All entries

Sparsity and Out-of-Distribution Generalization

arXiv:2603.07388v2 Announce Type: replace Abstract: Explaining out-of-distribution generalization has been a central problem in epistemology since Goodman's 'grue' puzzle in 1946. Today it's a central

safetyarxiv-cs-lg

Sparsity-Constraint Optimization via Splicing Iteration

arXiv:2406.12017v2 Announce Type: replace-cross Abstract: Sparsity-constrained optimization underlies many problems in signal processing, statistics, and machine learning. State-of-the-art hard-thresh

model-releasesarxiv-cs-lg

13 May 2026

Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors

arXiv:2605.11394v1 Announce Type: cross Abstract: We present the Spatial Adapter, a parameter-efficient post-hoc layer that equips any frozen first-stage predictor with a structured spatial representa

SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images

arXiv:2605.11462v1 Announce Type: new Abstract: Recent advancements in Large Vision-Language Models (VLMs) have demonstrated exceptional semantic understanding, yet these models consistently struggle

Spectral-Adaptive Modulation Networks for Visual Perception

arXiv:2503.23947v2 Announce Type: replace Abstract: Recent studies have shown that 2D convolution and self-attention exhibit distinct spectral behaviors, and optimizing their spectral properties can e

safetyarxiv-cs-cv

Spectral Vision Transformer for Efficient Tokenization with Limited Data

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

Agents

Spend less time on triaging Ship fixes faster Catch regressions earlier Introducing LangSmith Engine: an agent that works autonomously to fi…

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

agentsharrison-chase--x

Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation

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

SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels

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

applicationsarxiv-cs-cv

Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training

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

safetyarxiv-cs-lg

SRG: Score-based Relaxation-guided Generation for Mixed Integer Linear Programming

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

STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning

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

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

model-releasesarxiv-cs-cl

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

Industry

Starlink is the top reason to fly United. It immediately makes every flight ten times better and it's free.

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

industryelon-musk--x

Starship launch next week!

model-releaseselon-musk--x

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 …

model-releasesboris-cherny--x

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

Tools

Starting today, you can run cloud agents inside fully configured development environments. Set them up the same way you'd set up a laptop fo…

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

toolscursor--x

Stationary MMD Points

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

Steerable Neural ODEs on Homogeneous Spaces

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

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models

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

researcharxiv-cs-cl

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning

model-releasesarxiv-cs-cl

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

Agents

Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning

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

agentsarxiv-cs-lg

StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models

model-releasesarxiv-cs-cl

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

Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning

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 …

applicationsethan-mollick--x

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

Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding

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

researcharxiv-cs-cl

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space

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

researcharxiv-cs-cl

STRABLE: Benchmarking Tabular Machine Learning with Strings

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

applicationsarxiv-cs-lg

Tutorials

Strategically Deceptive Model Deployment in Performative Prediction

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

tutorialsarxiv-cs-lg

Streaming of rendered content with adaptive frame rate and resolution

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

STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models

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

safetyarxiv-cs-cv

Local Ai

Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioning

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

local-aiarxiv-cs-lg

STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts

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

Agents

Super excited about the new deepagents version from @LangChain What’s in their water supply??

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

agentsharrison-chase--x

Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization

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

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

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

safetyarxiv-cs-lg

SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis

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

SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning

model-releasesarxiv-cs-cv

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

Tutorials

Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages

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

tutorialsarxiv-cs-cl

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion

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.

applicationsarxiv-cs-cl

Tackling Fake Forgetting through Uncertainty Quantification

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

Tacmap: Bridging the Tactile Sim-to-Real Gap via Geometry-Consistent Penetration Depth Map

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

safetyarxiv-cs-ro

Taking the Road Less Scheduled with Adaptive Polyak Steps

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

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting

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

safetyarxiv-cs-cl

Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework

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

TAR: Text Semantic Assisted Cross-modal Image Registration Framework for Optical and SAR Images

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,

safetyarxiv-cs-cv

Targeted Neuron Modulation via Contrastive Pair Search

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

Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol

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