Knowledge catalogue
arXiv:2605.12026v1 Announce Type: new Abstract: We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline
Spend less time on triaging Ship fixes faster Catch regressions earlier Introducing LangSmith Engine: an agent that works autonomously to find patterns in your agent's failures 💻 Accelerate the agent
arXiv:2605.12000v1 Announce Type: new Abstract: This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from mul
arXiv:2605.11060v1 Announce Type: cross Abstract: Split Federated Learning (SplitFed) combines federated and split learning to preserve privacy while reducing client-side computation. However, in medi
arXiv:2605.11134v1 Announce Type: new Abstract: Preference learning methods such as Direct Preference Optimization (DPO) are known to induce reliance on spurious correlations, leading to sycophancy an
arXiv:2603.24033v2 Announce Type: replace Abstract: We propose Score-based Relaxation-guided Generation (SRG), a generative framework based on an approximate formulation of relaxation-guided stochasti
arXiv:2605.11919v1 Announce Type: new Abstract: Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node
arXiv:2602.15620v4 Announce Type: replace Abstract: Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic
Elon Musk posted on X claiming that Starlink internet connectivity is United Airlines' top feature and significantly enhances the flight experience at no cost to passengers. The post suggests Starlink
Starship launch next week! Starship’s twelfth flight test will debut the next generation Starship and Super Heavy vehicles, powered by the next evolution of the Raptor engine and launching from a newl
Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party a
Starting today, you can run cloud agents inside fully configured development environments. Set them up the same way you'd set up a laptop for an engineer: cloned repos, installed dependencies, and too
arXiv:2505.20754v3 Announce Type: replace-cross Abstract: Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance in numerical integratio
arXiv:2605.11133v1 Announce Type: new Abstract: We introduce steerable neural ordinary differential equations on homogeneous spaces M=G/H. These models constitute a novel geometric extension of manifo
arXiv:2605.10971v1 Announce Type: cross Abstract: Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive
arXiv:2605.11922v1 Announce Type: cross Abstract: Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct an
arXiv:2605.11975v1 Announce Type: new Abstract: We study stochastic minimum-cost reach-avoid reinforcement learning, where an agent must satisfy a reach-avoid specification with probability at least p
arXiv:2605.11483v1 Announce Type: new Abstract: While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints rem
arXiv:2605.11804v1 Announce Type: cross Abstract: Data-free continual learning (DFCIL) relies on model inversion to synthesize pseudo-samples and mitigate catastrophic forgetting. However, existing in
Stop turning prompting into magic spells (and yes, this includes random slash commands with obscure outcomes). Let this one area of working with AI not be weird. Just ask for stuff, in well-specified
arXiv:2602.06412v3 Announce Type: replace Abstract: Masked Diffusion Language Models generate sequences via iterative sampling that progressively unmasks tokens. However, they still recompute the atte
arXiv:2605.12412v1 Announce Type: new Abstract: Large Language Models (LLMs) update their behavior in context, which can be viewed as a form of Bayesian inference. However, the structure of the latent
arXiv:2605.12292v1 Announce Type: new Abstract: Benchmarking tabular learning has revealed the benefit of dedicated architectures, pushing the state of the art. But real-world tables often contain str
arXiv:2506.09044v2 Announce Type: replace Abstract: Machine Learning systems are increasingly deployed in decision-making settings that shape user behavior and, in turn, the data on which future decis
arXiv:2605.10995v1 Announce Type: cross Abstract: Streaming rendered content is an attractive way to bring high-quality graphics to billions of mobile devices that do not have sufficient rendering pow
arXiv:2605.11494v1 Announce Type: new Abstract: Distilled one-step (T=1) or few-step (Tleq4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to t
arXiv:2605.10985v1 Announce Type: new Abstract: Protein language models such as ESM-2 learn rich residue representations that achieve strong performance on protein function prediction, but their featu
arXiv:2605.12135v1 Announce Type: cross Abstract: We present STRUM (Spectral Transcription and Rhythm Understanding Model), an audio-to-chart pipeline that converts raw recordings into playable Clone
Super excited about the new deepagents version from @LangChain What’s in their water supply?? Not to mention 7 blog posts dropped today, including a new Deep Agents version with significant improvemen
arXiv:2605.11246v1 Announce Type: new Abstract: Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by
arXiv:2605.10989v1 Announce Type: new Abstract: The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sig
arXiv:2511.11935v2 Announce Type: replace Abstract: Deep-learning survival models for electronic health record (EHR) data are hard to compare across papers because the upstream preprocessing step, whi
arXiv:2605.12179v1 Announce Type: new Abstract: Recent advancements in video-audio joint generation have achieved remarkable success in semantic correspondence. However, achieving precise temporal syn
arXiv:2503.18760v2 Announce Type: replace Abstract: A key consideration when training an LLM is whether the target language is more or less resourced, for example English compared to Welsh, or Python
arXiv:2602.22586v2 Announce Type: replace-cross Abstract: Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy.
arXiv:2501.19403v3 Announce Type: replace Abstract: Machine unlearning seeks to remove the influence of specified data from a trained model. While the unlearning accuracy provides a widely used metric
arXiv:2602.21625v2 Announce Type: replace Abstract: Vision-Based Tactile Sensors (VBTS) are essential for achieving dexterous robotic manipulation, yet the tactile sim-to-real gap remains a fundamenta
arXiv:2511.07767v2 Announce Type: replace Abstract: Schedule-Free SGD, proposed in [Defazio et al., 2024], achieves optimal convergence rates without requiring the training horizon in advance, by repl
arXiv:2605.11538v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However
arXiv:2603.10281v3 Announce Type: replace-cross Abstract: While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization
arXiv:2605.12064v1 Announce Type: new Abstract: Existing deep learning-based methods can capture shared features from optical and synthetic aperture radar (SAR) images for spatial alignment. However,
arXiv:2605.12290v1 Announce Type: new Abstract: Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering
arXiv:2605.11599v1 Announce Type: new Abstract: Fixed reasoning benchmarks evaluate canonical prompts, but semantically valid changes in presentation can still change model behavior. Studies of prompt
arXiv:2605.12487v1 Announce Type: new Abstract: We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search
arXiv:2605.11572v1 Announce Type: new Abstract: Audio-visual understanding requires effective alignment between heterogeneous modalities, yet cross-modal correspondence remains challenging when tempor
arXiv:2605.11563v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as a compelling alternative to attention models for long-range vision tasks, offering input-dependent recurrence
Bloomberg: Tencent reports Q1 revenue up 9% YoY to ~28.9B, below ~29.4B est., and net income of ~$8.5B, meeting est., amid a costly AI pivot; its stock is down 23% YTD — Tencent Holdings Ltd. reported
The Information: Tencent says it plans to spend significantly more on AI infrastructure in H2 2026 as more China-designed AI chips become available “month by month” — Tencent Holdings is gearing up to
arXiv:2605.11374v1 Announce Type: cross Abstract: Test-time compute is widely believed to benefit only large reasoning models. We show it also helps small embedding models. Most modern embedding check
arXiv:2605.10991v1 Announce Type: new Abstract: Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process
arXiv:2605.02453v1 Announce Type: cross Abstract: We present a machine learning framework for testing general relativity (GR) with gravitational wave signals from binary black hole mergers. Using the
arXiv:2605.12456v1 Announce Type: cross Abstract: We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generatio
Thank you again to all 227 submitters! We loved seeing the range of creative domains and all of the unusual uses for Hermes Agent you found. The team will be highlighting more personal favorites and s
arXiv:2605.12452v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate fluent political text at scale, raising concerns about synthetic discourse during crises and social conflict.
arXiv:2605.11167v1 Announce Type: new Abstract: Existing multi-model and tool-augmented systems communicate by generating text, serializing every exchange through the output vocabulary. Can two pretra
arXiv:2507.13841v2 Announce Type: replace Abstract: Good storytelling involves surprise -- unpredictability in how the story unfolds -- and sense-making, the requirement that the story forms a coheren
arXiv:2602.19770v2 Announce Type: replace Abstract: Explainable artificial intelligence has emerged as a promising field of research to address reliability concerns in artificial intelligence. Despite
arXiv:2605.11550v1 Announce Type: new Abstract: A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action M
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. A plan to make drugs in orbit is going commercial A startup ca
arXiv:2605.11496v1 Announce Type: cross Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and