Ollama vs. LM Studio vs. ?
Hi everyone, I’ve been experimenting with local LLMs on my 48 GB RAM MacBook Pro and I’m still trying to figure out what the best setup is. Ollama feels very fast, which I really like. The problem for
Knowledge catalogue
Hi everyone, I’ve been experimenting with local LLMs on my 48 GB RAM MacBook Pro and I’m still trying to figure out what the best setup is. Ollama feels very fast, which I really like. The problem for
arXiv:2609.19358v1 Announce Type: new Abstract: Three-dimensional object detection for autonomous driving is dominated by detectors trained on large corpora of human-annotated 3D boxes. Such a detecto
arXiv:2609.20816v1 Announce Type: cross Abstract: Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and edi
arXiv:2609.19542v1 Announce Type: new Abstract: Open-vocabulary segmentation enables rich semantic perception for UAVs, but frame-wise predictions can remain temporally inconsistent across repeated ob
arXiv:2609.19337v1 Announce Type: new Abstract: We present Personalized Federated Hierarchical Gaussian Processes (pFedHGP) for probabilistic regression and classification when data are distributed ac
arXiv:2609.20623v1 Announce Type: new Abstract: Recent single-view feed-forward 3D Gaussian Splatting (3DGS) generation predicts a fixed number of Gaussians per camera ray, introducing severe spatial
arXiv:2609.20066v1 Announce Type: cross Abstract: Event cameras offer high temporal resolution and motion sensitivity for tiny UAV detection, yet distant targets generate sparse and fragmented events
arXiv:2609.19203v1 Announce Type: new Abstract: AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as p
arXiv:2609.20794v1 Announce Type: new Abstract: Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can pro
arXiv:2609.19441v1 Announce Type: cross Abstract: World action models (WAMs) rely on video-generation backbones, requiring substantial memory and compute for deployment. Post-training quantization red
arXiv:2609.20758v1 Announce Type: cross Abstract: Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in
arXiv:2609.19657v1 Announce Type: cross Abstract: Repeated prompt prefixes are increasingly common in LLM serving workloads, appearing in system prompts, templated retrieval-augmented generation pipel
arXiv:2609.19865v1 Announce Type: new Abstract: Representation learning from medical code sequences in electronic health records and medical claims data has been successful in various clinical applica
arXiv:2609.20812v1 Announce Type: cross Abstract: Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that
arXiv:2609.20283v1 Announce Type: new Abstract: Modern segmenters often fail after the expensive computation has already been done: a useful mask is present among the model's query-conditioned candida
arXiv:2609.19204v1 Announce Type: cross Abstract: Robotic systems operating in dynamic environments require visual perception that evolves continuously with the incoming sensory stream. Event cameras
arXiv:2609.20081v1 Announce Type: cross Abstract: SpeechLLMs have shown strong potential for emotion recognition, yet they read the predicted emotion off a generative decoder not suited for classifica
arXiv:2609.19156v1 Announce Type: new Abstract: Data-driven fine-tuning is widely adopted to enhance reasoning in Large Language Models (LLMs) due to its simplicity and efficiency. However, mainstream
arXiv:2609.20584v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly considered for safety-critical engineering, yet their reliability in regulated functional-safety workflows
arXiv:2609.19499v1 Announce Type: new Abstract: Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the in
arXiv:2609.20419v1 Announce Type: cross Abstract: Graph foundation models (GFMs) aim to learn transferable representations across severely heterogeneous graph domains. However, severe domain shifts in
arXiv:2609.19615v1 Announce Type: cross Abstract: Modern applications generate massive volumes of raw telemetry data, but translating those noisy, heterogeneous event streams into actionable business
arXiv:2609.19359v1 Announce Type: new Abstract: Falls in older adults are often preceded by changes in mobility, balance, and postural transitions. This paper presents a wireless smart insole platform
arXiv:2609.19815v1 Announce Type: new Abstract: We propose SnapPhysics, a training-free framework that reconstructs 3D objects and estimates their physical properties such as mass, friction, and cente
arXiv:2609.19747v1 Announce Type: new Abstract: Light field (LF) reconstruction from limited and noisy focal stack (FS) measurements is a highly ill-posed inverse problem. Although the LF-to-FS imagin
arXiv:2609.20227v1 Announce Type: new Abstract: Resource-constrained multi-object navigation in vast indoor environments (>2,000ext{ m}^2) poses significant challenges for efficiency and strategic pla
arXiv:2606.09735v2 Announce Type: replace Abstract: The ambition behind alignment training is to make large language models safe and useful. The primary mechanisms, reinforcement learning from human f
arXiv:2609.19611v1 Announce Type: cross Abstract: Tensor programs, as used in deep learning models, are a prime target for optimization, as small performance improvements can have a large impact acros
arXiv:2609.20290v1 Announce Type: new Abstract: Detecting crop disease early is central to sustainable agriculture and food security under United Nations Sustainable Development Goal 2 (Zero Hunger),
arXiv:2609.19167v1 Announce Type: new Abstract: As AI systems evolve into personalized digital companions, a central capability is reasoning over a user's long-term personal history: not merely storin
arXiv:2609.20199v1 Announce Type: new Abstract: Cognitive workload reflects the mental effort required during task performance and is central to the design of adaptive human-machine systems. The use o
arXiv:2609.19897v1 Announce Type: new Abstract: Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genre
arXiv:2609.19878v1 Announce Type: cross Abstract: Multimodal reasoning requires models to draw on information from multiple modalities throughout the reasoning process. Yet existing methods often conc
arXiv:2609.20630v1 Announce Type: new Abstract: Search advertising connects user intent with commercial content and plays a critical role in platform monetization. Recent systems typically align pretr
arXiv:2609.20612v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher
arXiv:2609.18739v1 Announce Type: cross Abstract: Poor quality or noisy annotations in Named Entity Recognition (NER), as in any other NLP task, make it challenging to achieve state-of-the-art perform
arXiv:2609.18789v1 Announce Type: new Abstract: Vision-language navigation requires aligning language with visual observations while maintaining spatial understanding over time. Geometry foundation mo
arXiv:2609.18864v1 Announce Type: cross Abstract: Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unaut
arXiv:2602.16218v2 Announce Type: replace Abstract: Bayesian quadrature is a probabilistic, model-based approach to numerical integration, the estimation of intractable integrals, or expectations. Alt
arXiv:2609.18203v1 Announce Type: new Abstract: Human values are deep motivational orientations that shape human behaviors. In e-commerce, they reveal the stable drivers behind users' purchase decisio
arXiv:2609.18273v1 Announce Type: new Abstract: Web browsing often appears ephemeral: users visit a few websites, complete a task, and move on. However, even short fragments of browsing activity can c
arXiv:2609.18673v1 Announce Type: cross Abstract: Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluation
arXiv:2609.18488v1 Announce Type: cross Abstract: Diffusion and flow-matching models are typically trained by corrupting data through independently sampled Gaussian noise. While simple and scalable, t
arXiv:2602.03994v3 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains unde
Hey all, Henry from Cactus Compute here, I kinda wanted to share our latest model and get feedback from the family :) Needle 3 is a small foundation model for automation: you give it the functions you
arXiv:2609.17820v1 Announce Type: new Abstract: Fine-grained recognition of visually similar industrial parts is challenging when classes differ primarily in physical dimensions. Normalizing detected
arXiv:2609.18038v1 Announce Type: new Abstract: The world population is growing rapidly, and technology is improving in parallel. Meeting the huge demand for food for these 7 billion people not only d
arXiv:2609.18836v1 Announce Type: new Abstract: A surveillance system that detects an anomaly often has to repair the footage as well, yet the two tasks are studied in isolation: training-free anomaly
arXiv:2609.17535v1 Announce Type: new Abstract: Language generation research increasingly spans three paradigms: autoregressive decoding, discrete masked diffusion, and continuous flow-matching. Compa
arXiv:2609.18566v1 Announce Type: cross Abstract: We present a physics-informed machine learning framework based on Neural Ordinary Differential Equations that solves the holographic inverse problem:
arXiv:2506.00214v2 Announce Type: replace-cross Abstract: Rapid urbanization demands efficient monitoring of turbulent wind and pollutant dispersion, yet existing reconstruction and sensor placement s
arXiv:2609.18510v1 Announce Type: new Abstract: We present DiT-Garment to model dynamic 3D clothing over human body models in arbitrary motion. Unlike existing methods, DiT-Garment can animate garment
arXiv:2609.18444v1 Announce Type: new Abstract: Weakly supervised class-incremental semantic segmentation (WILSS) aims to train a segmentation model over multiple steps, each introducing new concepts
arXiv:2609.18706v1 Announce Type: cross Abstract: Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust. Matching decompil
arXiv:2603.05757v2 Announce Type: replace Abstract: Video generative models (VGMs) pretrained on large-scale internet data can produce temporally coherent rollout videos that capture rich object dynam
arXiv:2509.16894v2 Announce Type: replace Abstract: Autonomous racing serves as a compelling testbed for advancing autonomous vehicle systems. The 1/10-scale F1Tenth platform is widely adopted for edu
arXiv:2609.19044v1 Announce Type: new Abstract: Sampling can increase response diversity without producing history-dependent behavior. We formalize a different design target, structured unpredictabili
arXiv:2609.17786v1 Announce Type: new Abstract: Fairness-aware model compression requires selecting methods and configurations that balance accuracy, fairness, and deployment cost. These decisions bec
arXiv:2609.18471v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety alignment often degrades when handling harmful queries. Existin
arXiv:2609.18766v1 Announce Type: cross Abstract: Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their