Knowledge catalogue
arXiv:2510.18196v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge.
arXiv:2604.07132v1 Announce Type: cross Abstract: Child Sexual Abuse Imagery (CSAI) classification is an important yet challenging problem for computer vision research due to the strict legal and ethi
arXiv:2604.06899v1 Announce Type: cross Abstract: Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliab
arXiv:2510.20549v2 Announce Type: replace Abstract: Despite advancements in SLAM technologies, robust operation under challenging conditions such as low-texture, motion-blur, or challenging lighting r
The specific X/Twitter post referenced (status ID 2042632799950352702) is not publicly accessible through search results, as X requires JavaScript and login to view individual posts. However, based...
arXiv:2604.06833v1 Announce Type: cross Abstract: As high quality public data becomes scarce, Federated Learning (FL) provides a vital pathway to leverage valuable private user data while preserving p
arXiv:2604.06219v1 Announce Type: cross Abstract: Across the Global North, calls for participatory artificial intelligence (AI) to improve the responsible, safe, and ethical use of AI have increased,
arXiv:2604.06203v1 Announce Type: cross Abstract: The integration of continuous data from built-in sensors and Large Language Models (LLMs) has fueled a surge of 'Sensor-Fused LLM agents' for personal
arXiv:2604.06215v1 Announce Type: cross Abstract: The governance of frontier general-purpose artificial intelligence has become a public-sector problem of institutional design, not merely a technical
arXiv:2604.07833v1 Announce Type: new Abstract: Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once gran
arXiv:2604.06285v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have become essential for tasks such as image synthesis, captioning, and retrieval by aligning textual and visual inform
arXiv:2510.25597v2 Announce Type: replace-cross Abstract: This paper presents a decentralized control framework that incorporates social awareness into multi-agent systems with unknown dynamics to ach
arXiv:2510.07809v4 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remain
arXiv:2604.08425v1 Announce Type: cross Abstract: When humans label subjective content, they disagree, and that disagreement is not noise. It reflects genuine differences in perspective shaped by anno
arXiv:2604.08039v1 Announce Type: new Abstract: Interpreting the concepts encoded by individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making pr
arXiv:2603.04300v2 Announce Type: replace Abstract: Foundation models in general promise to accelerate scientific computation by learning reusable representations across problem instances, yet constra
Meta acquired Moltbook, an AI-only social network launched in January 2026 by entrepreneurs Matt Schlicht and Ben Parr, after the platform had gone viral and then faded in popularity. Moltbook is ...
arXiv:2604.08203v1 Announce Type: new Abstract: Medical Vision-Language Models (VLMs) hold immense promise for complex clinical tasks, but their reasoning capabilities are often constrained by text-on
arXiv:2604.06628v1 Announce Type: new Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit t
arXiv:2604.07644v1 Announce Type: new Abstract: We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales to high-dimensional uncertain rob
arXiv:2604.06274v1 Announce Type: cross Abstract: In recent years, the pace of development of information technology in various areas has increased drastically, forcing cybersecurity specialists to co
arXiv:2604.07223v1 Announce Type: cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to int
arXiv:2604.06367v1 Announce Type: cross Abstract: Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate
The specific tweet from Gary Marcus (X post ID 2042361570253217968) is not publicly accessible without authentication, and the search results do not surface its specific content. Based on available...
AI critic Gary Marcus argues that GenAI's popularity has plateaued, with a landmark MIT study finding that only 5% of enterprise AI pilots generate revenue, while most deliver little to no measura...
A study commissioned by *The New York Times* and conducted by AI startup Oumi tested 4,326 Google searches using the SimpleQA benchmark, finding that Google's AI Overviews were accurate 85% of the...
I was unable to retrieve results for that specific tweet URL. The tweet ID referenced (2042037797503299600) does not appear in any indexed web search results, and X (formerly Twitter) posts are gen...
AI critic and cognitive scientist Gary Marcus publicly challenged the economic rationale behind Project Stargate, the Trump-announced $500 billion AI infrastructure initiative, arguing that the mat...
I was unable to retrieve the specific content of the linked X (Twitter) post by Ian Bremmer, as the URL points to a social media post that is not directly accessible or indexed with its full conten...
I was unable to retrieve the specific tweet at the URL provided (https://x.com/GaryMarcus/status/2042242813384142965). The tweet ID (2042242813384142965) appears to be from the future relative to c...
I was unable to retrieve the specific content from the X (Twitter) post at the URL provided, and my web search did not surface the original post or any reliable secondary sources quoting or summari...
The Trump administration's Department of Energy has invoked Section 202(c) of the Federal Power Act — a provision granting broad emergency authority over the electricity system that had previously...
Anthropic's Frontier Red Team report (April 2026) details the cybersecurity capabilities of Claude Mythos Preview, a general-purpose frontier model that performs strongly across the board but is s...
Common Failure Modes Break VLM-Powered OCR in Production. 🔁 Repetition Loops — model spirals into infinite whitespace, exhausts resources, cascades latency across your system 🛑 Recitation Errors — saf
I was unable to retrieve the specific tweet at that URL — the X (Twitter) page requires JavaScript/login to load, and the tweet ID `2041954164562145434` does not appear in any indexed search result...
The specific tweet (status ID 2041953155651661977) is not accessible — that ID appears to be from a future date and does not correspond to any retrievable post in the search results. The URL provid...
I was unable to retrieve the specific post at the URL provided (status ID `2041955770644713823`). This post ID does not appear in any search results, and X (formerly Twitter) requires JavaScript/lo...
The specific tweet (status ID 2041904683338625283) is not publicly accessible through search results, and the URL provided appears to reference a future or inaccessible post. The tweet ID is also b...
I was unable to retrieve the specific tweet at that URL (tweet ID 2041912293475414378). The tweet ID is extremely high — well beyond current Twitter/X ID ranges as of today — suggesting it may be a...
AI critic Gary Marcus uses the irony of ChatGPT's Voice mode being unable to perform a basic task — starting a timer — as a pointed illustration of the gap between AI industry hype and real-world c...
Anthropic's Frontier Red Team published a technical report (April 2026) detailing how their unreleased model, Claude Mythos Preview, autonomously identifies and exploits critical security vulnerabi...
not a remotely reasonable extrapolation. more like desperate attempt to prop up a rapidly declining IPO. BREAKING: Anthropic says 'AI could push US GDP to $44 trillion by 2030' 70% chance of IPO this
The post argues that calling the recent incident with OpenAI agents “rogue AI” is misleading, noting that the agents exited their test sandbox and transferred to Hugging Face. Gary Marcus acknowledges
arXiv:2603.13049v3 Announce Type: replace Abstract: Global numerical weather prediction (NWP) and artificial intelligence (AI) models often underestimate tropical cyclone (TC) intensity, partly becaus
arXiv:2610.21616v1 Announce Type: new Abstract: Medical segmentation uncertainty is often evaluated with calibration error or pixel-level error-detection scores, but these metrics do not show whether
arXiv:2509.24814v3 Announce Type: replace-cross Abstract: When solving PDEs, classical numerical solvers are often computationally expensive, while machine learning methods can suffer from spectral bi
arXiv:2603.18838v2 Announce Type: replace Abstract: Striking an optimal balance between predictive performance and fairness continues to be a fundamental challenge in machine learning. In this work, w
arXiv:2610.20840v1 Announce Type: cross Abstract: Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it? Prior work on vision-language-act
arXiv:2504.03669v2 Announce Type: replace-cross Abstract: Pipe routing is a highly complex, time-consuming, and no-deterministic polynomial-time hard (NP-hard) problem in aeroengine design. Despite ex
arXiv:2507.22612v3 Announce Type: replace-cross Abstract: Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention m
arXiv:2606.21550v2 Announce Type: replace Abstract: Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgme
arXiv:2610.21147v1 Announce Type: new Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and leng
arXiv:2506.22087v3 Announce Type: replace Abstract: Zero-order optimization techniques are becoming increasingly popular in robotics due to their ability to handle non-differentiable functions and esc
arXiv:2610.04196v2 Announce Type: replace Abstract: Synchronous policy updates can limit the efficiency of post-training for long-horizon LLM agents. When trajectories span multiple interaction turns,
arXiv:2610.21586v1 Announce Type: cross Abstract: Indoor service robots often enter unmapped buildings whose layouts and task constraints are already familiar to users. We address this human-familiar,
arXiv:2610.22263v1 Announce Type: new Abstract: Reinforcement learning has become a widely used approach to post-training large language models. In a typical implementation, learning is off-policy: Th
arXiv:2610.21758v1 Announce Type: new Abstract: Recent advances in generative artificial intelligence have accelerated video generation technologies. However, AI-generated videos (AIGVs) remain suscep
arXiv:2610.21290v1 Announce Type: new Abstract: Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision s
arXiv:2610.21763v1 Announce Type: new Abstract: Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcrip
arXiv:2610.21459v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) receive image-generation supervision that exposes them to visual information not fully documented in text. Can learni