Search: “papers”

Decentralized LLM-Driven Coordination of Acoustic Robots for Contactless Object Manipulation

arXiv:2605.29378v1 Announce Type: new Abstract: Natural language interfaces can simplify interaction with multi-robot systems, especially when non-expert users need to issue high-level commands. Acous

applicationsarxiv-cs-ro

Research

Decoupled Thrust-Axis Attitude Control Using Quaternions for Chandrayaan-3 Lunar Landing Mission

DGX agent

arXiv:2605.29409v1 Announce Type: cross Abstract: Chandrayaan-3 mission achieved a historic milestone with its successful soft landing near the lunar south pole, highlighting the critical role of the

researcharxiv-cs-ro

29 May 2026

Deep Optimal Individualized Treatment Rules for Bivariate Survival Outcomes via Adaptive Prediction-Powered Learning

arXiv:2605.29464v1 Announce Type: cross Abstract: In randomized trials involving multiple treatments, bivariate survival outcomes present significant analytical challenges for making decisions. This p

researcharxiv-cs-lg

Deep Psychovisual Image Representations

arXiv:2605.29260v1 Announce Type: new Abstract: Psychovisual models suggest human vision decouples low-level feature extraction from higher cognition by first forming intermediate abstractions. In con

tutorialsarxiv-cs-cv

Local Ai

Demystifying Data Organization for Enhanced LLM Training

arXiv:2605.30334v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. While data

local-aiarxiv-cs-ai

Designing Active Tether-Net Systems for Space Debris Capture with Graph-Learning-Aided Mixed-Combinatorial Optimization

arXiv:2605.29021v1 Announce Type: new Abstract: Active tether-net systems are a promising solution for capturing large non-cooperative targets, such as space debris, by deploying a flexible net manipu

agentsarxiv-cs-lg

Hardware

DFlash: Block Diffusion for Flash Speculative Decoding

arXiv:2602.06036v2 Announce Type: replace Abstract: Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency

hardwarearxiv-cs-cl

Distributed Non-Uniform Scaling Control of Multi-Agent Formation with Dynamic Agent Joining

arXiv:2605.29191v1 Announce Type: cross Abstract: Non-uniform scaling control of formation enables multi-agent systems to adjust their shape by scaling with different ratios along different coordinate

agentsarxiv-cs-ro

Does Distributed Training Undermine Compute Governance?

arXiv:2605.29359v1 Announce Type: cross Abstract: Compute governance proposals often rely on the assumption that frontier AI training requires large, detectable computing clusters. However, recent adv

researcharxiv-cs-ai

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

arXiv:2605.29707v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical

Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale

arXiv:2605.30200v1 Announce Type: new Abstract: The double-edged sword of integrating Large Language Models (LLMs) requires an effective triadic collaboration mechanism among LLMs, teachers and studen

applicationsarxiv-cs-ai

Dual Quaternion SE(3) Synchronization with Recovery Guarantees

arXiv:2602.00324v2 Announce Type: replace-cross Abstract: Synchronization over the special Euclidean group SE(3) aims to recover absolute poses from noisy pairwise relative transformations and is a co

applicationsarxiv-cs-cv

Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure

arXiv:2602.08783v3 Announce Type: replace Abstract: Latent or continuous chain-of-thought methods replace explicit textual rationales with a number of internal latent steps, but these intermediate com

safetyarxiv-cs-ai

Hardware

EarlyTom: Early Token Compression Completes Fast Video Understanding

arXiv:2605.30010v1 Announce Type: new Abstract: Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is stil

hardwarearxiv-cs-cv

Hardware

ESAM++: Efficient Online 3D Perception on the Edge

arXiv:2605.29505v1 Announce Type: new Abstract: Online 3D scene perception in real time is essential for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computa

hardwarearxiv-cs-cv

Evaluation of Conversational Agents: Understanding Culture, Context and Environment in Emotion Detection

arXiv:2605.30099v1 Announce Type: new Abstract: Valuable decisions and highly prioritized analysis now depend on applications such as facial biometrics, social media photo tagging, and human robots in

applicationsarxiv-cs-cv

EVL-ECG: Efficient ECG Interpretation With Multi-Aspect Heterogeneous Knowledge Distillation

model-releasesarxiv-cs-cv

arXiv:2605.29977v1 Announce Type: new Abstract: High-fidelity ECG interpretation is increasingly reliant on massive foundation models, yet their deployment in clinical edge-care remains hindered by ex

EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation

arXiv:2605.29847v1 Announce Type: new Abstract: Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation

safetyarxiv-cs-cl

Explaining Concept Shift with Interpretable Feature Attribution

arXiv:2505.20634v2 Announce Type: replace Abstract: Concept shift occurs when the distribution of labels conditioned on the features changes between domains, which can make even a well-tuned ML model

tutorialsarxiv-cs-lg

F-RNG: Feed-Forward Relightable Neural Gaussians

arXiv:2605.25975v2 Announce Type: replace-cross Abstract: Capturing relightable 3D assets from real-world objects is a widely researched problem. Several per-scene optimization-based methods, based on

applicationsarxiv-cs-cv

Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language

arXiv:2605.29793v1 Announce Type: new Abstract: Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untr

safetyarxiv-cs-cv

Local Ai

FHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting

arXiv:2605.29695v1 Announce Type: new Abstract: Approximately 10% of newborns require assistance to initiate breathing at birth, and around 5% need ventilation support. Fetal heart rate (FHR) monitori

local-aiarxiv-cs-ai

Fingerprinting Inference Systems of Large Language Models

arXiv:2605.29979v1 Announce Type: cross Abstract: The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend,

researcharxiv-cs-lg

From Data to Insights: Exploring Program-of-Thoughts Prompting for Chart Summarization

arXiv:2605.28874v1 Announce Type: new Abstract: Charts play a critical role in conveying numerical data insights through structured visual representations. However, semantic visual understanding and n

From Prompts to Context: An Ontology-Driven Framework for Human-Generative AI Collaboration

arXiv:2605.29675v1 Announce Type: cross Abstract: Collaborations with Generative AI often begin with a short prompt and end with an opaque output, leaving implicit who was involved, what task was bein

agentsarxiv-cs-ai

FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views

arXiv:2605.29997v1 Announce Type: new Abstract: We present FRUC, a feed-forward 3D Gaussian splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing

agentsarxiv-cs-cv

Gated Graph Attention Networks with Learnable Temperature

arXiv:2605.29803v1 Announce Type: new Abstract: Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable featur

tutorialsarxiv-cs-lg

GenClaw: Code-Driven Agentic Image Generation

arXiv:2605.30248v1 Announce Type: new Abstract: Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents endowed with visual comprehension and tool invocatio

agentsarxiv-cs-cv

Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning

arXiv:2605.29661v1 Announce Type: new Abstract: Monocular 3D shape recovery is fundamental to geometric understanding, yet achieving robust generalization across arbitrary viewpoints and unseen object

safetyarxiv-cs-cv

GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection

arXiv:2605.29539v1 Announce Type: cross Abstract: Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they fa

researcharxiv-cs-ai

Gradient Perturbation: Learning to Perturb Gradients for Adaptive Training

model-releasesarxiv-cs-lg

arXiv:2605.29494v1 Announce Type: new Abstract: Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradie

GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases

arXiv:2605.30237v1 Announce Type: cross Abstract: Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product s

GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German

arXiv:2605.30214v1 Announce Type: new Abstract: Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about referenc

safetyarxiv-cs-cl

Hallucination Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching

model-releasesarxiv-cs-ai

arXiv:2605.29055v1 Announce Type: new Abstract: Hallucination remains a major reliability barrier for production LLM systems, particularly in multi-agent pipelines where unsupported claims can propaga

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills

arXiv:2605.29354v1 Announce Type: cross Abstract: LLM-powered coding agents increasingly participate in software development workflows by generating code, selecting dependencies, and producing package

agentsarxiv-cs-lg

HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens

arXiv:2512.15133v2 Announce Type: replace-cross Abstract: Proteins inherently possess a consistent sequence-structure duality. The abundance of protein sequence data, which can be readily represented

tutorialsarxiv-cs-ai

HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?

model-releasesarxiv-cs-cl

arXiv:2605.30058v1 Announce Type: new Abstract: While LLM agents have demonstrated remarkable task-oriented abilities such as planning, reasoning, and action, few works have treated them as complete h

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction

arXiv:2605.29960v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability

agentsarxiv-cs-ai

Local Ai

HTAM: Hierarchical Transition-Attended Memory for Operator Optimization

arXiv:2605.29734v1 Announce Type: new Abstract: High-performance GPU kernels are essential for efficient LLM deployment, yet optimizing them remains expertise-intensive. Recent LLM-based code generati

local-aiarxiv-cs-cl

Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning

arXiv:2605.29776v1 Announce Type: new Abstract: Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain sce

safetyarxiv-cs-cv

Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language Models

arXiv:2605.29625v1 Announce Type: new Abstract: The topic of Co-creation, i.e., AI agents interacting with humans to generate outputs (e.g., art), has gained significant attention recently. However, m

agentsarxiv-cs-ai

Inferring Code Correctness from Specification

arXiv:2605.29822v1 Announce Type: cross Abstract: Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the

safetyarxiv-cs-ai

Intent-aligned Autonomous Spacecraft Guidance via Reasoning Models

arXiv:2604.17176v2 Announce Type: replace-cross Abstract: Future spacecraft operations require autonomy that can interpret high-level mission intent while preserving safety. However, existing trajecto

safetyarxiv-cs-ai

Large-Scale AI and Foundation Models for Neuroscience: A Comprehensive Review

arXiv:2510.16658v3 Announce Type: replace Abstract: The development of large-scale artificial intelligence (AI) models is influencing neuroscience research by enabling end-to-end learning from raw bra

researcharxiv-cs-ai

Learning and Adaptation in Wire Arc Additive Manufacturing Bead Geometry Control

arXiv:2605.29144v1 Announce Type: new Abstract: Robotics Wire Arc Additive Manufacturing (WAAM) is governed by complex and nonlinear process dynamics coupling thermal field to the build geometry. The

tutorialsarxiv-cs-ro

Learning to Perturb Hidden Representations for Generalizable Deep Learning

arXiv:2605.29525v1 Announce Type: new Abstract: Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the

researcharxiv-cs-lg

Lightweight Multimodal LLM-Enabled Cost-Effective Defect Grading of Power Transmission Equipment

arXiv:2605.28822v1 Announce Type: new Abstract: Defect grading of power transmission equipment (DGPTE) is crucial to the stability of electric energy transmission. Although existing machine learning m

LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning

model-releasesarxiv-cs-ai

arXiv:2605.29649v1 Announce Type: new Abstract: Heuristic search is the dominant paradigm in symbolic AI planning, and the strongest heuristics are the result of decades of work by planning researcher