Knowledge catalogue
arXiv:2605.25469v1 Announce Type: new Abstract: Quantization-aware training (QAT) is widely deployed but typically relies on the Straight-Through Estimator (STE), which passes gradients through non-di
arXiv:2602.18527v2 Announce Type: replace-cross Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. T
arXiv:2602.17162v2 Announce Type: replace Abstract: Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the 'Laws of Nature'. Whil
arXiv:2605.25240v1 Announce Type: cross Abstract: Two methodologies dominate current practices of benchmarking: rubric-based scoring evaluates items against predefined criteria, whereas comparative ju
arXiv:2510.02327v2 Announce Type: replace-cross Abstract: Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and se
arXiv:2605.25556v1 Announce Type: cross Abstract: Automated theorem proving systems built on Lean 4 increasingly rely on parallel tactic search over partially specified proofs, such as those generated
arXiv:2502.06018v3 Announce Type: replace-cross Abstract: Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter ex
arXiv:2605.25267v1 Announce Type: cross Abstract: Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cos
arXiv:2411.09816v4 Announce Type: replace Abstract: Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. A
arXiv:2605.25608v1 Announce Type: cross Abstract: The ability of deep neural networks to learn hierarchical features is widely regarded as a key mechanism underlying their success in high-dimensional
arXiv:2605.24597v1 Announce Type: new Abstract: Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We
arXiv:2510.03827v2 Announce Type: replace-cross Abstract: LIBERO has emerged as a widely adopted benchmark for evaluating Vision-Language-Action (VLA) models; however, its current training and evaluat
arXiv:2508.15760v2 Announce Type: replace-cross Abstract: Tool calling has emerged as a critical capability for AI agents. In contrast to conventional tool calling frameworks that rely on static, prov
arXiv:2605.25676v1 Announce Type: new Abstract: We release Llamion, a family of 14B-parameter open-weight language models obtained by transforming Orion-14B into the standardized Llama-family architec
arXiv:2605.25415v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adve
Cohere has announced a creative marketing initiative featuring LLM-themed merchandise available through their shop, with the tagline playing on the phrase 'on premises' to humorously suggest their lan
arXiv:2605.24417v1 Announce Type: new Abstract: Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data
arXiv:2605.26106v1 Announce Type: new Abstract: Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of trans
This podcast episode discusses Google's release of Gemini 3.5 and its Omni multimodal capabilities, covers recent developments in Elon Musk's AI ventures, and examines tensions or competition between
arXiv:2512.18735v2 Announce Type: replace-cross Abstract: Modern Large Multimodal Models (LMMs) have demonstrated extraordinary ability in static image and single-state spatial-temporal understanding.
arXiv:2605.24699v1 Announce Type: new Abstract: Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can
arXiv:2605.24661v1 Announce Type: new Abstract: LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offe
arXiv:2605.24244v1 Announce Type: cross Abstract: Low-dimensional embeddings are widely used as visual summaries of high-dimensional data and to enable downstream scientific discoveries. Yet, popular
arXiv:2605.24941v1 Announce Type: cross Abstract: Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinn
Cohere announced merchandise available for purchase at their on-premises shop (shop.cohere.com), likely offering branded items such as apparel, stickers, or other company merchandise for employees, cu
arXiv:2605.25890v1 Announce Type: new Abstract: This paper applies machine learning to the difficult and important task of version control merging. (1) We constructed a dataset, Merge-Bench, of 7938 r
arXiv:2605.22337v2 Announce Type: replace Abstract: The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when th
arXiv:2605.25030v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (L
arXiv:2605.26006v1 Announce Type: cross Abstract: Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typic
arXiv:2605.24523v1 Announce Type: cross Abstract: Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural re
arXiv:2605.25859v1 Announce Type: cross Abstract: We study the mean-squared error of k-fold cross-validation as a risk estimator, with particular emphasis on how its accuracy depends on the number of
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