal justice tasks, yet existing work focuses almost exclusively on post-arrest s
arXiv:2609.20625v1 Announce Type: cross Abstract: Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitw
arXiv:2601.08464v2 Announce Type: replace-cross Abstract: Context-aware building massing is an important early-stage design task: given a site for buildings, a generated massing should not only fit th
arXiv:2609.20722v1 Announce Type: new Abstract: Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a f
Been building this for a few months, mostly for myself, and it just got a proper release so figured I'd post it. It's a native GGUF inference runtime with OpenAI/Anthropic-compatible APIs and a chat U
I had Astra run a multi-hour investigation into speeding up local MoE inference while keeping the model weights and quantization unchanged. The experiments covered Qwen3.6-35B-A3B and Qwen3.8 Flash-Ne
arXiv:2609.19782v1 Announce Type: cross Abstract: Figurative paintings are often approached as if they depict a single recoverable 3D scene: viewers infer depth and occlusion, and reconstruction pipel
arXiv:2609.19983v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data, but training and inference on large graphs are often bottl
arXiv:2609.19592v1 Announce Type: new Abstract: This study developed and evaluated a deep-learning-based perception framework for selective robotic cotton picking. The dataset contained 1,008 annotate
arXiv:2609.20150v1 Announce Type: new Abstract: Conventional satellite remote sensing transmission follows a reconstruct-then-infer paradigm that optimizes pixel-level fidelity, creating an objective
arXiv:2609.20186v1 Announce Type: new Abstract: Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff betwee