Knowledge catalogue
arXiv:2604.06942v1 Announce Type: cross Abstract: Ensuring ciphertext indistinguishability is fundamental to cryptographic security, but empirically validating this property in real implementations an
arXiv:2604.06793v1 Announce Type: cross Abstract: Software documentation is crucial for repository comprehension. While Large Language Models (LLMs) advance documentation generation from code snippets
arXiv:2604.07378v1 Announce Type: new Abstract: Autonomous vehicles in interactive traffic environments are often limited by the scarcity of safety-critical tail events in static datasets, which biase
arXiv:2604.07392v1 Announce Type: cross Abstract: Autonomous agents operating in dynamic and safety-critical environments require decision-making frameworks that are both computationally efficient and
arXiv:2604.07577v1 Announce Type: new Abstract: Reliable monitoring of surgical instrument exchanges is essential for maintaining procedural efficiency and patient safety in the operating room. Automa
arXiv:2503.23078v3 Announce Type: replace Abstract: Large language models have improved dialogue systems, but often process conversational turns in isolation, overlooking the event structures that gui
Every single one of these ads was made by one person. That’s insane, see the thread. Six months ago, that would have been impossible to say. The level of craft, story, and quality is quite impressive.
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:2604.07070v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, their potential for purpose-driven exploration in dynamic geo-spatial
arXiv:2604.06172v1 Announce Type: cross Abstract: Cold-start cross-domain recommender (CDR) systems predict a user's preferences in a target domain using only their source-domain behavior, yet existin
arXiv:2603.11703v2 Announce Type: replace Abstract: We introduce EvoFlows, a variable-length protein sequence-to-sequence modeling approach designed for protein engineering. Existing protein language
arXiv:2604.08258v1 Announce Type: new Abstract: In the automated co-design of soft robots, precisely adapting the material stiffness field to task environments is crucial for unlocking their full phys
arXiv:2601.16074v2 Announce Type: replace Abstract: Industrial Cyber-Physical Systems (CPS) are sensitive infrastructure from both safety and economics perspectives, making their reliability criticall
arXiv:2604.06559v1 Announce Type: cross Abstract: Understanding and explaining the structure of generated test inputs is essential for effective software testing and debugging. Existing approaches--in
arXiv:2604.06838v1 Announce Type: new Abstract: In this paper, we propose using Learning from Answer Sets to approximate black-box models, such as Neural Networks (NN), in the specific case of learnin
arXiv:2410.08334v2 Announce Type: replace-cross Abstract: In this paper, we build a reinforcement learning framework to study how children compose numbers using base-ten blocks. Studying numerical cog
arXiv:2603.02070v2 Announce Type: replace-cross Abstract: When automating plan generation for a real-world sequential decision problem, the goal is often not to replace the human planner, but to facil
arXiv:2604.08418v1 Announce Type: new Abstract: Inspired by the human ability to understand and predict others, we study the applicability of Conditional Neural Processes (CNP) to the task of self-sup
arXiv:2604.06208v1 Announce Type: cross Abstract: A significant amount of data held in Oncology Electronic Medical Records (EMRs) is contained in unstructured provider notes -- including but not limit
arXiv:2604.06732v1 Announce Type: new Abstract: Recent developments in hardware, such as photonic integrated circuits and optical devices, are driving demand for research on constructing machine learn
F1's 2026 power unit regulations introduced a true 50/50 hybrid split between the internal combustion engine and the electric motor (MGU-K), while eliminating the MGU-H entirely — a change that has...
arXiv:2604.08159v1 Announce Type: new Abstract: The rapid advancement of facial forgery techniques poses severe threats to public trust and information security, making facial DeepFake detection a cri
arXiv:2603.16570v2 Announce Type: replace Abstract: Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models
arXiv:2604.08535v1 Announce Type: cross Abstract: Generalization under distribution shift remains a central bottleneck for closed-loop autonomous driving. Although simulators like CARLA enable safe an
arXiv:2511.08409v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) frequently suffer from unfaithfulness, generating reasoning chains that drift from visual evidence or contr
arXiv:2604.08476v1 Announce Type: new Abstract: Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchma
arXiv:2512.24290v2 Announce Type: replace-cross Abstract: Optical-readout Time Projection Chambers (TPCs) produce megapixel-scale images whose fine-grained topological information is essential for rar
arXiv:2604.07350v1 Announce Type: cross Abstract: Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates rem
Thomas Wolf, co-founder and Chief Science Officer of Hugging Face, shared a post describing his experience 'vibe coding' robot behaviors collaboratively with a Reachy Mini robot — an open-source d...
arXiv:2601.21708v2 Announce Type: replace Abstract: Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing accelerat
Sam Altman's tenure at OpenAI has been… messy. Messy to the point where Altman was briefly fired from his role as CEO, only to be reinstated days later, at which point he began reshaping the organizat
arXiv:2604.06795v1 Announce Type: cross Abstract: Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data, making it ideal for privacy-sensit
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:2604.06297v1 Announce Type: cross Abstract: Given the growing reliance on private data in training Large Language Models (LLMs), Federated Learning (FL) combined with Parameter-Efficient Fine-Tu
arXiv:2604.07997v1 Announce Type: new Abstract: Incremental 3D object perception is a critical step toward embodied intelligence in dynamic indoor environments. However, existing incremental 3D detect
arXiv:2604.02360v1 Announce Type: cross Abstract: The transformative potential of large language models (LLMs) in education, such as improving accessibility and personalized learning, is being eclipse
I was unable to retrieve the specific content of the X/Twitter post at the URL provided (status ID 2042636279482061058). The X/Twitter platform requires JavaScript and user login to display individ...
Finally some good news from @simonw: The Kākāpō parrots of New Zealand are having a fantastic breeding season. Media 'Using coding agents well is taking every inch of my 25 years of experience as a so
The OpenAI Academy Financial Services page covers how ChatGPT can be applied across core financial workflows. Finance teams can leverage ChatGPT to accelerate financial analysis, automate routine d...
arXiv:2604.06723v1 Announce Type: cross Abstract: In today's AI-assisted software engineering landscape, developers increasingly depend on LLMs that are highly capable, yet inherently imperfect. The t
Replit has introduced a Tax Skill, an AI-powered tool designed to assist users with tax-related questions and guidance during tax season. The skill likely leverages Replit's AI agent capabilities to h
arXiv:2406.12009v5 Announce Type: replace Abstract: Accurate and transparent financial information disclosure is essential for market efficiency, investor decision-making, and corporate governance. Ch
In the early morning hours of April 10, 2026, a 20-year-old suspect threw a Molotov cocktail at OpenAI CEO Sam Altman's San Francisco residence; the device ignited an exterior gate before self-exti...
arXiv:2604.07675v1 Announce Type: new Abstract: Accurate prediction of next-day wildfire spread is critical for disaster response and resource allocation. Existing deep learning approaches typically c
First (supervised) FSD approval in Europe! Congratulations to the Tesla team and thank you to the regulatory authorities in the Netherlands for all the hard work required to make this happen. De toeko
NASA's Artemis II mission — a nine-day lunar flyby that launched April 1, 2026, and the first crewed flight beyond low Earth orbit since Apollo 17 in 1972 — successfully concluded when the crew ...
arXiv:2604.08526v1 Announce Type: new Abstract: Given a person and a garment image, virtual try-on (VTO) aims to synthesize a realistic image of the person wearing the garment, while preserving their
arXiv:2408.09369v3 Announce Type: replace-cross Abstract: As the rapid development of computer vision and the emergence of powerful network backbones and architectures, the application of deep learnin
arXiv:2604.06253v1 Announce Type: cross Abstract: Cross-lingual code generation is critical in enterprise environments where multiple programming languages coexist. However, fine-tuning large language
arXiv:2604.08275v1 Announce Type: new Abstract: Metaphor pervades everyday language, allowing speakers to express abstract concepts via concrete domains. While prior work has studied metaphors cogniti
Florida’s Attorney General James Uthmeier announced today that his office will open a probe into OpenAI Group PBC over a number of concerns including alleged harm to children, threats to national secu
arXiv:2604.07084v1 Announce Type: cross Abstract: Open-loop end-to-end neural motion planners have recently been proposed to improve motion planning for robotic manipulators. These methods enable plan
arXiv:2604.06652v1 Announce Type: new Abstract: Adaptive moment methods such as Adam use a diagonal, coordinate-wise preconditioner based on exponential moving averages of squared gradients. This diag
arXiv:2604.06770v1 Announce Type: cross Abstract: Maintenance procedures in manufacturing facilities are often documented as flowcharts in static PDFs or scanned images. They encode procedural knowled
arXiv:2604.07879v1 Announce Type: new Abstract: Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content
arXiv:2604.07394v1 Announce Type: cross Abstract: The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. W
A 2-stage upscaling workflow using FLUX.2 Klein in ComfyUI combines the model's image-editing capabilities with a secondary upscaler (such as SeedVR2) to produce high-resolution outputs — for examp...
arXiv:2604.06403v1 Announce Type: cross Abstract: The paper presents an approach for the recognition of toxic habits named entities in Spanish clinical texts. The approach was developed for the ToxHab
For anyone building agentic workflows: the real bottleneck isn't the model, it's the harness. Open standards are a must, not just for flexibility, but to ensure we actually own the long-term memory th
arXiv:2603.04038v2 Announce Type: replace Abstract: Imitation learning (IL) has shown strong potential for contact-rich precision insertion tasks. However, its practical deployment is often hindered b