All entries

SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates

arXiv:2512.06344v2 Announce Type: replace Abstract: Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic inconsistency at ultra-low bitrates (

SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision

DGX agent

arXiv:2606.28562v1 Announce Type: new Abstract: On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent

safetyarxiv-cs-cl

30 Jun 2026

Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories

arXiv:2606.28589v1 Announce Type: new Abstract: Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and 'Wait' prompts, primarily encourage models to think mor

SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages

arXiv:2606.28715v1 Announce Type: cross Abstract: While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood d

Applications

See and Switch: Vision-Based Branching for Interactive Robot-Skill Programming

arXiv:2603.08057v2 Announce Type: replace-cross Abstract: Programming by demonstration (PbD) makes robot programming accessible to non-experts, but scaling it to real-world variability remains a chall

applicationsarxiv-cs-cv

Local Ai

See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs

arXiv:2606.29847v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) excel at multimodal tasks but remain prone to object hallucinations. Prior training-free remedies often uniformly s

local-aiarxiv-cs-cv

Tools

See our full model rankings: http://cursor.com/evals

Cursor published a comprehensive ranking of AI models, likely evaluating them across performance metrics, capabilities, and use cases relevant to their code editor platform. The rankings help users un

toolscursor--x

See, Think, Learn: A Self-Taught Multimodal Reasoner

arXiv:2512.02456v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effecti

tutorialsarxiv-cs-cl

Seed-to-Seed: Unpaired Image Translation in Diffusion Seed Space

arXiv:2409.00654v2 Announce Type: replace Abstract: We introduce Seed-to-Seed Translation (StS), a novel approach that combines GANs and diffusion models (DMs) for unpaired Image-to-Image Translation.

Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation

arXiv:2606.29941v1 Announce Type: cross Abstract: Visuo-Tactile policies leveraging optical tactile sensors have shown great promise in contact-rich manipulation. These sensors achieve high spatial re

safetyarxiv-cs-cv

Selective Memory Retention for Long-Horizon LLM Agents

arXiv:2606.29178v1 Announce Type: new Abstract: When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightweight framework for bounded external memory in froze

Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution

arXiv:2606.28971v1 Announce Type: new Abstract: Real-world image restoration (IR) remains challenging due to complex and coupled degradations. While recent agentic IR frameworks leverage Large Languag

agentsarxiv-cs-cv

Self-Evolving World Models for LLM Agent Planning

arXiv:2606.30639v1 Announce Type: new Abstract: World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unrel

agentsarxiv-cs-ai

Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery

arXiv:2606.29403v1 Announce Type: cross Abstract: Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in s

safetyarxiv-cs-ai

Self-Supervised Calibration of Scientific Instruments Using Physical Consistency Constraints

arXiv:2606.29466v1 Announce Type: new Abstract: Calibration remains one of the principal obstacles to the deployment of machine learning in scientific instrumentation because it typically relies on ex

agentsarxiv-cs-lg

Self-supervised Geometry Reasoning for LiDAR Simultaneous Localization and Mapping

arXiv:2606.30166v1 Announce Type: new Abstract: LiDAR simultaneous localization and mapping (SLAM) relies on local geometric quantities such as covariances, correspondences, and surface structures. Ho

researcharxiv-cs-ro

Self-Supervised Theorem Discovery in a Formal Axiomatic System

arXiv:2606.28747v1 Announce Type: new Abstract: Recent artificial intelligence (AI) systems have shown remarkable progress in mathematical reasoning. Many existing approaches, including large language

Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems

arXiv:2606.28398v1 Announce Type: new Abstract: Resource-constrained visual Internet of Things (IoT) systems, such as edge cameras, unmanned sensing platforms, industrial inspection nodes, and remote

Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis

arXiv:2606.29020v1 Announce Type: cross Abstract: Weather synthesis aims to add weather effects to input videos while preserving scene identity, structure, and motion. The key limitation of existing m

agentsarxiv-cs-ai

Semantic Correspondence: Unified Benchmarking and a Strong Baseline

arXiv:2505.18060v4 Announce Type: replace Abstract: Establishing semantic correspondence is a challenging task in computer vision, aiming to match keypoints with the same semantic information across d

Semantic-Driven Scale and Spatial Selection for Efficient Cross-Modal Alignment in Referring Remote Sensing Image Segmentation

model-releasesarxiv-cs-cv

arXiv:2606.30244v1 Announce Type: new Abstract: Referring Remote Sensing Image Segmentation (RRSIS) seeks to localize and segment the target object or region specified by a natural language expression

SemConFlow: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching

arXiv:2603.26553v2 Announce Type: replace Abstract: While the field of co-speech gesture generation has seen significant advances, producing holistic, semantically grounded gestures remains a challeng

SemDynReg: Semantics-Guided Deformation Regularization for Dynamic 3D Gaussian Splatting

arXiv:2606.28656v1 Announce Type: cross Abstract: Deformable 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for rendering dynamic scenes in a wide range of 3D applications. However,

tutorialsarxiv-cs-ai

SemFlowRAG: Directed Semantic Flow from Abstraction to Evidence for Complex Reasoning

arXiv:2606.28447v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhanced by Knowledge Graphs has shown promise in complex multi-hop reasoning tasks. However, existing graph-base

researcharxiv-cs-ai

Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss

arXiv:2606.29901v1 Announce Type: cross Abstract: Sound event detection (SED) is a core module for acoustic environmental analysis, yet its performance is often limited by scarce labeled data. Recent

researcharxiv-cs-ai

SemJoin: Semantic Join Optimization

arXiv:2606.29532v1 Announce Type: cross Abstract: Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A

agentsarxiv-cs-ai

SEO Agent. Security Agent. Design in Claude. Replit Desktop. Shopify on Replit. Skills + Custom Instructions. 450+ integrations. Package Fir…

SEO Agent. Security Agent. Design in Claude. Replit Desktop. Shopify on Replit. Skills + Custom Instructions. 450+ integrations. Package Firewall. And more! ✨ All shipped in June! 🤯 And there's a good

model-releasesreplit--x

Sequential Fairness Auditing with Limited Output Access

arXiv:2606.30338v1 Announce Type: new Abstract: External evaluations are becoming increasingly central to the governance of AI systems. In practice, however, independent auditors often have limited ac

safetyarxiv-cs-ai

Sequential Hiring of Contingent Workers Through Learning-Based Optimization

model-releasesarxiv-cs-lg

arXiv:2606.18438v2 Announce Type: replace-cross Abstract: In this paper, we study a sequential workforce management problem in a contingent labor setting with uncertainty in both worker production and

Sequential Planning via Anchored Robotic Keypoints

model-releasesarxiv-cs-ro

arXiv:2606.30613v1 Announce Type: new Abstract: We present Sequential Planning via Anchored Robotic Keypoints, SPARK, a training-free neurosymbolic manipulation system that reaches 43.7% on six LIBERO

Set-Inclusive Uncertainty Modeling for Robust Brain Tumor Segmentation

arXiv:2606.30374v1 Announce Type: cross Abstract: Multimodal MRI is essential for accurate brain tumor segmentation. However, acquiring all modalities at inference is often challenging in practice, wh

researcharxiv-cs-ai

SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution

arXiv:2606.29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers

SFBench: The SciFy Scientific Feasibility Benchmark

arXiv:2606.29630v1 Announce Type: new Abstract: We present SFBench, a benchmark dataset for evaluating systems that assess the feasibility of scientific claims. SFBench includes 197 claims in material

SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model

arXiv:2606.30444v1 Announce Type: cross Abstract: Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut

safetyarxiv-cs-lg

Shell-Supervised Gaussian Splatting for Urban Real-to-Sim Reconstruction

arXiv:2606.30014v1 Announce Type: new Abstract: Real-to-sim reconstruction for embodied AI requires geometry that is useful for collision reasoning, navigation, and agent-environment interaction, not

agentsarxiv-cs-cv

Shoot from the HIP: Hessian Interatomic Potentials without derivatives

arXiv:2509.21624v3 Announce Type: replace Abstract: Fundamental tasks in computational chemistry, from transition state search to vibrational analysis, rely on molecular Hessians, which are the second

researcharxiv-cs-lg

shot-scraper 1.10

shot-scraper is a command-line utility for taking automated screenshots of websites . It is designed primarily for documentation but also has scraping applications . The 1.10 release likely includes u

agentssimon-willison

SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation

model-releasesarxiv-cs-cl

arXiv:2606.30201v1 Announce Type: cross Abstract: Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical

Showing how to display dynamic subagents was tricky - this is what we aligned on

tutorialsharrison-chase--x

This post likely discusses technical decisions and design patterns for dynamically displaying subagents within an AI system, documenting the alignment the team reached after encountering implementatio

SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset

arXiv:2606.30001v1 Announce Type: new Abstract: Recent co-speech gesture generation methods often overlook cultural differences, limiting their effectiveness in human-agent interaction. Moreover, cult

agentsarxiv-cs-cv

Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG

arXiv:2606.28352v1 Announce Type: cross Abstract: Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits. We propos

researcharxiv-cs-cl

SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation

arXiv:2606.28626v1 Announce Type: new Abstract: Sign language translation (SLT) remains challenging due to its high spatio-temporal complexity, long sequences, and the need to model multiple articulat

Sim2Swim: Zero-Shot Velocity Control for Agile AUV Maneuvering in 3 Minutes

arXiv:2512.08656v2 Announce Type: replace Abstract: Holonomic autonomous underwater vehicles (AUVs) have the hardware ability for agile maneuvering in both translational and rotational degrees of free

agentsarxiv-cs-ro

Applications

SIMAX: A Scalable and Interpretable Framework for Multi-Fidelity and Annotated Clinician-Patient Dialogue Simulation

arXiv:2606.30491v1 Announce Type: cross Abstract: Background. The widespread deployment of ambient digital scribes is driving large-scale capture of clinician-patient dialogues. Human coding of clinic

applicationsarxiv-cs-ai

Simplify multi-account access to Amazon Bedrock models with managed entitlements

In this post, we show you how to use managed entitlements for Amazon Bedrock to subscribe once from a central account and distribute model access across your organization. This approach removes the ne

tutorialsaws-ml-blog

Simplifying Flow Matching Transformations with Low-Rank Mixture Models

arXiv:2606.29724v1 Announce Type: new Abstract: Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, ty

tutorialsarxiv-cs-lg

Singular Learning and Occam's Razor in Deep Monomial Networks

model-releasesarxiv-cs-lg

arXiv:2606.28464v1 Announce Type: new Abstract: In the optimization of neural networks, gradient dynamics are influenced by critical points that arise from the model's architecture. These critical poi

SIR: Structured Image Representations for Explainable Robot Learning

arXiv:2606.30101v1 Announce Type: cross Abstract: Existing robot policies based on learned visual embeddings lack explicit structure and are sensitive to visual distractions. Thus, the representations

safetyarxiv-cs-cv