Knowledge catalogue
arXiv:2610.12148v1 Announce Type: new Abstract: Quantum machine learning, and quantum neural networks (QNNs) in particular, are advancing fields with growing potential. Although systematic comparisons
(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next
arXiv:2610.11945v1 Announce Type: cross Abstract: Collecting tactile demonstrations on robots is costly and slow, motivating the use of lower-cost human tactile gloves for scalable data collection. Ho
arXiv:2610.09026v1 Announce Type: cross Abstract: We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavior
arXiv:2610.08870v1 Announce Type: new Abstract: Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly
arXiv:2606.15568v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models perform well in generalist robot manipulation but remain brittle to out-of-distribution perturbations, while ful
arXiv:2610.07522v1 Announce Type: new Abstract: Post-training quantization is a powerful tool for compressing large language models. The most scalable methods quantize every layer in parallel, but qua
arXiv:2610.06903v1 Announce Type: cross Abstract: Activation steering manipulates large language model behavior by intervening on internal activations, but the mechanistic basis of these interventions
Running a model on your own machine used to be a privacy story with a quality tax. On this generation that trade has narrowed to where we can state it plainly: for daily work, the local model is good
arXiv:2610.07661v1 Announce Type: new Abstract: Massive activations, a phenomenon in which a small number of hidden channels exhibit exceptionally large magnitudes, are pervasive in large language mod
arXiv:2610.08131v1 Announce Type: cross Abstract: Achieving compositional concept generalization (CoCoGen), the ability to understand novel situations by recombining learned primitives, remains a fund
arXiv:2610.07217v1 Announce Type: cross Abstract: Despite its promise for scaling robot learning, egocentric manipulation data is still scarce today. Collection at scale requires vertically integratin
I constantly see recommendations saying that ik_llama.cpp (ikawrakow's fork) is the undisputed king of hybrid CPU/GPU offloading and MoE performance. However, every time I benchmark it against mainlin
Row-Bot 5.0 with qwen3.8:27b in Ollama, on my own GPU. No API keys, no cloud. Gave it a year of bills, a tenancy agreement, an insurance policy and a rent increase letter (all made up). It spotted a l
arXiv:2610.05744v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has been widely adopted in recent large language model (LLM) architectures. However, scaling up MoE in LLM training introduces
arXiv:2610.04137v1 Announce Type: new Abstract: Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Be
Ideally I'd like to be able to run Qwen 3.8-Flash-Next with decent performance. I was thinking of just buying 2x Radeon AI R9700 (64GB VRAM), or maybe a DGX Spark but that was before the price hike. M
arXiv:2610.04784v1 Announce Type: cross Abstract: Traffic classification (TC) is crucial to secure Internet of Things (IoT) networks, whose edge nodes often operate under privacy, bandwidth, and energ
arXiv:2610.06387v1 Announce Type: new Abstract: Large language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. Ho
arXiv:2610.05329v1 Announce Type: new Abstract: Large language models (LLMs) are typically pretrained in high precision but increasingly deployed with low-precision post-training quantization (PTQ). R
arXiv:2610.04433v1 Announce Type: cross Abstract: A coding agent is a language model wrapped in a harness: the system prompt, the tool set, and the context management that turn a chat model into somet
arXiv:2610.02728v1 Announce Type: new Abstract: Closed-loop learned locomotion is established on commercial quadrupeds but remains uncommon at the sub-kilogram scale. Continuous-rotation legs give MiN
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
Finally finished my fork: https://github.com/IceFog72/ik_llama.cpp Nothing else I wanted to add/try currently works In short, it now has: Bandwidth-adaptive CPU/GPU execution Shared expert-residency i
arXiv:2610.02511v1 Announce Type: new Abstract: Advancements in high-resolution numerical weather prediction (NWP) and data assimilation (DA) have shaped the developments in deep learning (DL) archite
Hey all. We've spent the last weeks getting Qwen3.8-Flash-Next (125B MoE, 6B active) to run properly on one AMD Strix Halo box (Ryzen AI Max+ 395, 128 GB). Tonight we're releasing both the 95 GB EXL3
arXiv:2610.02304v1 Announce Type: cross Abstract: Existing Simulink benchmarks mainly evaluate whether generated models compile, execute, or resemble a reference model. These criteria do not establish
I keep testing harness & model setups on real tasks: basic math, vision, computer use (reading emails, navigating stores) and coding. I created a benchmark and a leaderboard. You can see it here: http
Help with this list. Give me your recommendation on 'not supported anymore' GPUs. Looking for budget and Vulkan friendly options. Most of the GPU are not supported by latest CUDA / ROCm. Often with so
Auto-generated synthesis of 2154 entries about r-stablediffusion
I wanted to see how far I could push a fairly ordinary laptop with a huge MoE model. Turns out, Qwen3.8 Flash Next 176B can run on: RTX 3080 Laptop — 16GB VRAM 32GB system RAM SSD No 128GB/256GB RAM w
There seems to be a whole category of extremely narrow inference runtimes appearing: Strata, ninfer, DwarfStar, Splash, llamAmpere, gufo, etc. They deliberately give up the thing llama.cpp/vLLM are gr
arXiv:2610.00053v1 Announce Type: new Abstract: Four-bit floating-point (FP4) Tensor Cores accelerate matrix multiplication, but scale computation, operand packing, layout construction, and saved back
arXiv:2610.00007v1 Announce Type: cross Abstract: Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept local). The practitioner's question is not the leaderb
arXiv:2610.00649v1 Announce Type: cross Abstract: Synthetic speech detection is critical for audio security, but performance can degrade when labeled data are scarce and evaluation conditions differ f
arXiv:2610.00067v1 Announce Type: new Abstract: Reliable visual inspection is essential for quality assurance in aero-engine blade manufacturing, where defect appearance may vary across production lin
arXiv:2609.39090v1 Announce Type: cross Abstract: Data-driven machine learning (ML) techniques have become an essential tool in many domains of science. Their application to atomistic simulations of m
An AI agent uses compute differently than a traditional application. Over a single session, it writes and runs code, calls a model, and waits on a tool or a person before picking the work back up. As
arXiv:2609.39755v1 Announce Type: new Abstract: Safe and efficient quadruped navigation over unfamiliar terrain requires predicting terrain-robot interaction before contact: geometry and visual appear
So everyone has been yelling about how I should be using Gufo instead of halogen because it's open source and it's 'just as good or better'. Checking in on their GitHub (GitHub.com/gufo-org/gufo) got
arXiv:2609.39350v1 Announce Type: cross Abstract: As model sizes continue to scale, distributed training has become inevitable. Automatic parallelization techniques can derive efficient training paral
arXiv:2609.38202v1 Announce Type: new Abstract: Soft continuum robots can exploit distributed compliance for whole-body manipulation, but synthesizing behavior through changing contacts remains diffic
arXiv:2310.11379v2 Announce Type: replace-cross Abstract: Voice-based interfaces rely on a wake-up word mechanism to initiate communication with devices. However, achieving a robust, energy-efficient,
arXiv:2607.10891v2 Announce Type: replace Abstract: Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interf
40 year tech gap? No problem! The Tandy runs DeskMind, a native DOS program. It talks over WiFi (a PicoMEM 2 card with mTCP) to a small Python server on my PC. That server drives Qwen3.8-27B (NInfer o
arXiv:2609.36993v1 Announce Type: new Abstract: Complex tasks for underwater robots remain limited by the capabilities of their controllers. Learning a better one for a soft, underactuated robotic fis
arXiv:2609.37887v1 Announce Type: new Abstract: Activation and key-value cache precision change what a quantized language model computes without altering its stored weights. Direct weight-code bounds,
arXiv:2505.12683v2 Announce Type: replace Abstract: Key feature fields need bigger embedding dimensionality, others need smaller. This demands automated dimension allocation. Existing approaches, such
arXiv:2609.37072v1 Announce Type: new Abstract: Aerial seed broadcasting can reach remote restoration sites, but provides limited control over seed placement within the soil. This paper presents a geo
arXiv:2601.11433v2 Announce Type: replace Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) are demonstrated to be suitable for the automatic classification of
arXiv:2609.36584v1 Announce Type: new Abstract: Analog in-memory computing (AIMC) offers an alternative for model training by executing matrix operations directly where weights are stored. However, sc
arXiv:2609.37070v1 Announce Type: cross Abstract: Rare but consequential failures can persist in learned locomotion policies for legged robots even when average task performance is high, in part becau
arXiv:2609.35783v1 Announce Type: cross Abstract: Large-scale recommender systems, particularly short-form video platforms, are often bottlenecked by massive popularity feedback loops. In such environ
While AI has made plenty of inroads on people's phones and computers, it's largely failed in dedicated devices. But over the next year, two major AI companies, Meta and OpenAI, will attempt to change
arXiv:2609.31168v1 Announce Type: new Abstract: My doctoral work aims to explore Audio Emotion Recognition (AER) in the context of atypical listening. This research focuses on auditory hypersensitivit
arXiv:2609.30884v1 Announce Type: new Abstract: Large language models rely on KV caching to reduce repeated prefill computation in long context and interactive applications. As lightweight adapters ev
arXiv:2609.31211v1 Announce Type: new Abstract: Underwater robotic inspection depends on acquiring views that reveal task-relevant structure. For a structurally complex coral colony, recognising the t
arXiv:2609.30270v1 Announce Type: new Abstract: On-device inference with small language models keeps user data local, works offline, and incurs no per-query cost, so the on-device tier is preferred wh
arXiv:2603.05069v3 Announce Type: replace Abstract: Personal AI agents face a deployment paradox on mobile: persistent background execution drains the battery and conflicts with platform background li
I've been experimenting with ways to run MoE models that don't fit comfortably in RAM, and I ended up making Overspill, a disk tier for FreeToken. The basic idea came from looking at how Colibri handl