Search: “papers”

Modular Retrieval-Augmented Generalization for Human Action Recognition

arXiv:2605.08117v1 Announce Type: cross Abstract: Inertial Measurement Unit (IMU)-based Human Activity Recognition (HAR) aims to interpret and classify user behaviors from temporal motion signals. Rec

applicationsarxiv-cs-cv

MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery

DGX agent

arXiv:2605.09856v1 Announce Type: cross Abstract: Although recent studies have made remarkable progress in human mesh recovery, they still exhibit limited robustness to occlusions and often produce in

researcharxiv-cs-ai

12 May 2026

Morphology-Aware Graph Reinforcement Learning for Tensegrity Robot Locomotion

arXiv:2510.26067v2 Announce Type: replace Abstract: Tensegrity robots combine rigid rods and elastic cables, offering high resilience and deployability but at the same time posing major challenges for

safetyarxiv-cs-ro

MTA-RL: Robust Urban Driving via Multi-modal Transformer-based 3D Affordances and Reinforcement Learning

arXiv:2605.10177v1 Announce Type: cross Abstract: Robust urban autonomous driving requires reliable 3D scene understanding and stable decision-making under dense interactions. However, existing end-to

safetyarxiv-cs-ai

MultiAnimate: Pose-Guided Image Animation Made Extensible

arXiv:2602.21581v2 Announce Type: replace Abstract: Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based

Muon Does Not Converge on Convex Lipschitz Functions

arXiv:2605.08980v1 Announce Type: new Abstract: Muon and its variants have shown strong empirical performance in a variety of deep learning tasks. Existing convergence analyses of Muon rely on smoothn

Agents

MUSDA: Multi-source Multi-modality Unsupervised Domain Adaptive 3D Object Detection for Autonomous Driving

arXiv:2605.10026v1 Announce Type: new Abstract: With the advancement of autonomous driving, numerous annotated multi-modality datasets have become available. This presents an opportunity to develop do

agentsarxiv-cs-cv

Nested Slice Sampling: Vectorized Nested Sampling for GPU-Accelerated Inference

arXiv:2601.23252v2 Announce Type: replace-cross Abstract: Model comparison and calibrated uncertainty quantification often require integrating over parameters, but scalable inference can be challengin

Neural Co-state Policies: Structuring Hidden States in Recurrent Reinforcement Learning

arXiv:2605.05373v2 Announce Type: replace Abstract: A key capability of intelligent agents is operating under partial observability: reasoning and acting effectively despite missing or incomplete stat

safetyarxiv-cs-lg

NeuralBench: A Unifying Framework to Benchmark NeuroAI Models

arXiv:2605.08495v1 Announce Type: new Abstract: Deep learning and large public datasets have recently catalyzed the proliferation of AI models for processing brain recordings. However, systematically

Neuromorphic Monocular Depth Estimation with Uncertainty Modeling

arXiv:2605.10675v1 Announce Type: new Abstract: Event cameras offer distinct advantages over conventional frame-based sensors, including microsecond-level temporal resolution, high dynamic range, and

NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification

arXiv:2505.20001v5 Announce Type: replace Abstract: Multi-modal object Re-IDentification (ReID) aims to obtain complete identity features across heterogeneous modalities. However, most existing method

applicationsarxiv-cs-cv

NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning

arXiv:2605.09387v1 Announce Type: new Abstract: While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty

safetyarxiv-cs-ai

Non-Parametric Rehearsal Learning via Conditional Mean Embeddings

arXiv:2605.08999v1 Announce Type: new Abstract: In machine learning, a critical class of decision-related problems concerns preventing predicted undesirable outcomes, referred to as the extit{avoiding

Agents

NyayaAI: An AI-Powered Legal Assistant Using Multi-Agent Architecture and Retrieval-Augmented Generation

arXiv:2605.10155v1 Announce Type: new Abstract: Legal information in India remains largely inaccessible due to the complexity of legal language and the sheer volume of legal documentation involved in

agentsarxiv-cs-cl

Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search

arXiv:2605.08762v1 Announce Type: cross Abstract: Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start

On Observation Time for Recovering Latent Hawkes Networks

arXiv:2605.08400v1 Announce Type: cross Abstract: Dynamics of interacting systems in engineering, society, and nature often evolve over latent networks that govern which entities can interact. We stud

applicationsarxiv-cs-lg

On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency

arXiv:2601.21619v2 Announce Type: replace-cross Abstract: Parallel thinking improves LLM reasoning through multi-path sampling and aggregation. In standard evaluations, due to a lack of sample-specifi

applicationsarxiv-cs-ai

Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection

arXiv:2605.10040v1 Announce Type: new Abstract: The rapid evolution of generative paradigms has enabled the creation of highly realistic imagery, which escalating the risks of identity fraud and the d

Optimal FALQON for Quantum Approximate Optimization via Layer-wise Parameter Tuning

arXiv:2605.08332v1 Announce Type: cross Abstract: Feedback-based adaptive quantum optimization (FALQON) is a promising approach for solving combinatorial problems on noisy intermediate-scale quantum (

Optimality of Sub-network Laplace Approximations: New Results and Methods

arXiv:2605.09075v1 Announce Type: cross Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessia

Optimised Support Vector Regression for California Housing Price Prediction: The Critical Role of Feature Engineering and Hyperparameter Tuning

arXiv:2605.08660v1 Announce Type: new Abstract: In the recent literature, Support Vector Regression (SVR) has been cited as one of the weakest performers on the California Housing benchmark dataset, w

Optimized Culprit Identification Using Mobilenet and Attention Mechanisms

arXiv:2605.08169v1 Announce Type: cross Abstract: Automated culprit identification in surveillance systems is a critical task that requires high accuracy along with computational efficiency for real-t

OZ-TAL: Online Zero-Shot Temporal Action Localization

arXiv:2605.09976v1 Announce Type: new Abstract: Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon t

PAINET: A Principled Efficient Transformer for 3D Dynamics Modeling

arXiv:2510.04233v2 Announce Type: replace-cross Abstract: Modeling 3D dynamics is a fundamental problem in multi-body systems across scientific and engineering domains and has important practical impl

applicationsarxiv-cs-ai

Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses

arXiv:2605.10219v1 Announce Type: cross Abstract: We study the parameterized complexity of testing approximate first-order stationarity at a prescribed point for continuous piecewise-affine (PA) funct

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding

arXiv:2605.08632v1 Announce Type: cross Abstract: Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verifi

Perceptual Asymmetry Between Hue Categories: Evidence from Human Color Categorization

arXiv:2605.09339v1 Announce Type: cross Abstract: Human color categories are not uniformly distributed in perceptual space, yet most computational color models still assume fixed and evenly structured

Performance and Energy Trade-Off Analysis of Hierarchical Federated Learning for Plant Disease Classification

arXiv:2605.08121v1 Announce Type: cross Abstract: Early detection of plant diseases is critical for improving crop productivity, while it also facilitates the foundations of precision agriculture. Rec

Hardware

PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models

arXiv:2605.09503v1 Announce Type: new Abstract: Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challengin

hardwarearxiv-cs-cv

Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity

arXiv:2605.09119v1 Announce Type: cross Abstract: Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistic

PHIDA: Persistence-Guided Node-to-Cluster Mapping for Online Clustering

arXiv:2605.08673v1 Announce Type: new Abstract: Online clustering methods that adaptively create and update nodes as data arrive often make node learning explicit, whereas the mapping from the learned

PlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker Reasoning

model-releasesarxiv-cs-cl

arXiv:2605.10032v1 Announce Type: new Abstract: Cell-type-specific marker genes are fundamental to plant biology, yet existing resources primarily rely on curated databases or high-throughput studies

Local Ai

PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks

arXiv:2605.09434v1 Announce Type: cross Abstract: Low-cost air quality sensors are becoming ubiquitous in our daily lives as public awareness of air pollution continues to grow, and people take measur

local-aiarxiv-cs-lg

Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead

arXiv:2507.23009v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved remarkable results on a range of standardized tests originally designed to assess human cognitive a

Positional Encoding via Token-Aware Phase Attention

arXiv:2509.12635v3 Announce Type: replace-cross Abstract: We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scor

safetyarxiv-cs-ai

PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models

arXiv:2605.08800v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmar

Practical Wi-Fi-based Motion Recognition Under Variable Traffic Patterns

arXiv:2605.08308v1 Announce Type: cross Abstract: Wi-Fi sensing detects human motions and activities by analysing the channel state information (CSI) derived from Wi-Fi transmissions. However, the imp

Privacy Auditing Synthetic Data Release through Local Likelihood Attacks

arXiv:2508.21146v2 Announce Type: replace Abstract: Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely

Local Ai

Privacy-Preserving Federated Learning: Integrating Zero-Knowledge Proofs in Scalable Distributed Architectures

arXiv:2605.08152v1 Announce Type: cross Abstract: The intersection of Artificial Intelligence (AI) and distributed systems has given rise to Federated Learning (FL), a paradigm that enables decentrali

local-aiarxiv-cs-ai

Probing Cross-modal Information Hubs in Audio-Visual LLMs

arXiv:2605.10815v1 Announce Type: new Abstract: Audio-visual large language models (AVLLMs) have recently emerged as a powerful architecture capable of jointly reasoning over audio, visual, and textua

ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability

arXiv:2605.08858v1 Announce Type: new Abstract: Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive 'this looks like that' reasoning p

PumpSense: Real-Time Detection and Target Extraction of Crypto Pump-and-Dumps on Telegram

model-releasesarxiv-cs-cl

arXiv:2605.09431v1 Announce Type: new Abstract: Cryptocurrency pump-and-dump schemes coordinated via Telegram threaten market integrity. However, existing research addressing this specific threat has

Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime

arXiv:2605.10931v1 Announce Type: cross Abstract: Transformers with self-attention modules as their core components have become an integral architecture in modern large language and foundation models.

Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow

arXiv:2605.09456v1 Announce Type: cross Abstract: Stein Variational Gradient Descent (SVGD) is a deterministic interacting-particle method for sampling from a target probability measure given access t

Rapid Forest Fuel Load Estimation via Virtual Remote Sensing and Metric-Scale Feed-Forward 3D Reconstruction

arXiv:2605.10789v1 Announce Type: new Abstract: Accurate quantification of forest coverage and combustible biomass (fuel load) is critical for wildfire risk assessment and ecosystem management. Howeve

RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache

arXiv:2605.08317v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memor

Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation

arXiv:2605.10430v1 Announce Type: cross Abstract: Estimating heterogeneous treatment effects with machine learning has attracted substantial attention in both academic research and industrial practice