Knowledge catalogue
arXiv:2603.02883v3 Announce Type: replace Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder ed
arXiv:2605.08034v1 Announce Type: cross Abstract: Distributional treatment effects can be invisible to means: a treatment may preserve average outcomes while changing tails, modes, dispersion, or rare
arXiv:2605.07771v1 Announce Type: new Abstract: Close-proximity offshore wind turbine inspection requires strict clearance control around large cylindrical structures under wind and model mismatch. No
arXiv:2605.06353v2 Announce Type: replace Abstract: In a conversation, a helpful assistant must reliably follow user directives, even as they refine, modify, or contradict earlier requests. Yet most i
Serious question: Should I write a short book called 7 lies about AI that never die? AI hype has become a giant game of bait and switch. the bait: we are going to make an AI that can solve any problem
arXiv:2603.14186v4 Announce Type: replace Abstract: State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or
Socket: Several npm packages for the TanStack web development tools were compromised in the Mini Shai-Hulud supply chain attack; Mistral packages were also affected — - Immediate triage: Run shasum -a
arXiv:2605.07531v1 Announce Type: new Abstract: Black-Box Variational Inference (BBVI) typically relies on Stochastic Gradient Descent (SGD) to optimize the Evidence Lower Bound (ELBO). However, the s
arXiv:2603.24914v2 Announce Type: replace-cross Abstract: Artificial intelligence is transforming mathematics at a speed and scale that demand active engagement from the mathematical community. We exa
arXiv:2605.06822v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationa
arXiv:2605.07338v1 Announce Type: new Abstract: The decline of global shellfish biodiversity poses a severe threat to coastal ecosystems. Although artificial intelligence (AI) technologies show potent
arXiv:2605.07482v1 Announce Type: cross Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous
arXiv:2602.07425v2 Announce Type: replace-cross Abstract: While adaptive gradient methods are the workhorse of modern machine learning, sign-based optimization algorithms such as Lion and Muon have re
arXiv:2605.07276v1 Announce Type: new Abstract: Code-agent RL often receives weak feedback: rollout-time signals are reliable and executable, but capture only necessary or surface conditions for task
arXiv:2605.07711v1 Announce Type: new Abstract: On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and stude
arXiv:2605.07767v1 Announce Type: new Abstract: Poor lighting conditions significantly impact image quality, posing substantial challenges for image editing and visualization. Many existing enhancemen
arXiv:2605.07130v1 Announce Type: new Abstract: Being robust to the presence of outliers is crucial for applying clustering algorithms in practice. In the extit{robust k-Means} problem (i.e., k-Means
Since Hinton has actually replied let me clarify some things - LLMS don’t *always* regurgitate - LLMs don’t literally store full texts - but given the mechanisms that they use they do sometimes regurg
arXiv:2605.06130v2 Announce Type: replace Abstract: A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupl
arXiv:2509.25584v2 Announce Type: replace Abstract: Vision-language models achieve incredible performance across a wide range of tasks, but their large size makes inference costly. Recent work has sho
🧵 Slime: The Most Elegant & Comfortable RL Training Framework Ever A deep dive into why Slime redefines LLM RL training with clean architecture & production-grade engineering ✨ Insights from Zhihu con
arXiv:2603.24755v2 Announce Type: replace-cross Abstract: Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmar
arXiv:2602.03201v3 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) is sample-efficient but struggles in sparse reward settings. A critical bottleneck arises from the lack of
arXiv:2605.07950v1 Announce Type: new Abstract: We study Slowly Annealed Langevin Dynamics (SALD), a sampler for tracking a path of moving target distributions and approximating the terminal target th
arXiv:2605.07001v1 Announce Type: cross Abstract: Architectural code smells erode software maintainability and are costly to repair manually, yet unlike localized bugs, they require cross-module reaso
arXiv:2605.07758v1 Announce Type: cross Abstract: We present an SMT-based active learning algorithm for nondeterministic weighted automata (WFAs) as a practical and robust alternative to Hankel/L*-sty
Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, but fail to consistently improve the user’s position, even with explicit instructions to optimize fo
arXiv:2602.06283v2 Announce Type: replace Abstract: Exploiting sparsity during long-context inference is key to scaling large language models, as attention dominates the cost of autoregressive decodin
arXiv:2605.07725v1 Announce Type: cross Abstract: Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model
Min-Jeong Lee / Bloomberg: SoftBank partners with South Korea's Cosmos Lab and DeltaX to mass produce next-gen data center batteries in Japan at the scale of one GWh per year in FY 2027 — SoftBank Gro
arXiv:2605.06610v2 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both
arXiv:2605.07346v1 Announce Type: new Abstract: Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods
arXiv:2605.07113v1 Announce Type: new Abstract: Exact solution of hard combinatorial optimization problems often relies on strong convex relaxations, but solving these relaxations repeatedly inside a
arXiv:2605.07301v1 Announce Type: new Abstract: Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and g
In a 9-0 Supreme Court decision, Cox Communications prevailed against Sony Music Entertainment in a landmark copyright case decided March 25, 2026, with the Court finding that internet service provide
The Information: Source: new revenue sharing terms cap OpenAI's payments to Microsoft at 38B; they previously could have totaled 135B through 2030 if long-term goals were met — OpenAI Chief Financial
Lucinda Shen / Axios: Source: Robinhood has filed confidentially for its second publicly traded venture fund, Robinhood Venture Fund II, focusing on early-stage startups — Robinhood has filed confiden
Financial Times: Sources: German defense tech startup Helsing is set to raise 1.2B led by Dragoneer and Lightspeed at a valuation of about 18B, up from 14B in June 2025 — German company backed by Spot
The Information: Sources: Kuaishou plans to spin off its Kling AI video unit for an IPO in 2027 and is seeking a $20B valuation in pre-IPO funding talks with potential investors — Chinese social media
Bloomberg: Sources: Masayoshi Son has held talks with French President Emmanuel Macron about unveiling a multibillion-dollar AI data center project in the coming weeks — SoftBank Group Corp. founder M
Berber Jin / Wall Street Journal: Sources: OpenAI facilitated a 6.6B secondary share sale in October 2025 for 600+ current and ex-employees; over 75 people cashed out the maximum cap of 30M — Employee
Washington Post: Sources: the White House's Office of the National Cyber Director and Commerce Department's CAISI are fighting over which agency should lead AI model evaluations — As the White House g
SpaceX has installed a cover on the Marmac 31 barge, a vessel designated to transport Super Heavy Boosters from Starbase to unspecified destinations. The barge, nicknamed 'You'll Thank Me Later,' repr
arXiv:2605.06763v1 Announce Type: new Abstract: Sparse attention improves LLM inference efficiency by selecting a subset of key-value entries, but at the cost of potential accuracy degradation. In par
arXiv:2601.22766v3 Announce Type: replace Abstract: Recent work has revealed a link between self-attention mechanisms in transformers and test-time kernel regression via the Nadaraya-Watson estimator,
arXiv:2605.07447v1 Announce Type: cross Abstract: Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based
arXiv:2605.07286v1 Announce Type: cross Abstract: Random-feature neural networks (RFNNs), including architectures with fixed hidden layers and analytically determined output weights, offer fast traini
arXiv:2603.23198v2 Announce Type: replace-cross Abstract: Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, w
arXiv:2605.07330v1 Announce Type: cross Abstract: In large-scale reinforcement learning (RL) systems with decoupled Trainer-Rollout execution, the Trainer must regularly synchronize policy weights to
Sam Altman comments on OpenAI's new ChatGPT model, noting that the combination of improved capabilities, personality features, and personalization options has crossed an important threshold of functio
arXiv:2605.07243v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters f
arXiv:2605.07870v1 Announce Type: cross Abstract: We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mea
arXiv:2601.22400v2 Announce Type: replace-cross Abstract: We study the problem of learning complex-valued linear dynamical systems (CLDS) with sector-bounded spectrum. This class captures oscillatory
arXiv:2605.07790v1 Announce Type: cross Abstract: The Hessian spectrum of trained deep networks exhibits a characteristic structure: a continuous bulk of near-zero eigenvalues and a small number of la
arXiv:2605.07297v1 Announce Type: cross Abstract: Understanding why trained Transformers generalize well is a fundamental problem in modern machine learning theory, and complexity-based generalization
arXiv:2605.08003v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods
arXiv:2509.05276v4 Announce Type: replace-cross Abstract: Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence
arXiv:2605.07287v1 Announce Type: new Abstract: Generalizable novel view synthesis aims to render unseen views from uncalibrated input images without requiring per-scene optimization. Recent feed-forw
arXiv:2605.07420v1 Announce Type: cross Abstract: Pre-trained models with parameter-efficient fine-tuning (PEFT) have demonstrated promising potential for class-incremental learning (CIL), yet catastr
arXiv:2605.07161v1 Announce Type: new Abstract: AI agents are increasingly used to diagnose and mitigate failures in production systems, known as agentic Site Reliability Engineering (SRE). Current SR