Knowledge catalogue
arXiv:2604.26390v1 Announce Type: cross Abstract: Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades
arXiv:2604.24912v1 Announce Type: cross Abstract: We introduce HAML (Hamiltonian Adaptation via Meta-Learning), a framework for fast online adaptation of effective Hamiltonian models of superconductin
Sheer insanity. Amazon, Google, Microsoft, and Meta collectively are spending more money than the Manhattan Project *every single month*. More than 12x the Manhattan Project every year. And what they
The Guardian: Australia unveils a draft News Bargaining Incentive scheme that imposes a 2.25% levy on local revenues for platforms; Meta says the government is “simply wrong” — Google also rejects nee
arXiv:2604.24178v1 Announce Type: cross Abstract: Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives
arXiv:2604.24096v1 Announce Type: cross Abstract: Training reliable respiratory sound classification models remains challenging due to the limited size and subject diversity of datasets. Ensemble meth
China is blocking the Manus acquisition by Meta. A few things stand out: - China has historically been more opaque and less public in restricting foreign acquisitions of Chinese tech assets, while the
Clem Delangue posted about someone flying to work with the llama.cpp team on developing next-generation local AI capabilities, framed as meta commentary on headlines related to the endeavor. The post
arXiv:2604.19072v1 Announce Type: cross Abstract: Semi-supervised learning with manifold regularization is a classical framework for jointly learning from both labeled and unlabeled data, where the ke
Ashley Gold / Axios: Filing: Anthropic spent 1.6M and OpenAI 1M on lobbying in Q1, vs. 360K and 560K in Q1 2025, respectively; Meta topped Big Tech lobbying spending with 7.1M — Both Anthropic and Ope
arXiv:2604.12325v1 Announce Type: cross Abstract: We consider the problem of offline black-box optimization, where the goal is to discover optimal designs (e.g., molecules or materials) from past expe
arXiv:2604.12336v1 Announce Type: cross Abstract: Streaming Data-Driven Optimization (SDDO) problems arise in many applications where data arrive continuously and the optimization environment evolves
arXiv:2410.17976v2 Announce Type: replace-cross Abstract: metasnf is an R package that enables users to apply meta clustering, a method for efficiently searching a broad space of cluster solutions by
arXiv:2601.07208v2 Announce Type: replace-cross Abstract: Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is
I think Muse Spark came in far better than most were expecting as the first new model attempt from Meta, especially given the fact that it has been a year since Llama 4 with no models at all (and that
Routing every task to your largest model burns tokens, adds latency, and inflates costs. @AI21Labs' Maestro Orchestration Meta Model (OMM) is the layer above your stack that dynamically selects the ri
sam3.cpp - Meta's SAM 3 in pure C++ with @ggerganov's ggml - Supports SAM 3.1, 3, 2.1, 2 and EdgeTAM - FP16, 4-bit quant (EdgeTAM in 15 MB) - Apple Metal GPU, CUDA, CPU - Text-prompted: 'peach' → ever
arXiv:2610.18535v1 Announce Type: new Abstract: Video understanding benchmarks are the primary yardstick for measuring progress in video-language modeling, and a growing body of work relies on them to
arXiv:2610.11067v1 Announce Type: new Abstract: Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classe
arXiv:2610.11117v1 Announce Type: new Abstract: Dynamic convolution enhances convolutional neural networks (CNNs) by adapting kernels to input content, but it expresses the effective kernel as a linea
arXiv:2511.04000v2 Announce Type: replace-cross Abstract: Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an effici
arXiv:2610.10393v1 Announce Type: cross Abstract: Models can be retrained as new data arrive, but deploying every new version risks replacing a good policy with a worse one. We study how to plan polic
arXiv:2610.01949v1 Announce Type: cross Abstract: Ransomware has emerged as a major cybersecurity threat, with incidents increasing in frequency and impact across critical sectors. These attacks are t
arXiv:2609.38143v1 Announce Type: new Abstract: Agent performance depends on both reasoning ability and the environment in which it acts. We study test-time AI-for-AI, asking how a Builder can learn t
arXiv:2609.38147v1 Announce Type: new Abstract: As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control c
arXiv:2609.21122v1 Announce Type: new Abstract: Manipulating previously unseen objects remains challenging, as their dynamics depend on latent physical properties, such as friction and mass distributi
arXiv:2609.19832v1 Announce Type: new Abstract: Relational table learning has gained increasing attention with the widespread use of relational databases. Existing methods typically rely on deep GNN o
arXiv:2609.18597v1 Announce Type: new Abstract: Propagation structures provide crucial evidence for fake news detection, yet existing approaches primarily rely on supervised GNN-based models, which re
arXiv:2602.00532v2 Announce Type: replace-cross Abstract: Constraint handling is central to constrained black-box optimization (BBO), where objective improvement and feasibility restoration often prov
arXiv:2609.11041v1 Announce Type: new Abstract: No Free Lunch theorem implies that any performance gains achieved by a classifier on a particular image distribution are necessarily offset by a loss of
arXiv:2609.09511v1 Announce Type: cross Abstract: Physical-layer authentication (PLA) in non-terrestrial networks (NTNs) is challenged by severe Doppler shifts, long delays, and fast channel variation
arXiv:2609.06396v1 Announce Type: new Abstract: Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet R
arXiv:2608.30678v1 Announce Type: new Abstract: Text-rich image understanding requires multimodal large language models (MLLMs) to organize OCR (Optical Character Recognition)-grounded evidence across
arXiv:2608.26638v1 Announce Type: new Abstract: Across various non-verifiable tasks, human evaluation is reliable but expensive, while automatic metrics are more scalable but often biased. Building on
arXiv:2608.20513v1 Announce Type: cross Abstract: Continuous deployment to large scale production systems creates a tension between release velocity and reliability. Every change is a potential reliab
arXiv:2608.12389v1 Announce Type: new Abstract: Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen conversational domains from only a handful of target-
arXiv:2607.19322v2 Announce Type: replace Abstract: Rubric-based evaluation of open-ended generation faces a fundamental tension between expressiveness and reliability. Authoring a faithful rubric req
arXiv:2608.00107v1 Announce Type: new Abstract: Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an in
arXiv:2605.05623v2 Announce Type: replace Abstract: Hyperspectral in situ sensing has shown promise in retrieving aquatic biogeochemical (BGC) parameters, such as total suspended solids, dissolved org
arXiv:2607.24749v1 Announce Type: cross Abstract: Although advancements in game character AI aim to enhance player engagement, evidence suggests that perceiving an opponent as artificial can diminish
arXiv:2607.22770v1 Announce Type: cross Abstract: Although artificial intelligence (AI) has shown promising performance in several medical tasks, accurate dementia etiology diagnosis with AI remains c
arXiv:2505.23378v3 Announce Type: replace Abstract: Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications. While mixed-effect models are comm
arXiv:2607.05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further
arXiv:2603.27313v2 Announce Type: replace Abstract: Disturbance observer-based control has shown promise in robustifying robotic systems against uncertainties. However, tuning such systems remains cha
arXiv:2607.00926v1 Announce Type: cross Abstract: Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data fr
arXiv:2606.28399v1 Announce Type: new Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual represe
arXiv:2606.23758v1 Announce Type: cross Abstract: Domain generalization learns from multiple source domains to generalize to unseen target domains. However, it often neglects the realistic case of lab
arXiv:2606.20702v1 Announce Type: new Abstract: Vision-language models (VLMs) have sparked growing interest in zero-shot Earth Observation (EO) downstream tasks, with further gains enabled by remote-s
arXiv:2606.21627v1 Announce Type: cross Abstract: As agentic systems tackle increasingly complex multi-step tasks, evaluating their trajectories presents a major bottleneck - human annotation of a sin
arXiv:2606.07217v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are emerging as a promising paradigm for robotic manipulation, enabling general-purpose policies trained from larg
arXiv:2606.04823v1 Announce Type: new Abstract: Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, where a system must plan, use tools, and act over extended horizon
arXiv:2605.31271v1 Announce Type: new Abstract: Driving Vision-Language-Action Models (Driving VLAs) aim to use language to improve end-to-end planning, but the language-action gap limits this promise
arXiv:2601.21909v2 Announce Type: replace Abstract: Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcem
arXiv:2602.02417v2 Announce Type: replace Abstract: Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-
arXiv:2504.04639v4 Announce Type: replace-cross Abstract: It is an open question whether the search and decision versions of promise CSPs are equivalent. Most known algorithms for PCSPs solve only the
arXiv:2605.25233v1 Announce Type: new Abstract: AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and de
arXiv:2601.18685v3 Announce Type: replace-cross Abstract: The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace. Rese
arXiv:2605.20385v1 Announce Type: new Abstract: Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the
arXiv:2508.13309v3 Announce Type: replace Abstract: Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such nor
arXiv:2605.18437v1 Announce Type: new Abstract: Vehicular edge computing (VEC) enables latency-sensitive vehicular applications by offloading computation-intensive tasks to nearby edge servers. Howeve