Knowledge catalogue
arXiv:2605.27298v1 Announce Type: new Abstract: Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digit
arXiv:2605.26690v1 Announce Type: cross Abstract: Protein sequence optimization under tight oracle budgets requires methods that explore vast combinatorial spaces while making each evaluation informat
Yohei Nakajima discusses the emergence of self-improving AI agents, likely exploring how autonomous agents can iteratively enhance their capabilities and performance through feedback loops and learnin
arXiv:2605.26744v1 Announce Type: new Abstract: Human motion generation has made tremendous progress in recent years, with state-of-the-art approaches surpassing ground truth data in leading evaluatio
arXiv:2510.06843v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Age
arXiv:2605.26132v1 Announce Type: new Abstract: Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools?
arXiv:2605.27322v1 Announce Type: new Abstract: We introduce interaction SSD, an extension of Supervised Semantic Differential that models how semantic meaning varies across moderators such as groups,
arXiv:2605.27155v1 Announce Type: cross Abstract: Testing object detectors in safety-critical domains requires semantically meaningful probes beyond pixel-level corruptions. We present SemProbe, a too
arXiv:2605.27080v1 Announce Type: new Abstract: Appearance-based gaze estimation always suffers from poor generalization due to limited annotated samples and insufficient dataset diversity. Leading ap
arXiv:2605.26324v1 Announce Type: cross Abstract: Learned physics simulators are often evaluated by one-step or short-horizon prediction error, but these metrics can miss failures in temporal composit
arXiv:2605.26239v1 Announce Type: new Abstract: In this work, we study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate effectively under dynamic environmen
arXiv:2605.26571v1 Announce Type: new Abstract: Federated learning enables collaborative model training without sharing raw data, but its performance can degrade substantially under heterogeneous clie
arXiv:2605.27294v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems can respond incorrectly even when the correct passage was retrieved. The model must still read the retrieve
arXiv:2605.26186v1 Announce Type: cross Abstract: Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a reposito
arXiv:2601.04275v2 Announce Type: replace-cross Abstract: Machine unlearning aims to selectively remove the influence of specific training samples to satisfy privacy regulations such as the GDPR's 'Ri
arXiv:2605.27030v1 Announce Type: new Abstract: Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution
arXiv:2509.15121v2 Announce Type: replace-cross Abstract: We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the Z_3-sym
Delta Weight Sync (DWS) is a technique for efficiently distributing and synchronizing large language models with trillions of parameters across distributed systems using Hugging Face's TRL (Transforme
arXiv:2603.14864v2 Announce Type: replace Abstract: In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budget management, and bundle deals, where accurately capturing u
arXiv:2605.27276v1 Announce Type: new Abstract: Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The l
arXiv:2605.26973v1 Announce Type: cross Abstract: Neural networks are known to develop latent representations that are aligned, namely structurally similar across networks trained with different archi
arXiv:2605.26509v1 Announce Type: new Abstract: Gaussian processes (GPs) provide a principled Bayesian framework for uncertainty estimation, but their computational complexity severely limits scalabil
arXiv:2605.26135v1 Announce Type: new Abstract: Unsupervised anomaly detection is widely used in transaction fraud detection where labels are scarce. Isolation Forest (IF) is among the most popular cl
arXiv:2605.26894v1 Announce Type: new Abstract: In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction
arXiv:2512.14140v2 Announce Type: replace Abstract: Sketch editing requires jointly handling high-level semantic changes and precise local redrawing, a combination that is particularly challenging for
arXiv:2605.26704v1 Announce Type: cross Abstract: Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread, creating feedback loops that induce distrib
arXiv:2605.26295v1 Announce Type: new Abstract: Accurate classification of sleep stages is crucial for diagnosing sleep disorders and automating this process can significantly enhance clinical assessm
arXiv:2605.26428v1 Announce Type: new Abstract: Generating high-quality, pedagogically useful questions from lecture slide decks is difficult because important instructional content is distributed acr
arXiv:2605.26884v1 Announce Type: new Abstract: In this paper, we address the problem of detecting small, dense, and overlapping objects, a major challenge in computer vision. Our focus is on reviewin
CNBC: Snowflake reports Q1 revenue up 33% YoY to 1.39B, vs. 1.32B est., and commits to spending 6B on AWS over five years; SNOW jumps 35%+ after hours — Amazon said Wednesday that its cloud division h
Snowflake Inc.’s shares jumped in late trading today after it announced a $6 billion spending commitment on Amazon Web Services Inc.’s cloud infrastructure, including a deal to use the company’s custo
arXiv:2605.27075v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve strong visual quality, but their iterative denoising process requires many costly Transformer evaluations. Trainin
arXiv:2603.28730v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervis
some data i shared yesterday on anthropic revenue possibly slowing down aren’t as a compelling as i thought; i have deleted my posts and await better data before drawing conclusions. h/t @GergelyOrosz
Someone just asked me “What I don’t get is why you see it as some kind of failure that AI labs are now using harnesses and neurosymbolic tools…?” I don’t! As I argued in my newsletter on Claude Code (
arXiv:2508.05305v2 Announce Type: replace Abstract: The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-s
Bloomberg: Source: at a town hall, TSMC CEO C.C. Wei told staff they will see a 30%+ bump in their profit-sharing payouts in 2026 on average, after some staff had concerns — Taiwan Semiconductor Manuf
arXiv:2601.08375v2 Announce Type: replace Abstract: Semantic segmentation of 3D geospatial point clouds is fundamental to remote sensing applications, yet domain shifts caused by regional and acquisit
Bloomberg: Sources: ByteDance is discussing capex of up to 70B in 2026 as it builds out data centers and AI infrastructure, underwriting it with its 50B profit from 2025 — ByteDance Ltd., the develope
Foo Yun Chee / Reuters: Sources: EU leaders are divided on curbing Big Tech as they weigh cloud tender rules and giving EU companies preferential access to mobile satellite spectrum — European leaders
Bloomberg: Sources: Germany and Spain are leading opposition to EU plans to ban Chinese suppliers like Huawei from telecom networks as part of new cybersecurity rules — Germany and Spain are leading o
Financial Times: Sources: software-specialist PE firm Hg agrees to acquire Rightsline, whose software helps Disney, the BBC, WBD, and others manage IP licensing, for 500M — Acquisition of rights and r
Bloomberg: Sources: Taiwan suspects three people smuggled at least one Nvidia chip shipment to China after first exporting them to Japan; Taiwan detained them last week — Taiwan prosecutors suspect th
Financial Times: Sources: Uber has increased its stake in Delivery Hero to ~37% by acquiring Aspex Management's 14.6% share at a €12B valuation, after a takeover offer last week — Share purchase from
arXiv:2510.09606v2 Announce Type: replace Abstract: With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still strug
arXiv:2605.26456v1 Announce Type: new Abstract: Sparse-LiDAR-prompted depth foundation models (PromptDA, Prior Depth Anything, DMD3C) have shown strong results on indoor scenes or within KITTI's stand
arXiv:2605.27367v1 Announce Type: new Abstract: While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round pla
arXiv:2605.26275v1 Announce Type: new Abstract: Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed
arXiv:2506.08543v3 Announce Type: replace Abstract: High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circu
arXiv:2605.26606v1 Announce Type: cross Abstract: Reinforcement learning (RL) is the dominant paradigm for post-training large language models. However, in the online, on-policy setting, rollout gener
arXiv:2605.26900v1 Announce Type: new Abstract: A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. R
arXiv:2605.27027v1 Announce Type: new Abstract: The scaling of quantum processors is currently limited by technical challenges such as decoherence and cross-talk. As the number of qubits grows, interf
sqlite AGENTS.md SQLite gained an AGENTS.md file five days ago - but it's not intended for their own development, it's presumably aimed at people who are pointing agents at the SQLite codebase. It inc
arXiv:2604.18103v2 Announce Type: replace Abstract: Prefilling computational costs pose a significant bottleneck for Large Language Models (LLMs) and Large Multimodal Models (LMMs) in long-context set
arXiv:2605.26733v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: perfor
Starbucks learned the hard way: you literally can’t even trust (current) AI to count. For some reason OpenAI doesn’t seem to be talking about how Starbucks spent years creating and testing an AI inven
Dan Goodin / Ars Technica: Starlette, an open-source Python framework underpinning FastAPI, has a vulnerability called BadHost that can allow hackers to bypass authorization — Millions of AI agents an
arXiv:2605.26289v1 Announce Type: new Abstract: Multi-agent tool calling is becoming the dominant interaction pattern for LLM-based systems, yet existing inference frameworks treat each tool call as a
arXiv:2605.26682v1 Announce Type: cross Abstract: This dataset provides high-resolution, annotated video sequences of shredded E40-grade steel and copper scrap on a conveyor belt. Captured in a contro
arXiv:2602.09842v2 Announce Type: replace-cross Abstract: We present a theoretical analysis of stochastic optimization methods in terms of their sensitivity with respect to the step size. We identify