Knowledge catalogue
arXiv:2601.11729v2 Announce Type: replace Abstract: Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities
arXiv:2608.12743v1 Announce Type: new Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ability
arXiv:2602.09120v2 Announce Type: replace Abstract: Electrospinning is a powerful technique for producing micro to nanoscale fibers with application specific architectures. Small variations in solutio
arXiv:2608.12443v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich informa
arXiv:2510.06200v4 Announce Type: replace-cross Abstract: Current time series foundation model (TSFM) training corpora largely omit data with certain complexities like irregular temporal sampling. Ast
arXiv:2608.12654v1 Announce Type: new Abstract: Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or wire a payment. The steering decision is the pr
arXiv:2608.12334v1 Announce Type: cross Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood.
arXiv:2608.12549v1 Announce Type: new Abstract: Visual content is the dominant medium of communication, yet without audio descriptions (ADs), it remains inaccessible to blind and low-vision people. AD
arXiv:2608.13416v1 Announce Type: new Abstract: Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. P
arXiv:2608.13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-
arXiv:2608.12920v1 Announce Type: new Abstract: Sports-video understanding is moving beyond event recognition toward explaining how actions collectively shape match progression, however, existing tenn
I'm currently testing out Qwen3.8-27B using Unsloth's UD-Q4_K_XL running a freshly rebuilt llama.cpp. I have a 22GB RTX 2080TI on which I'm able to fit 100k context with q8_0 quantization, and using M
arXiv:2608.12875v1 Announce Type: new Abstract: Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across
arXiv:2608.12341v1 Announce Type: new Abstract: Cultural taboo safety is essential for deploying large language models (LLMs), as culturally insensitive outputs may cause offense or even social harm.
arXiv:2608.12959v1 Announce Type: cross Abstract: Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades. O
There's a lot of real-world documents that are scanned, rotated, handwritten, or some combination of any of these elements. This week we created a comprehensive document extraction benchmark that cont
arXiv:2608.13389v1 Announce Type: new Abstract: Enterprise security topology design requires translating business intent, regulatory requirements, and risk assumptions into zones, boundary devices, in
arXiv:2608.13047v1 Announce Type: new Abstract: Driven by the availability of large-scale datasets, Human Pose Estimation (HPE) plays a critical role in numerous downstream tasks. However, mainstream
arXiv:2608.13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more
arXiv:2608.13331v1 Announce Type: cross Abstract: The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further ex
arXiv:2509.24928v2 Announce Type: replace Abstract: This work introduces an adaptive Bayesian algorithm for real-time trajectory prediction via intention inference, where a target's intentions and mot
arXiv:2608.13167v1 Announce Type: cross Abstract: When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distingui
arXiv:2608.13495v1 Announce Type: new Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis. Structured a
arXiv:2608.13221v1 Announce Type: new Abstract: The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models
OpenAI announced the “Ultrafast” mode (GPT‑5.6 Sol), which can deliver responses up to 14× faster than standard API calls. The feature will first be released to a limited group of API users, with expa
arXiv:2512.02965v2 Announce Type: replace Abstract: Addressing the urgent need for high-performance real-time low-light image enhancement on resource-constrained edge devices in low-illumination scena
arXiv:2608.12962v1 Announce Type: new Abstract: Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setti
arXiv:2608.12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programma
arXiv:2608.12953v1 Announce Type: new Abstract: Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that pro
arXiv:2508.12220v2 Announce Type: replace-cross Abstract: Can a prospectively instrumented training continuation reproduce a deletion counterfactual exactly after selected examples leave its replay da
What's Changed launch: add Muse Code integration by @dhiltgen in #17594 model/renderers: match Muse Glimmer reasoning template by @dhiltgen in #17732 launch: add DeepSeek Harness integration by @Parth
Qwen 3.8 - 27B model support This release adds the support of Qwen 3.8 27B. For Apple Silicon devices, Ollama has in particular optimized for maximum performance and output quality suitable for repeat
arXiv:2608.13522v1 Announce Type: cross Abstract: AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in w
arXiv:2608.13260v1 Announce Type: new Abstract: Accurate modeling and forecasting of power transformer thermal behavior are critical for reliability, asset lifetime, and optimized power system operati
arXiv:2608.12333v1 Announce Type: cross Abstract: Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the l
arXiv:2608.13418v1 Announce Type: cross Abstract: Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution. To this end, we
We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world
I prefer the model to have the internet as a source of truth and info and my coding work needs lot of web lookups. The middle bar section ( light blue) is the weekly quota taken by it. 120 web search
I am currently building up a local assistant profile on my MacBook Pro M2 with 32gbs. With Claude I am building out this Hermes agent to be my assistant. I am using Qwen3.6 A3B 4bit. We have Frankenst
What's new in LangChain? 🚀 🔌 Support for OpenAI's 3.0 SDK (using httpx2) ✨ Support for gemini-3.7-flash Plus a wave of core reliability fixes from external contributors: 🛠️ Tool calling & structured o
arXiv:2608.12324v1 Announce Type: cross Abstract: People increasingly ask large language models (LLMs) for counsel on questions of faith, doctrine, and pastoral care. These questions are not ordinary
arXiv:2608.12489v1 Announce Type: new Abstract: Organizations decide whom to treat under a budget and want to know what a targeting rule would have earned before deploying it. Off-policy evaluation pr
arXiv:2505.09662v4 Announce Type: replace Abstract: Large Language Models (LLMs) have been shown to be highly persuasive, but when and why they outperform humans is still an open question. We compare
arXiv:2608.12888v1 Announce Type: new Abstract: Agent-memory systems increasingly buy retrieval quality with structure, transforming raw conversation histories into summaries, embeddings, trees, or kn
arXiv:2607.19058v2 Announce Type: replace-cross Abstract: Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training. On a 6.78B-parameter MoE language m
arXiv:2608.13337v1 Announce Type: new Abstract: Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see
arXiv:2608.13168v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationshi
arXiv:2608.12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation. We demonstrate that this enfo
Google will now allow you to remove visible watermarks from the images, videos, and music made with AI tools. With the update, you can toggle off a new 'Media watermark' setting in Gemini and Google's
Chinese artificial intelligence developer Z.ai Co. today debuted GLM-5.3, an open-source large language model that set records across several popular benchmarks. The LLM is based on an algorithm calle
Throughput observation more than a demo. Box and recording are sudoingX's on X, shared with his okay; I work on Ling at inclusionAI. He handed the web UI on his llama-server a 33-token prompt — build
arXiv:2608.12269v1 Announce Type: new Abstract: Public procurement involves the allocation of substantial financial resources; therefore, continuous oversight through audits, controls, and monitoring
arXiv:2608.11762v1 Announce Type: cross Abstract: Alzheimer's disease is a leading cause of death with no cure. Therefore, early detection is critical to slow progression and preserve quality of life.
arXiv:2608.12138v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but s
arXiv:2608.11613v1 Announce Type: new Abstract: In this paper, we propose a local Sinkhorn divergence framework for conditional distribution reconstruction of multidimensional random fields. By utiliz
arXiv:2608.12274v1 Announce Type: cross Abstract: Background: Accurate segmentation of the Left Anterior Descending (LAD) artery in 3D free-breathing, non-contrast CT is critical for cardiac dose spar
A positive Claude watermark doesn’t prove it’s entirely AI-generated and the lack of a watermark doesn’t prove it’s entirely human-generated. The two best ways to tell if something is AI-generated: 1)
arXiv:2502.11665v3 Announce Type: replace-cross Abstract: The classical kernel ridge regression problem aims to find the best fit for the output Y as a function of the input data Xin R^d, with a fixed
A weird experiment I've been trying the last few weeks is having Claude take over day-to-day maintenance of our apps. Seeing early signs of life that this might be possible. The setup is straightforwa
arXiv:2608.12144v1 Announce Type: cross Abstract: Over the past decade, many test adequacy metrics have been proposed for deep learning that characterize test dataset adequacy from different perspecti