Knowledge catalogue
Mistral-7B v0.3 model achieves significant memory optimization when running at 128K context length in llama.cpp, reducing live VRAM usage from 22,657 MiB to 13,235 MiB while maintaining minimal perfor
arXiv:2605.24681v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine
arXiv:2505.23764v3 Announce Type: replace-cross Abstract: Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, h
arXiv:2605.25574v1 Announce Type: cross Abstract: Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing st
arXiv:2605.24777v1 Announce Type: new Abstract: LiDAR model selection is a critical issue in roadside sensing systems, as it directly determines both perception capability and deployment cost. However
Jeremy Howard comments that large language models released 6 months ago feel comparable in capability to recently released models, suggesting that the pace of improvement in model development may be s
arXiv:2605.25842v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex multimodal tasks, but their large parameter sizes m
arXiv:2605.24922v1 Announce Type: new Abstract: We present MuJoCoUni, a downstream MuJoCo distribution for online robot learning and batched physics evaluation. Alongside the open-loop batched traject
arXiv:2605.24919v1 Announce Type: new Abstract: Hallucinations in Large Language Models (LLMs) represent a critical barrier to their reliable deployment, a vulnerability heavily exacerbated in non-Eng
arXiv:2605.25861v1 Announce Type: cross Abstract: 3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking t
arXiv:2602.05725v2 Announce Type: replace Abstract: Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remai
arXiv:2505.03677v3 Announce Type: replace Abstract: Learning maps between function spaces with a strong inductive bias is a central challenge in soft computing, especially when training data are scarc
arXiv:2605.25701v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-clou
arXiv:2605.25985v1 Announce Type: new Abstract: Complex Query Answering (CQA) is a fundamental knowledge representation and reasoning task over incomplete knowledge graphs (KGs). Answering existential
arXiv:2605.25293v1 Announce Type: cross Abstract: Autonomous driving perception demands accurate and efficient processing of three-dimensional sensor data under strict power constraints. Traditional c
Neurosymbolic AI is saving deep learning from hitting the wall (*exactly* as I said my 2022 paper “deep learning is hitting a wall”) Really sad to see someone as smart @peterwildeford confusing the or
New on the Engineering Blog: The access and permissions we grant agents should evolve with their capabilities. In our own products, we set these parameters through sandboxing, which limits the scope o
Nine reasons why I warned OpenAI might fail and turn out to be the WeWork of AI, from two years ago. 9 reasons that OpenAI could someday be seen as the WeWork of AI: 👉 Lots of competitors are catching
arXiv:2605.24910v1 Announce Type: new Abstract: Financial Numerical Entity (FNE) understanding aims to recover the meaning of numerical mentions in financial reports. Existing studies primarily focus
arXiv:2605.25590v1 Announce Type: cross Abstract: We study nonstationary generalized linear bandits (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-
arXiv:2506.21137v3 Announce Type: replace Abstract: Linear attention mitigates the quadratic complexity of softmax attention but suffers from a critical loss of expressiveness. We identify two primary
Artificial intelligence penetration testing startup Novee Cyber Security Ltd. today launched Agentic Fix, a new capability that pushes validated exploit findings directly into the AI coding agents dev
The shift to agentic AI creates a new CPU requirement for the AI factory: fast cores, massive memory bandwidth and the ability to sustain high performance when all cores are active. Initial benchmark
arXiv:2605.24319v1 Announce Type: new Abstract: As large language models become a default source of guidance on personal, moral, and existential questions, it matters whether they draw on the religiou
arXiv:2605.25234v1 Announce Type: cross Abstract: Epistemic uncertainty is often viewed as a reducible uncertainty that vanishes with increasing data. This perspective implicitly assumes parameter ide
arXiv:2605.24741v1 Announce Type: cross Abstract: We study the sample complexity of robust binary hypothesis testing under three standard contamination models: arepsilon-additive (Huber), arepsilon-su
arXiv:2603.07523v2 Announce Type: replace Abstract: Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a p
arXiv:2605.24261v1 Announce Type: new Abstract: A critical challenge facing clinicians managing chronic disease interventions is sustaining long-run patient health given limited information and resour
arXiv:2603.28128v2 Announce Type: replace Abstract: Although Graph Neural Networks (GNNs) have shown promise for smart contract vulnerability detection, they still face significant limitations. Homoge
arXiv:2605.26092v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and t
arXiv:2605.24969v1 Announce Type: cross Abstract: Long-tailed recognition suffers from a persistent head--tail trade-off: improving tail performance often degrades head accuracy and can increase train
Our strategy lead @yeahfortommy was just on stage with CTO of @alibaba_cloud discussing Hermes Agent at the Qwen Conference, check it out: https://www.youtube.com/live/r99c3sfgkmc?si=cnuR07ofhO_V69l-&
arXiv:2605.24907v1 Announce Type: new Abstract: We present an overview of PsyDefDetect, the shared task on detecting levels of psychological defense mechanisms in emotional support dialogues, co-locat
arXiv:2605.06505v2 Announce Type: replace-cross Abstract: We introduce PACZero, a family of PAC-private zeroth-order mechanisms for fine-tuning large language models that delivers usable utility at I(
arXiv:2605.24154v1 Announce Type: new Abstract: Current safety alignment of foundation models largely follows a one-size-fits-all paradigm, applying the same refusal policy across users and contexts.
arXiv:2605.24549v1 Announce Type: new Abstract: Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adapta
arXiv:2605.25348v1 Announce Type: cross Abstract: Low-dose computed tomography (LDCT) reconstruction faces a critical tradeoff between reconstruction quality and resource requirements. While recent de
arXiv:2605.23984v1 Announce Type: cross Abstract: Industrial anomaly detection has attracted significant attention as a fundamental challenge in industrial systems. The rapid advancement of heterogene
arXiv:2605.24792v1 Announce Type: cross Abstract: The major limitations of gastrointestinal (GI) endoscopy AI systems arise from a shortage of annotated data, strict privacy policies, and significant
arXiv:2605.25782v1 Announce Type: new Abstract: Humanoid parkour requires locomotion policies to coordinate whole-body dynamics across rapidly changing terrains such as stairs, gaps, slopes, and obsta
arXiv:2602.00511v2 Announce Type: replace Abstract: Despite their empirical success, neural network classifiers remain difficult to interpret. In softmax-based models, class regions are defined implic
arXiv:2605.24352v1 Announce Type: new Abstract: Multi-agent collaboration, especially in human-AI teaming, requires agents that can adapt to novel partners with diverse and dynamic behaviors. Conventi
arXiv:2605.25353v1 Announce Type: new Abstract: Inverse problems in partial differential equations (PDEs) involve estimating the physical parameters of a system from observed spatiotemporal solution f
arXiv:2605.24562v1 Announce Type: cross Abstract: Pedestrian intention and trajectory prediction are critical for the safe deployment of autonomous driving systems, directly influencing navigation dec
arXiv:2605.25572v1 Announce Type: cross Abstract: The growing complexity of quantum programming frameworks has exposed a critical limitation in existing large language model (LLM)-based code assistant
arXiv:2605.25535v1 Announce Type: new Abstract: Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are wor
arXiv:2605.25212v1 Announce Type: new Abstract: Federated learning (FL) is an effective paradigm for enhancing the learning capability of edge devices while preserving data privacy. In geographically
arXiv:2605.24590v1 Announce Type: cross Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise. Ex
arXiv:2601.05613v2 Announce Type: replace-cross Abstract: While collaborative forecasting on distributed time series is highly desirable, directly pooling localized datasets is often impractical due t
arXiv:2605.24577v1 Announce Type: cross Abstract: Independently trained transformers compute the same function in residual-stream bases that differ by a uniform random rotation on SO(d_{model}). We ca
arXiv:2602.01322v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. H
arXiv:2605.24558v1 Announce Type: new Abstract: AI for Science (AI4Science) workflows often treat the released dataset as a fixed interface to the underlying system. However, in domains relying on ind
arXiv:2502.15835v5 Announce Type: replace-cross Abstract: Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and cou
arXiv:2605.24904v1 Announce Type: new Abstract: Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these b
arXiv:2605.24920v1 Announce Type: cross Abstract: Quaternion neural networks are parameter-efficient and model multidimensional dependencies by representing four related features as a single entity. H
arXiv:2410.10652v4 Announce Type: replace-cross Abstract: Cells in multicellular organisms coordinate to form structural and functional niches. With spatial transcriptomics (ST) enabling gene expressi
arXiv:2605.24218v1 Announce Type: new Abstract: Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how human
arXiv:2605.25955v1 Announce Type: cross Abstract: Large language models (LLMs) face a dual challenge in creative capability evaluation: existing benchmarks (e.g., Story Cloze Test, HellaSwag) measure
Nous Research has added support for Qwen 3.7 Max, a large language model, within their Hermes Agent framework. This integration enables users to leverage Qwen 3.7 Max's capabilities when building or d
Alibaba's Qwen team has released Qwen3.7 Max, their most advanced model to date, now available for use with Go programming language support. The model features a 1 million token context window and is