Knowledge catalogue
arXiv:2608.11765v1 Announce Type: new Abstract: Weakly supervised semantic segmentation enables histopathology tissue segmentation from image-level annotations, avoiding costly pixel-level labeling by
arXiv:2507.15958v5 Announce Type: replace-cross Abstract: On-device skin lesion analysis is constrained by the compute and energy cost of conventional CNN inference and by the need for lightweight cal
This release brings smaller prompts, longer-running conversations, safer remote access, and more reliable model streaming. External tools and skills are now discovered only when relevant. Long chats g
arXiv:2608.11322v1 Announce Type: cross Abstract: Human-AI research often evaluates individual capabilities, combined performance, or final outputs, but these approaches do not preserve how one party'
arXiv:2608.11243v1 Announce Type: new Abstract: We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.g., the agent does
arXiv:2608.11638v1 Announce Type: cross Abstract: Spatially continuous quantification of forest above-ground biomass (AGB) is what makes carbon accounting credible and mitigation strategies actionable
arXiv:2608.11288v1 Announce Type: cross Abstract: Assessing catheter and tube placement on chest X-rays is safety-critical yet tedious and error-prone. Current deep learning methods either classify pl
arXiv:2608.12155v1 Announce Type: new Abstract: Vision foundation models have recently emerged as powerful feature extractors for detecting AI-generated images, achieving strong generalization across
arXiv:2608.11585v1 Announce Type: cross Abstract: Physical computing systems exploit device dynamics for computation, but their gradient-based optimization is challenging: backpropagation through a di
arXiv:2603.08131v2 Announce Type: replace-cross Abstract: 3D Visual Grounding (3DVG) localizes objects from natural-language descriptions in 3D scenes and is fundamental to embodied AI applications. A
Using @AIatMeta's Muse Glimmer all locally to process personal monthly credit card statements. Your data belongs to you! Try different agent tasks using your favorite apps / harnesses with Ollama. Med
In OCP APAC 2026, Tai AMD SVP of compute and enterprise AI said agents don't cut GPU demand but they just pile on a whole extra layer of orchestration, retrieval, and tool-calling work that runs on CP
arXiv:2608.10239v1 Announce Type: new Abstract: Generative AI makes social-engineering attacks more fluent, adaptive, and scalable, increasing the need for LLM-based de- fenders that can protect users
arXiv:2608.10893v1 Announce Type: new Abstract: Certified selective predictors attain whatever coverage they attain; operators impose an automation floor: answer at least a eta-fraction of shifted tar
arXiv:2608.10714v1 Announce Type: cross Abstract: The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its pro
arXiv:2509.26087v5 Announce Type: replace Abstract: In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable roa
arXiv:2608.10684v1 Announce Type: new Abstract: Multi-oriented text is ubiquitous in real-world scenes and remains a major challenge for scene text recognition (STR). Existing rotation-aware methods e
arXiv:2608.10756v1 Announce Type: cross Abstract: Embodied mobile manipulation requires language, visual observations, three-dimensional scene structure, and action feasibility to be aligned before ex
arXiv:2608.10343v1 Announce Type: new Abstract: While deep learning-based denoising has become widely adopted in low-dose CT, conventional models use generic architectures designed for natural images,
arXiv:2608.10668v1 Announce Type: new Abstract: Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timesta
arXiv:2608.10723v1 Announce Type: new Abstract: Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher i
ChatGPT desktop app will not download images even after a complete reinstall I am on Windows 11 and the Download button in the ChatGPT desktop app does nothing when I try to download generated images.
arXiv:2608.10780v1 Announce Type: new Abstract: Generalist robot policies aim to map multimodal observations and linguistic task instructions to actions across diverse tasks. However, existing methods
arXiv:2608.11077v1 Announce Type: new Abstract: Feed-forward Gaussian reconstruction has recently emerged as an efficient approach for driving scene reconstruction. However, prevailing LiDAR-based met
arXiv:2608.10429v1 Announce Type: new Abstract: Deep learning models that synthesize PET from CT or MRI can reduce patient dose and scanner demand, but are typically optimized with global losses such
Liquid AI put out LFM2.5-VL-3B today, which is a 3.1B vision model that weighs roughly 2GB and fits well on a phone Benchmarks are benchmarks so I tried something sillier. Took a photo of a little Ste
LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training. LFM2.5-VL-3B can process both
Local AI is exploding! Transformers.js, that we've been building @huggingface for the past three years has now become the most popular open-source library to run AI models directly in your browser and
arXiv:2608.11167v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image repr
arXiv:2608.10131v1 Announce Type: new Abstract: Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are diffic
arXiv:2608.10449v1 Announce Type: new Abstract: Long-horizon service robots require persistent world models that can be built autonomously in unseen environments and revised as task-relevant objects c
arXiv:2608.11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-acce
Burke Holland announced that the Qwen‑3 Coder 30B model was running locally through GitHub Copilot’s Ollama integration, achieving roughly 85 tokens per second while utilizing 96 GB of VRAM. He noted
arXiv:2608.11017v1 Announce Type: cross Abstract: Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it la
One of the reasons I got into local LLMs was the possibility of getting answers using my own documents and books (a few hundreds) instead of having to search through them manually. However since I'm n
arXiv:2509.03140v2 Announce Type: replace-cross Abstract: We demonstrate that local sensing is sufficient for effective global reconfiguration of homogeneous pivoting cube modular robots in two dimens
arXiv:2608.10553v1 Announce Type: cross Abstract: Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often ineff
arXiv:2608.10933v1 Announce Type: new Abstract: Text-to-Video (T2V) generative models are vulnerable to jailbreak attacks in real-world deployment, leading them to produce harmful or inappropriate con
arXiv:2608.11034v1 Announce Type: cross Abstract: In LLM pre-training, synchronization propagates rank-local stalls, slowdowns, and numerical errors into job-wide symptoms, obscuring their origin. Exi
arXiv:2608.10888v1 Announce Type: new Abstract: Per-point uncertainty models are important in structured-light 3D reconstruction for probabilistic registration, fusion, and quality assessment. In prac
arXiv:2608.10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing mo
arXiv:2608.09995v1 Announce Type: cross Abstract: Joint demosaicing and denoising is a fundamental step in camera image signal processing, yet remains challenging because different Bayer-like color fi
arXiv:2603.12231v3 Announce Type: replace Abstract: Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual fe
arXiv:2608.11146v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. How
arXiv:2608.10234v1 Announce Type: cross Abstract: Operator learning is a rapidly advancing area of computational science. It is particularly well suited to problems where a partial differential equati
arXiv:2608.10981v1 Announce Type: new Abstract: Task-driven 3D affordance grounding aims to localize the functional region in a cluttered 3D scene that enables an action specified by a natural-languag
arXiv:2509.04009v2 Announce Type: replace-cross Abstract: Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit uni
arXiv:2608.10618v1 Announce Type: new Abstract: Embodied artificial intelligence aims to develop agents that perceive, reason, and act through continuous interaction with the physical world. However,
arXiv:2608.10835v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by th
ModelOpt checkpoints apply a float32 global scale to every projection output on top of the per-group quantization scales. Running the multiply and the cast back to the activation dtype as separate eag
arXiv:2608.11201v1 Announce Type: new Abstract: Recent advances in video generation models have significantly improved the realism of synthetic videos, blurring the boundary between generated and auth
arXiv:2608.10489v1 Announce Type: new Abstract: Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token p
GitHub announced on August 12 2026 that users can now integrate Ollama as a provider in **GitHub Copilot for JetBrains**. This update allows JetBrains developers to switch to or add locally‑hosted (or
arXiv:2608.08023v1 Announce Type: new Abstract: Building on recent advances in world models, World Action Models (WAMs) jointly model video prediction and action generation. However, they typically re
arXiv:2608.08163v1 Announce Type: new Abstract: The convergence of the Metaverse and Large Language Model (LLM)-based AI agent is catalyzing a shift toward autonomous, immersive, and personalized peda
arXiv:2608.01344v2 Announce Type: replace Abstract: Stage-one stellarator design searches a high-dimensional family of three-dimensional plasma boundaries and fixed-boundary MHD equilibria for configu
arXiv:2608.07542v1 Announce Type: new Abstract: Autonomous research loops driven by large language models can run machine-learning experiments at scale but tend to drift toward local refinements of wh
arXiv:2608.08883v1 Announce Type: new Abstract: Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows. H
arXiv:2608.07550v1 Announce Type: new Abstract: Vision-language models return structured chest-radiograph findings through interfaces exposing no confidence score, so a receiving institution cannot re
arXiv:2608.09908v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to identify and temporally localize abnormal events in videos. Supervised methods learn anomaly decision boundaries f