All entries

arXiv:2606.30012v1 Announce Type: new Abstract: Volume microscopy, including electron and light microscopy, suffers from severe anisotropic resolution due to physical axial sectioning. Existing self-s

AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavio

arXiv:2511.14900v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) have recently shown promise for assisting clinical reasoning in dermatological diagnosis. However, their trustw

arXiv:2602.18431v2 Announce Type: replace-cross Abstract: Motivated by the problem of assigning mediators to cases in the Kenyan judicial system, we study an online resource allocation problem where i

arXiv:2606.29858v1 Announce Type: new Abstract: Language model loss follows remarkably regular scaling laws over model and data size, yet it remains unclear why the aggregate loss should exhibit a pow

arXiv:2606.28389v1 Announce Type: new Abstract: We present our submission to the SoccerNet 2026 Player-Centric Ball Action Spotting challenge, which uses a two-stage pipeline: a Track-Aware Action Det

Israeli startup Arato Software Ltd. is developing tools for developers to test and evaluate their artificial intelligence applications, and it has just gotten 10 million in seed funding to pursue that

arXiv:2510.18989v2 Announce Type: replace Abstract: Neural operators are commonly utilized as fast surrogates for numerical solvers in PDE problems, mapping input functions to solution functions. Howe

arXiv:2606.29366v1 Announce Type: cross Abstract: Balance-oriented multi-warehouse inventory allocation is a recurring decision problem in large-scale e-commerce supply chains, in which a fixed replen

“Sometimes I wonder, maybe everything is conscious, or nothing is conscious. I prefer the former; it just seems more fun.” – Elon Musk Media Neuralink has solved through-dura electrode implantation! T

Sonnet 5 is here! This is going to support better long-running agents. Previous Sonnet models were unreliable, so it's great to see the improved version that can complete agentic tasks more reliably.

arXiv:2606.29586v1 Announce Type: cross Abstract: Vision-language foundation models have shown strong potential in medical image analysis. Although foundation models for ultrasound imaging have recent

arXiv:2602.23353v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model

Stephanie Palazzolo / The Information: Source: OpenAI engineers earlier this month told some colleagues they had figured out a way to more than halve the cost of inference — We closely track efforts b

Nikkei Asia: Sources: Chinese smartphone makers like Xiaomi, Oppo, and Vivo told suppliers they will again cut 2026 shipment targets, with Xiaomi cutting 30% to ~95M units — TAIPEI — Major Chinese sma

Bloomberg: Sources: Kalshi agreed to pay 20M to sponsor the World Cup knockouts, after initially balking at FIFA's 150M asking price, alongside ADI Predictstreet — When the World Cup knockout round be

Bobby Allyn / NPR: Sources: Mark Zuckerberg met with Kalshi CEO Tarek Mansour about a possible takeover last year, before directing Meta employees to build a prediction market app — Before Meta CEO Ma

Ashley Stewart / Business Insider: Sources: Microsoft plans to announce job cuts next week affecting less than 2.5% of its 220,000-person workforce, including roles in sales, consulting, and Xbox — -

Politico: Sources: the Trump administration plans to lift export restrictions on Anthropic's Fable 5 as early as Tuesday evening, making it available to all general users — Anthropic and the administr

Bloomberg: Sources: TikTok settles a lawsuit before a second California trial over social media harm to minors for an undisclosed sum; Meta and Snap remain defendants — TikTok is finalizing a settleme

arXiv:2606.29322v1 Announce Type: new Abstract: Collaborative learning is sustainable only when it benefits each participant. Standard federated learning optimizes a global average objective, which ca

Rocket Lab Corp. today announced plans to acquire Iridium Communications Inc., a major satellite operator, for 8 billion in cash and stock. The companies expect to complete the transaction in mid-2027

arXiv:2606.29372v1 Announce Type: new Abstract: Massive robot swarms can explore unknown environments quickly, but adding robots eventually stops helping. Doorways and dense traffic create congestion,

Carmen Arroyo / Bloomberg: SpaceX cuts monthly Starlink prices in half in the Memphis area, as it endures blowback and legal challenges from opponents of its Colossus data centers — SpaceX is offering

SpaceXAI has become a major force for good in Memphis and surrounding communities. • SpaceXAI’s expansion is projected to push local tax revenue above 100 million • Employs almost 3,000 people locally

arXiv:2602.15727v2 Announce Type: replace-cross Abstract: Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformat

arXiv:2412.04739v2 Announce Type: replace Abstract: Deep learning models exhibit fairness concerns when predictions are inadvertently influenced by sensitive attributes. However, existing attempts to

arXiv:2602.02472v2 Announce Type: replace-cross Abstract: Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively ex

arXiv:2602.12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-

arXiv:2512.06208v3 Announce Type: replace-cross Abstract: Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep n

arXiv:2510.08762v2 Announce Type: replace Abstract: Causal inference in spatial domains faces two intertwined challenges: (1) unmeasured spatial factors, such as weather, air pollution, or mobility, t

arXiv:2606.29162v1 Announce Type: new Abstract: Self-supervised learning (SSL) currently drives state-of-the-art performance in no-reference image quality assessment (NR-IQA). However, standard SSL pi

Speaking at @aiDotEngineer today about long-horizon RL and the different tradeoffs involved. 2:25pm. Also here in SF for a week if anyone wants to catchup 👋 Excited to be speaking at @aiDotEngineer Wo

Special new @latentspacepod live recording added to the Expo schedule on Thursday, with @swyx and @robertwachen alongside his Inference track appearance! congrats to Etched on a massive milestone! We'

arXiv:2602.20610v3 Announce Type: replace-cross Abstract: Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large lang

arXiv:2512.09165v2 Announce Type: replace Abstract: Deep Operator Networks (DeepONets) have emerged as a powerful framework for data-driven operator learning, providing flexible surrogates for nonline

arXiv:2606.28432v1 Announce Type: cross Abstract: We study the spectral perturbation of the empirical Fisher Information Matrix (FIM) of a parametric statistical model under two structured perturbatio

arXiv:2606.28486v1 Announce Type: cross Abstract: The emergence of low-dimensional structures in the spectra of neural network weight matrices is a common empirical feature of trained models, but the

arXiv:2606.29565v1 Announce Type: new Abstract: A stateless inference server (vLLM, SGLang, TensorRT-LLM) idles between requests while the accelerator waits; a stateful session reclaims that idle time

arXiv:2606.29910v1 Announce Type: new Abstract: Multi-camera visual-inertial odometry (VIO) overcomes the inherent limitations of pure visual systems by expanding the field of view. However, existing

arXiv:2606.29955v1 Announce Type: cross Abstract: Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks

arXiv:2606.29815v1 Announce Type: new Abstract: Evaluating code large language models (Code LLMs) requires reliable detection of data leakage, where benchmark performance is artificially inflated by e

arXiv:2510.12784v2 Announce Type: replace-cross Abstract: Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding

arXiv:2510.04961v2 Announce Type: replace Abstract: Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing da

arXiv:2403.07711v5 Announce Type: replace-cross Abstract: Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extend

arXiv:2602.09415v2 Announce Type: replace Abstract: We develop an operator-theoretic framework for stability and statistical concentration in nonlinear inverse problems with block-structured parameter