Knowledge catalogue
arXiv:2608.08467v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequentl
arXiv:2608.08382v1 Announce Type: new Abstract: As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control. Enabling fractio
arXiv:2608.08600v1 Announce Type: cross Abstract: World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environment
arXiv:2608.09222v1 Announce Type: new Abstract: Inverse decision modeling infers latent properties of decision processes from observed behavior, but existing formulations rely primarily on action traj
arXiv:2608.07548v1 Announce Type: cross Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to make fine-grained navigation decisions under partial observabili
https://preview.redd.it/xxjh11f38jih1.png?width=1852&format=png&auto=webp&s=76850ed51e29a8bc86c2ca718d4320075eed4363 Just wanted to share a user report that I found to be very interesting. Some person
arXiv:2608.07148v1 Announce Type: new Abstract: Modern manufacturing imposes six coupled demands on adaptive control: local decisions with global consequences, partial observability, nonstationarity,
arXiv:2608.06861v1 Announce Type: new Abstract: Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions. Existin
Hey. Just tried it on my old ass gpus 😄 Surprisingly Tensor Split is working on 2 gpus almost doubling PP (wonder how it will work with 4 gpus) Q6 — 1 GPU llama-server --model <MODEL_DIR>/Muse-Glimmer
arXiv:2608.06931v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory
arXiv:2509.10482v2 Announce Type: replace-cross Abstract: The increasing sophistication of technology systems makes traditional threat modeling hard to scale, especially for small organizations with l
arXiv:2608.05250v1 Announce Type: new Abstract: Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach
arXiv:2608.05420v1 Announce Type: cross Abstract: Large language models (LLMs) can generate text that resembles a mathematical proof, but resemblance does not establish correctness. A formal proof che
Financial Times: Sources: ByteDance is pretraining an AI model with up to 10T parameters, roughly 3x larger than Kimi K3 and larger than the 8T estimate for Anthropic's Mythos 5 — TikTok owner trainin
arXiv:2608.05889v1 Announce Type: cross Abstract: Large language models (LLMs) can leave small stylistic traces in text written with their help. The most discussed is the em-dash (U+2014), especially
this talk by openai researchers going through hugging face incident is totally insane, so much to unpack openai only realized it was their agent who hacked hugging face infra while asking hf to revoke
arXiv:2608.05776v1 Announce Type: new Abstract: Autoregressive continuation provides a natural path toward minute-scale audio-visual generation by repeatedly extending a short-window generator conditi
arXiv:2608.06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet m
arXiv:2608.04472v1 Announce Type: cross Abstract: The development of foundation models (FMs) is crucial for advancing endoscopic image analysis. However, existing endoscopy FMs mainly rely on self-sup
arXiv:2608.04106v1 Announce Type: new Abstract: Dense image matching establishes pixel-wise correspondences and underpins broad applications in computer vision and photogrammetry. However, extending d
arXiv:2608.04174v1 Announce Type: new Abstract: Time series data are ubiquitous in practical applications, where classification (TSC) and extrinsic regression (TSER) have emerged as essential tasks fo
arXiv:2608.02799v1 Announce Type: cross Abstract: Score-based diffusion models are typically formulated using continuous-time stochastic differential equations and measure-theoretic stochastic calculu
arXiv:2608.03067v1 Announce Type: new Abstract: Changes in spontaneous speech provide an early signal of cognitive dysfunction in Alzheimer's disease (AD) that large language models (LLMs) can detect.
Also I think AISI is a great model of a government agency tasked with AI security. They have open benchmarks, very fast testing, and clear communication about incidents that is neither hyped up nor hi
arXiv:2608.03629v1 Announce Type: new Abstract: A companion paper studies when activation patching and weight-space ablation agree, inside an idealized model where a conditional computation is carried
arXiv:2608.02620v1 Announce Type: new Abstract: LLM-as-a-judge evaluation has become a dominant paradigm for ranking language models, yet the ecosystem remains fragmented: most benchmarks ship their o
arXiv:2608.02629v1 Announce Type: cross Abstract: The use of variable well perforation and injection strategies can improve the efficiency of geological carbon storage operations. We develop a new mul
arXiv:2608.02713v1 Announce Type: cross Abstract: Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow,
arXiv:2608.02689v1 Announce Type: new Abstract: We convert 21 of 28 full-attention layers of Qwen3-0.6B-Base into KDA (Kimi Delta Attention) linear-attention layers on a single consumer-grade GPU budg
arXiv:2608.02662v1 Announce Type: cross Abstract: Reliable forecasting of nonlinear physical systems underpins scientific discovery and engineering decision-making. Yet high-fidelity simulations are p
arXiv:2608.00263v1 Announce Type: new Abstract: Contact planning in robotics requires models that are both computationally efficient and physically accurate. Sphere-based robot representations satisfy
arXiv:2608.00355v1 Announce Type: new Abstract: Progress in large language models is often summarized using a single scalar measure, such as a time horizon, a latent ability estimate, or an aggregate
arXiv:2607.11510v2 Announce Type: replace Abstract: Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanis
arXiv:2608.02428v1 Announce Type: new Abstract: Forecasting future states from video sequences is a critical challenge for autonomous robotic systems and a fundamental objective of world modeling. Pri
arXiv:2608.00086v1 Announce Type: new Abstract: Brain tumor diagnosis is a time-sensitive process in which patients may wait weeks for a finalized pathology report. This problem motivates automated sy
arXiv:2608.01661v1 Announce Type: new Abstract: The challenge of fair deepfake detection (FDD) has attracted increasing attention. Existing fairness-enhanced detectors often suffer from suboptimal gen
arXiv:2608.01005v1 Announce Type: new Abstract: Solomonoff Induction, or SolInd, provides an ideal unbounded model of a priori sequence prediction but cannot naturally describe extrapolation from a gi
arXiv:2608.00925v1 Announce Type: new Abstract: Monocular panoramic SLAM benefits from substantial visual overlap under large camera rotations, yet remains prone to errors caused by camera tilt, scale
arXiv:2603.19258v2 Announce Type: replace Abstract: Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the
arXiv:2608.00489v1 Announce Type: new Abstract: Single-photon avalanche diode (SPAD) cameras are promising for low-light and high-dynamic-range intensity imaging, but their practical use is limited by
arXiv:2608.00561v1 Announce Type: cross Abstract: Vision-language models (VLMs) process image patches and text tokens in a shared residual stream, but the local geometry through which the two modaliti
arXiv:2608.01898v1 Announce Type: new Abstract: Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance. We identify a persistent low-frequency bia
arXiv:2510.24598v2 Announce Type: replace Abstract: Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability. To address this,
arXiv:2607.29172v1 Announce Type: cross Abstract: While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-sourc
arXiv:2606.14142v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world kn
arXiv:2607.29177v1 Announce Type: cross Abstract: Utility data (e.g., electricity, water, and gas consumption), collected by ubiquitous sensors and embedded devices, often contains substantial missing
arXiv:2607.29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought. This has been a promising development for AI safety--where models verbal
I serve a free local model on my Mac Mini and route real agent work to it. To check I was not fooling myself, I set up a blind grader that replays frontier tasks locally and scores both. https://previ
arXiv:2607.28644v1 Announce Type: cross Abstract: Creativity in computational systems is often evaluated as an objective property of artifacts, with existing Computational Creativity (CC) frameworks a
arXiv:2607.28903v1 Announce Type: cross Abstract: Variance-based global sensitivity analysis (GSA) plays a key role in uncertainty quantification by identifying the contributions of uncertain inputs t
I know qwen 3.5 4b is great but a bit too large and miniPCM5 1b is great for agentic use but not so great for multilingual natural language understanding. Google eXb variants are just too big in total
Checkmate: you can’t take the harness (which is typically in large part symbolic) away from the neural model without giving up performance. HUGE victory for neurosymbolic AI, straight from @AnthropicA
I don't know much about llms aside from downloading them through a frontend and running them on my laptop or potato phone. Google released gemma 4, but unlike gemma 3, there isn't a 1b model this time
arXiv:2511.10101v2 Announce Type: replace Abstract: Background: both embodied intelligence and developmental morphogenesis depend on a division of labour between centralized guidance and distributed m
arXiv:2602.05307v2 Announce Type: replace Abstract: Large reasoning models (LRMs) achieve strong performance by producing long chains of thought, but their inference costs are high and often generate
arXiv:2607.26220v1 Announce Type: cross Abstract: Context: Large Language Models (LLMs) offer natural-language flexibility for automated requirements elicitation but frequently generate structurally i
arXiv:2601.16651v3 Announce Type: replace Abstract: Gradient-based methods for instance-based explanation for large language models (LLMs) are hindered by the immense dimensionality of model gradients
Atomic Chat signed the Open Weights letter! We believe everyone should be able to run AI on their own device. When a model is open, thousands of teams fine-tune it, quantize it and build new tools on
arXiv:2607.26933v1 Announce Type: cross Abstract: Federated Learning (FL) is vulnerable to backdoor attacks because of its distributed nature in edge computing scenarios. Existing defense methods show
arXiv:2607.26801v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative learning over decentralized data silos without centralizing raw data. However, heterogeneous local archite