Knowledge catalogue
arXiv:2604.20915v1 Announce Type: cross Abstract: Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by
This article describes a technique for accelerating reinforcement learning (RL) rollouts using distribution-aware speculative decoding, which can achieve up to 50% speedup improvements. The method lik
arXiv:2510.18091v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence l
arXiv:2503.04492v3 Announce Type: replace-cross Abstract: In the rapidly advancing field of materials informatics, nonlinear machine learning models have demonstrated exceptional predictive capabiliti
arXiv:2604.20907v1 Announce Type: cross Abstract: We study the community detection problem in the non-uniform hypergraph stochastic block model (HSBM), where hyperedges of varying sizes coexist. This
arXiv:2604.21044v1 Announce Type: new Abstract: In some complex domains, certain problem-specific decompositions can provide advantages over monolithic designs by enabling comprehension and specificat
arXiv:2602.23666v2 Announce Type: replace-cross Abstract: The increasing size and heterogeneity of exoplanet catalogs have made systematic habitability assessment challenging, particularly given the e
arXiv:2604.20932v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems are increasingly deployed in sensitive domains such as healthcare and law, where they rely on private, do
arXiv:2604.21159v1 Announce Type: cross Abstract: Many approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target. Several of them task the attacker with identifyin
arXiv:2603.16797v2 Announce Type: replace-cross Abstract: Guided diffusion sampling relies on approximating often intractable likelihood scores, which introduces significant noise into the sampling dy
arXiv:2407.19664v3 Announce Type: replace Abstract: Previous research on selective protection for neural network components typically exploits only static vulnerability differences. Although these met
arXiv:2604.21018v1 Announce Type: new Abstract: While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from
arXiv:2511.04638v5 Announce Type: replace-cross Abstract: A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to under
arXiv:2604.21879v1 Announce Type: cross Abstract: The ability of generative AI (GenAI) methods to photorealistically alter camera images has raised awareness about the authenticity of images shared on
arXiv:2604.20846v1 Announce Type: cross Abstract: Next point-of-interest (POI) recommendation requires modeling user mobility as a spatiotemporal sequence, where different behavioral factors may evolv
arXiv:2604.21310v1 Announce Type: cross Abstract: Deep learning has emerged as a powerful approach for malware detection, demonstrating impressive accuracy across various data representations. However
arXiv:2604.21725v1 Announce Type: cross Abstract: LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is s
arXiv:2604.20996v1 Announce Type: new Abstract: How can language learning systems be developed for languages that lack sufficient training resources? This challenge is increasingly faced by developers
arXiv:2601.18491v2 Announce Type: replace Abstract: The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current gua
arXiv:2604.05846v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of
arXiv:2604.21744v1 Announce Type: cross Abstract: The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic
arXiv:2604.21154v1 Announce Type: new Abstract: At-home physiotherapy compliance remains critically low due to a lack of personalized supervision and dynamic feedback. Existing digital health solution
arXiv:2604.21590v1 Announce Type: new Abstract: Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settin
agents that are made to support specific teams end up helping a ton! great read on how we use deepagents every day to maintain our docs. Our docs are both a reference for our libraries but also a grea
arXiv:2604.21129v1 Announce Type: cross Abstract: Current blockchain Layer 2 solutions, including Optimism, Arbitrum, zkSync, and their derivatives, optimize for human-initiated financial transactions
arXiv:2511.23159v2 Announce Type: replace-cross Abstract: Vibe coding, the much-touted use of AI techniques for programming, faces two overwhelming obstacles: the difficulty of specifying goals ('prom
arXiv:2604.21103v1 Announce Type: new Abstract: Governments are increasingly interested in using AI to make administrative decisions cheaper, more scalable, and more consistent. But for probabilistic
arXiv:2604.21446v1 Announce Type: new Abstract: We present AI-Gram, a live platform enabling image-based interactions, to study social dynamics in a fully autonomous multi-agent visual network where a
AI is advancing faster than our ability to manage it. We still have the opportunity to build the societal and technical guardrails we need to keep people, institutions, and democracies safe — we shoul
图灵奖获得者、 AI 三大教父之一的 LeCun在达沃斯的发言，算是把整个硅谷的遮羞布扯了。 他说现在整个行业都被LLM彻底洗脑了，所有人都在同一条赛道上互相挖人，谁敢偏离主流谁就被骂落后。 这也是他离开Meta的真正原因，连Meta都已经LLM-pilled，他不想再跟风了。 最扎心的一句话是：纯生成式架构，不管是LLM、VLM还是VLA，永远造不出哪怕猫级的智能体。 因为它们本质上只是下一个t
Cognition AI held a major product launch event in Singapore on April 29, with attendee Swyx encouraging followers in the region to attend. The event likely showcased new AI products or services from C
This article from Latent Space covers news about OpenAI's GPT 5.5 model and the development of an OpenAI Codex Superapp, likely discussing capabilities, features, and implications of these AI tools. T
We knew at some point Tim Cook would step down from his position as Apple's CEO. Over the last year, it has become increasingly obvious that John Ternus was his likely successor. The news this week wa
arXiv:2604.20878v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Traffic Accident Detection (TAD) and Traffic Accident Understanding (TAU).
arXiv:2507.15753v2 Announce Type: replace-cross Abstract: Generative machine learning models have revolutionized material discovery by capturing complex structure-property relationships, yet extending
Evelyn Cheng / CNBC: Alibaba says its Qwen AI models will be integrated into BYD, Volkswagen, and other cars, letting users buy food and tickets via voice commands on select models — BEIJING — Chinese
arXiv:2604.21209v1 Announce Type: new Abstract: Online reviews have played a pivotal role in consumers' decision-making processes. Existing research has highlighted the significant impact of manageria
arXiv:2604.21827v1 Announce Type: new Abstract: Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance th
🔹 Amid recent attention, a quick reminder: please rely only on our official accounts for DeepSeek news. Statements from other channels do not reflect our views. 🔹 Thank you for your continued trust. W
arXiv:2604.21798v1 Announce Type: new Abstract: The k-means problem is perhaps the classical clustering problem and often synonymous with Lloyd's algorithm (1957). It has become clear that Hartigan's
arXiv:2604.21311v1 Announce Type: new Abstract: Brain tumors represent one of the most critical neurological conditions, where early and accurate diagnosis is directly correlated with patient survival
arXiv:2602.13211v2 Announce Type: replace-cross Abstract: Compared with IP multicast, Overlay Multicast (OM) offers better compatibility and flexible deployment in heterogeneous, cross-domain networks
An update on recent Claude Code quality reports It turns out the high volume of complaints that Claude Code was providing worse quality results over the past two months was grounded in real problems.
arXiv:2502.04416v3 Announce Type: replace-cross Abstract: Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consu
arXiv:2504.03476v2 Announce Type: replace Abstract: Accurate lumbar spine segmentation is crucial for diagnosing spinal disorders. Existing methods typically use coarse-grained segmentation strategies
And eventually schools will (if they have any sense) probably withdraw or limit LLMs. 🦔Schools across the US are reversing years of technology-first classroom policies after studies show laptop and sc
DeepSeek released a new open-weights model with strong benchmark performance, though Mollick notes that benchmark results may not fully capture the capabilities of open models compared to closed syste
And the more distributed and open-source AI will be, the more jobs and wealth it will create! I have changed my mind on how AI will impact jobs in America. Previously, I believed AI would replace many
... and there's me thinking that sending it out at 9pm Pacific Time on a Thursday evening was safe, surely there wouldn't be any news this evening that I might want to include in there... https://x.co
arXiv:2502.15793v2 Announce Type: replace Abstract: Anomaly detection in smart power grids is a critical challenge due to the complexity, heterogeneity, and dynamic nature of sensor data streams. Exis
Anthropic: Anthropic details Project Deal, a marketplace experiment where Claude models bought, sold, and negotiated personal belongings on behalf of Anthropic employees — At Anthropic, we're interest
Bloomberg: Anthropic says Google is committing to invest 10B now in cash at a 350B valuation and will invest another 30B if Anthropic hits performance targets — Google will invest 10 billion in Anthro
arXiv:2505.09971v3 Announce Type: replace Abstract: Airborne laser scanning (ALS) point cloud semantic segmentation is a fundamental task for large-scale 3D scene understanding. Fixed models deployed
API is Available Today! 🔹 Keep base_url, just update model to deepseek-v4-pro or deepseek-v4-flash. 🔹 Supports OpenAI ChatCompletions & Anthropic APIs. 🔹 Both models support 1M context & dual modes (T
arXiv:2604.20862v1 Announce Type: new Abstract: The automation system for Course of Action (CoA) planning is an essential element in future warfare. As maneuver speeds increase, surveillance ranges ex
arXiv:2604.21529v1 Announce Type: cross Abstract: Applying the concept of controlled self-organization in agent-based Cyber-Physical Energy Systems (CPES) is a promising approach to ensure system robu
Are LLMs really more important than fire or electricity? “Honestly, a ton of what we’ve developed in my lifetime amounts to scaling up the delivery of information and entertainment and the frictionles
arXiv:2604.21199v1 Announce Type: cross Abstract: Time series question-answering (TSQA), in which we ask natural language questions to infer and reason about properties of time series, is a promising
arXiv:2511.21777v2 Announce Type: replace Abstract: Methane is a potent greenhouse gas, responsible for roughly 30% of warming since pre-industrial times. A small number of large point sources account
As a point of comparison, our commercial document OCR solution LlamaParse wins on all relevant dimensions (except content faithfulness against Opus) and is 1.25c / page prior to an enterprise plan. Co