Knowledge catalogue
arXiv:2605.21168v1 Announce Type: new Abstract: Safety-critical scenarios are central to evaluating autonomous driving systems, yet their rarity in naturalistic logs makes simulation-based stress test
arXiv:2605.22693v1 Announce Type: new Abstract: Autonomous robot teams navigating partially known environments face costly backtracking when ground robots encounter blocked roads that are only reveale
arXiv:2605.21919v1 Announce Type: new Abstract: Assessing progress toward the Sustainable Development Goals (SDGs) requires multi-step reasoning over visual cues, contextual knowledge, and development
arXiv:2605.22633v1 Announce Type: new Abstract: The Python robotics ecosystem faces a challenge: while many libraries exist for rigid body transformations, few are both lightweight and mathematically
arXiv:2605.22511v1 Announce Type: cross Abstract: Post-training has become the dominant recipe for turning a language model into a competent search-augmented reasoning agent. A line of recent work pus
This Replit broadcast covers security best practices for Vibe-coded applications and introduces new features or updates to the Connectors system, likely including integration improvements and enhanced
arXiv:2605.20368v1 Announce Type: cross Abstract: Organizations that scan documents for sensitive information face a practical problem. Cloud services require data to be sent to external infrastructur
arXiv:2605.22654v1 Announce Type: new Abstract: Previous detection studies have shown that LLMs cannot be effectively used as detectors, but these studies have not addressed modern Chinese poetry. Mor
arXiv:2605.22668v1 Announce Type: new Abstract: Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resol
arXiv:2605.22658v1 Announce Type: new Abstract: While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoni
arXiv:2605.22572v1 Announce Type: new Abstract: Accurate segmentation of brain tumour sub-regions from multi-parametric MRI is critical for treatment planning yet remains challenging due to morphologi
arXiv:2605.22538v1 Announce Type: new Abstract: Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects an
arXiv:2605.21852v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in general video understanding, their capacity to interpret invo
arXiv:2605.22675v1 Announce Type: new Abstract: Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signal
arXiv:2605.21713v1 Announce Type: new Abstract: How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not b
arXiv:2506.14648v2 Announce Type: replace Abstract: Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human prefe
arXiv:2605.22809v1 Announce Type: new Abstract: Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (
Artificial intelligence startups are facing two massive headaches: There’s too much AI-generated code to deal with, and not nearly enough computing power to run it all on. Modal Labs Inc., which has j
arXiv:2509.17086v2 Announce Type: replace Abstract: Detecting and localizing poultry is essential for advancing smart poultry farming. Despite the progress of detection-centric methods, challenges per
arXiv:2602.08064v2 Announce Type: replace-cross Abstract: The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off b
arXiv:2602.23231v2 Announce Type: replace Abstract: Human action recognition plays an important role when developing intelligent interactions between humans and machines. While there is a lot of activ
arXiv:2605.22677v1 Announce Type: new Abstract: Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery s
arXiv:2605.22031v1 Announce Type: new Abstract: Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State
US solar generation surged 35% in 2025 with 27 gigawatts of newly installed capacity, surpassing hydroelectric power for the first time in annual generation. Solar's expansion added roughly 85 terawat
software security is a hot topic right now timely podcast with @cogent_security on building agents for cyber defense Great conversation on the Max Agency podcast with @cogent_security Co-Founder + CTO
This post discusses a feature or workflow preference for managing terminal or development sessions by opening them in separate windows rather than keeping them in tabs or panes within a single window,
arXiv:2511.07820v3 Announce Type: replace-cross Abstract: Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humano
Ashley Stewart / Business Insider: Sources and documents detail Satya Nadella's effort to revamp Microsoft's senior leadership, creating a startup-style operating model to compete in the AI race — CEO
Politico: Sources: David Sacks told President Trump that federal reviews of AI models before release would slow down innovation and hurt the US in its AI race with China — But during a conversation wi
Washington Post: Sources: last-minute calls with Elon Musk, Mark Zuckerberg, David Sacks, and others helped persuade President Trump not to sign the highly anticipated AI EO — Industry leaders warned
Takashi Mochizuki / Bloomberg: Sources: Nintendo asked partners and suppliers to assemble ~20M Switch 2 consoles by March 2027, ~20% above the 16.5M public sales outlook issued in early May — Nintendo
Scott Patterson / Bloomberg: Sources: the SEC has delayed the release of a plan for an “innovation exemption” that would allow crypto firms to trade tokenized versions of US stocks — The Securities an
New York Times: Sources: WH approved a $9B request to acquire advanced AI chips for spy agencies; Anthropic is finalizing a classified contract for NSA to keep using its tools — The C.I.A. and N.S.A.
arXiv:2605.22536v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pr
arXiv:2512.10719v2 Announce Type: replace Abstract: End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual under
SpaceX has just launched and deployed ~45 tons to space. This was one of the heaviest payloads since Polyus launched by Energia in 1987 and Skylab launched by Saturn V in 1973! Starship has successful
SpaceX has achieved a milestone where it launches more rockets than all other countries combined, marking an unprecedented moment in spaceflight history. This represents a significant shift in the com
A SpaceX team was recorded chanting 'USA! USA! USA!' in what appears to be a celebratory moment, likely following a successful rocket launch or space mission achievement. The post was shared on X (for
arXiv:2605.22283v1 Announce Type: new Abstract: We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly ass
arXiv:2605.21965v1 Announce Type: new Abstract: Large language models increasingly use external tools such as web search and document retrieval to solve information-intensive tasks. However, multi-hop
This article argues that specialized AI models often outperform larger, general-purpose models for specific use cases, challenging the common procurement assumption that bigger is always better. It li
arXiv:2605.22751v1 Announce Type: new Abstract: As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection
arXiv:2603.08403v3 Announce Type: replace Abstract: Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended
SpaceX successfully completed the twelfth flight test of Starship, with the vehicle achieving splashdown as planned. This milestone represents continued progress in SpaceX's development of the fully r
AI covers and remixes of songs are already a blight on the internet. Spotify, YouTube, TikTok, and Instagram are awash in flat reggae versions of 'Smells Like Teen Spirit,' dinky country renditions of
arXiv:2605.22158v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual token
arXiv:2605.21800v1 Announce Type: cross Abstract: World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is cur
Starlink enables reliable real-time communication with recovery teams and live streaming of Starship’s splashdown in the middle of the Indian Ocean The Starship recovery team is deployed in one of the
This article from Zero Hedge criticizes the UK Starmer government's policies regarding free speech restrictions, suggesting the administration is intensifying its enforcement or expansion of speech-li
During a test flight, Starship executed a banking maneuver designed to simulate the final approach trajectory it would use when returning to Starbase for a booster catch in future missions. This maneu
Elon Musk announced an imminent Starship launch attempt via X, indicating a SpaceX test flight was scheduled to begin within five minutes of the post. This represents one of SpaceX's integrated flight
arXiv:2605.21405v1 Announce Type: cross Abstract: Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natur
arXiv:2605.22456v1 Announce Type: new Abstract: Cloud-hosted LLM driver agents provide useful semantic judgments, but their inference latency exceeds stepwise vehicle-control windows. Learned world mo
'Strawberry' was OpenAI's internal code word for the extended reasoning capabilities featured in the o1-preview model, which enables the AI to work through complex problems with longer chains of thoug
arXiv:2507.03674v3 Announce Type: replace Abstract: Extracting structured information from scientific literature is critical for accelerating discovery, yet Large Language Models (LLMs) often struggle
arXiv:2601.20107v2 Announce Type: replace-cross Abstract: Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index sto
arXiv:2605.22202v1 Announce Type: new Abstract: In this paper, we show that high-performing embedding models organize their embedding spaces in a consistent way. We evaluate 25 contemporary embedding
arXiv:2605.22476v1 Announce Type: cross Abstract: Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operat
arXiv:2511.04106v5 Announce Type: replace-cross Abstract: The diffusion of ideas and language in society has conventionally been described by S-shaped models, such as the logistic curve. However, the
arXiv:2605.22748v1 Announce Type: new Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This f