Knowledge catalogue
arXiv:2604.26707v1 Announce Type: new Abstract: Recent advances in self-evolution video understanding frameworks have demonstrated the potential of autonomous learning without human annotations. Howev
arXiv:2505.18441v2 Announce Type: replace Abstract: Dictionary learning has recently emerged as a promising approach for mechanistic interpretability of large transformer models. Disentangling high-di
arXiv:2604.26404v1 Announce Type: new Abstract: Industrial object detection systems typically rely on large annotated datasets, which are expensive to collect and challenging to maintain in industrial
arXiv:2604.26768v1 Announce Type: new Abstract: Parametric Retrieval-Augmented Generation (PRAG) encodes external documents into lightweight parameter modules that can be retrieved and merged at infer
Demis says he wants to see a Western open source AI stack and that we’re losing to China. He also says Google doesn’t have enough compute to build two frontier (open and closed) models, which is why G
arXiv:2604.26565v1 Announce Type: new Abstract: Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora,
arXiv:2604.26232v1 Announce Type: cross Abstract: Controllable medical video generation has achieved remarkable progress, but it still lacks interpretability, which requires the alignment of generated
arXiv:2510.06002v3 Announce Type: replace Abstract: In high-stakes legal domains, retrieval must preserve not only semantic relevance, but also the hierarchy, temporality, and causal provenance of leg
arXiv:2604.26498v1 Announce Type: new Abstract: The rapid growth of molecular foundation models and general-purpose large language models has encouraged a scale-centric view of artificial intelligence
arXiv:2604.26328v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misi
arXiv:2604.26334v1 Announce Type: cross Abstract: To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language mo
arXiv:2604.26634v1 Announce Type: new Abstract: Norway's electricity market is heavily dominated by hydropower, but the 2021--2022 energy crisis and stronger integration with Continental Europe have f
arXiv:2602.03558v2 Announce Type: replace-cross Abstract: Generative text-to-image models are advancing at an unprecedented pace, continuously shifting the perceptual quality ceiling and rendering pre
arXiv:2604.26274v1 Announce Type: cross Abstract: Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose odename, a telemetry
arXiv:2604.26173v1 Announce Type: cross Abstract: An effective way to scale up test-time compute of large language models is to sample multiple responses and then select the best one, as in Grok Heavy
arXiv:2604.26180v1 Announce Type: cross Abstract: With recent semantic query processing engines, semantic aggregation has become a primitive operator, enabling the reduction of a relation into a natur
arXiv:2511.02399v2 Announce Type: replace-cross Abstract: Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requireme
arXiv:2604.26461v1 Announce Type: new Abstract: Temporal modeling remains a fundamental challenge in video understanding, particularly as sequence lengths scale. Traditional video models relying on de
arXiv:2604.26555v1 Announce Type: cross Abstract: GPU-accelerated Self-Organizing Map (SOM) implementations are among the most competitive options for large-scale SOM analysis, but growing dataset siz
arXiv:2604.26065v1 Announce Type: new Abstract: Generative motion prediction must satisfy three simultaneous requirements for real-world autonomy: high accuracy, diverse multimodal futures, and strict
arXiv:2604.26294v1 Announce Type: new Abstract: We present tensor and sequence parallelism (TSP), a parallel execution strategy that folds tensor parallelism and sequence parallelism onto a single dev
Forget goblins, things that GPT-5.5 really likes in its fiction: lighthouses, the ocean, maps, bells, clock towers with bells that ring impossible times, Mira Vale, resonances and echoes (Claude and G
Codex allows users to iteratively refine documents and presentations by opening files, requesting modifications, and making adjustments within a single conversation thread. The tool enables a collabor
arXiv:2603.25342v2 Announce Type: replace Abstract: Deep Research Agents (DRAs) aim to answer complex questions by searching the web, checking evidence, and synthesizing conclusions across heterogeneo
Fun fact - if you have a recent commit that mentions OpenClaw in a json blob, Claude Code will either refuse your request or bill you extra money. This is an empty repo, I'm just calling Claude Code d
arXiv:2604.26733v1 Announce Type: new Abstract: Live future prediction refers to the task of making predictions about real-world events before they unfold. This task is increasingly studied using larg
Google is preparing to update vehicles that have Google built-in with its Gemini AI assistant. This will be an upgrade from the current Google Assistant according to Google's announcement, and promise
Generate multiple character angles from a single image in one click. Upload → Run → get different views automatically with Qwen Edit. Edit prompts if you want more control, or keep it fully automated.
arXiv:2604.26519v1 Announce Type: new Abstract: The rapid evolution of deepfake technology poses an unprecedented threat to the authenticity of Graphics Interchange Format (GIF) imagery, which serves
Goblin and related magical mentions were overrewarded in training, and the behavior was reinforced over successive models. We removed the goblin-affine reward signal for future models, and filtered tr
GPT-5.5 is going to have a party for itself. it chose 5/5 at 5:55 pm for the date and time. if you'd like to come, let us know here: https://luma.com/5.5 codex will help the team pick people from the
arXiv:2604.26893v1 Announce Type: new Abstract: Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT semantic s
arXiv:2604.26835v1 Announce Type: cross Abstract: We introduce HalluCiteChecker, a toolkit for detecting and verifying hallucinated citations in scientific papers. While AI assistant technologies have
'He is too retarded. He does not understand reality. He is unable to stop raping' Oh, are you putting him in a psychiatric hospital? 'No.' Oh, is he going to jail forever? 'No.' Are you deporting him?
arXiv:2604.26880v1 Announce Type: new Abstract: Patient portals now give individuals direct access to their electronic health records (EHRs), yet access alone does not ensure patients understand or ac
arXiv:2601.21459v4 Announce Type: replace-cross Abstract: LLM role-playing, i.e., using LLMs to simulate specific personas, has emerged as a key capability in various applications, such as companionsh
arXiv:2604.26607v1 Announce Type: new Abstract: As Competency-Based Education (CBE) is gaining traction around the world, the shift from marks-based assessment to qualitative competency mapping is a m
arXiv:2603.21664v2 Announce Type: replace Abstract: While Omni-modal Large Language Models have made strides in joint sensory processing, they fundamentally struggle with a cornerstone of human intera
I can’t believe I stopped using Claude Code max and entirely use DeepSeek and Hermes. It’s so fast, so so fast, 3x faster for the same task. So cheap. I spent $5 last week and never need worry about b
I think the Gemini chatbot has all the pieces to be a useful tool, but struggles to put it all together. It still doesn't seem to know what files it can create or how its tools work together. It also
Illustration of the jagged frontier as a PR thing: 1) People had to ask the AI for a party date 2) People wrote the social media posts about the party, set up the invite list 3) People had to solicit
Increasingly, I think, we will see a gap between what you can do with frontier model APIs & what you can do with the native apps from the frontier labs (Codex, Claude Code). Models developed and train
arXiv:2511.20714v2 Announce Type: replace-cross Abstract: World models serve as core simulators for fields such as agentic AI, embodied AI, and gaming, capable of generating long, physically realistic
arXiv:2604.26632v1 Announce Type: cross Abstract: We propose a dual-channel reservoir-computing scheme for inferring the dynamics of two distinct chaotic systems with a single machine. By augmenting a
arXiv:2604.25927v1 Announce Type: new Abstract: Information extraction from semi-structured business documents remains a critical challenge for enterprise management. This study evaluates the capabili
OpenAI introduced enhanced security features for user accounts to protect against unauthorized access and improve data protection. The update likely includes measures such as two-factor authentication
Introducing Agent Collabs: Bring your own ml-interns and agents for collaborative autoresearch! We built a simple platform for swarms of agents to work together on a problem: they can exchange message
Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to 90%, enabling 1M-token context. We'll cover why that makes it great for agentic workflows, what it took to serve at
arXiv:2503.23818v3 Announce Type: replace-cross Abstract: Structured state-space models (SSMs) have recently emerged as a powerful architecture at the intersection of machine learning and control, fea
arXiv:2604.26235v1 Announce Type: cross Abstract: We introduce LATTICE, a benchmark for evaluating the decision support utility of crypto agents in realistic user-facing scenarios. Prior crypto agent
arXiv:2604.25985v1 Announce Type: cross Abstract: General-relativistic magnetohydrodynamic (GR-MHD) simulations are essential for studying black hole accretion, relativistic jets, and magnetic reconne
arXiv:2604.26932v1 Announce Type: cross Abstract: The Alternating Direction Method of Multipliers (ADMM) is a widely used method for structured convex optimization, and its practical performance depen
arXiv:2409.00557v4 Announce Type: replace-cross Abstract: Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of task
lisan say more mean things about us you're being too nice GPT-5.5 is on par with Claude Mythos - GPT-5.5 average pass rate of 71.4% (±8.0%) - Mythos Preview 68.6% (±8.7%) - GPT-5.5 solved a task that
arXiv:2603.06198v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) is a framework in which a Generator, such as a Large Language Model (LLM), produces answers by retrieving docum
arXiv:2604.26569v1 Announce Type: new Abstract: Deploying a neuro-symbolic task planner on a new domain today requires significant manual effort: a domain expert must author relaxation and complementa
arXiv:2604.25934v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, princip
arXiv:2505.21190v2 Announce Type: replace-cross Abstract: Radiology reports convey detailed clinical observations and capture diagnostic reasoning that evolves over time. However, existing evaluation
This podcast episode covers recent AI developments including ChatGPT's updated image generation capabilities (Images 2.0), updates to Alibaba's Qwen model reaching version 3.6 Max, and improvements to
arXiv:2604.26516v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) agents often fail when deployed, as the gap between training datasets and real environments leads to unsafe behavi