Search: “research”

QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking

arXiv:2605.09513v1 Announce Type: new Abstract: Tracking points in videos is typically formulated as frame-to-frame correspondence, where each point is matched locally to the next frame. While this wo

Research

Radar-Guided Polynomial Fitting for Metric Depth Estimation

DGX agent

arXiv:2503.17182v4 Announce Type: replace Abstract: We propose POLAR, a novel radar-guided depth estimation method that introduces polynomial fitting to efficiently transform scaleless depth predictio

researcharxiv-cs-cv

12 May 2026

Randomized PCA Forest for Unsupervised Outlier Detection

arXiv:2508.12776v3 Announce Type: replace-cross Abstract: We propose a novel unsupervised outlier detection method based on Randomized Principal Component Analysis (PCA). Motivated by the performance

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

Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction

arXiv:2602.09016v2 Announce Type: replace Abstract: Reconstructing a structured vector-graphics representation from a rasterized floorplan image is typically an important prerequisite for computationa

Raymoval: Raycasting-based Dynamic Object Removal for Static 3D Mapping

arXiv:2605.08937v1 Announce Type: new Abstract: Static mapping is fundamental to robot navigation, providing a persistent geometric prior and a consistent reference for long-term autonomy. However, dy

researcharxiv-cs-ro

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

Model Releases

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

model-releasesarxiv-cs-ai

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

Reasoning-Aware Training for Time Series Forecasting

arXiv:2605.08625v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) excel at numerical forecasting but operate as black boxes lacking qualitative reasoning. Conversely, applying LL

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR

arXiv:2605.10781v1 Announce Type: cross Abstract: Self-distillation has emerged as a powerful framework for post-training LLMs, where a teacher conditioned on extra information guides a student withou

Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations

arXiv:2605.08688v1 Announce Type: new Abstract: We establish, from the point of view of Explainable AI (XAI), connections between Consistency-Based Diagnosis (CBD), on one side, and Actual Causality a

Reconfigurable Computing Challenge: Real-Time Graph Neural Networks for Online Event Selection in Big Science

arXiv:2605.10612v1 Announce Type: cross Abstract: Graph neural networks are increasingly adopted in trigger systems for collider experiments, where strict latency and throughput constraints render dep

Reducing Annotation Burden for Femoral Cartilage Segmentation in Knee MRI via Cross-Sequence Transfer Learning

arXiv:2605.09067v1 Announce Type: new Abstract: Purpose: To develop and evaluate cross-sequence transfer learning for automatic femoral cartilage segmentation, testing bidirectional transfer between d

Region Seeding via Pre-Activation Regularization: A Geometric View of Piecewise Affine Neural Networks

arXiv:2605.06300v2 Announce Type: replace Abstract: Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine reg

Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs

arXiv:2605.10385v1 Announce Type: cross Abstract: Guided-diffusion black-box optimization (BO) has shown strong empirical performance on structured design problems such as molecules and crystals, but

Regret Minimization in Bilateral Trade With Perturbed Markets

arXiv:2605.10475v1 Announce Type: cross Abstract: We address the problem of maximizing Gain from Trade (GFT) in repeated buyer-seller exchanges subject to global budget balance constraints. While this

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

arXiv:2605.10759v1 Announce Type: cross Abstract: Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses ag

RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings

arXiv:2605.10706v1 Announce Type: new Abstract: We present a new class of efficient attention mechanisms applying universal 3D Relative Positional Encoding (RPE) methods given by arbitrary integrable

ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning

arXiv:2605.08639v1 Announce Type: new Abstract: Load imbalance is a long-standing challenge in Mixture-of-Experts (MoE) training and is exacerbated in reinforcement learning (RL) for LLMs, where hot e

Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems

arXiv:2605.09259v1 Announce Type: cross Abstract: Timbre transfer aims to modify the timbral identity of a musical recording while preserving the original melody and rhythm. While single-instrument ti

Representative Action Selection for Large Action Space Bandit Families

arXiv:2505.18269v5 Announce Type: replace Abstract: We study the problem of selecting a subset from a large action space shared by a family of bandits. In many natural situations, while the nominal se

Resource-Aware Evolutionary Neural Architecture Search for Cardiac MRI Segmentation

arXiv:2605.08238v1 Announce Type: cross Abstract: Cardiac magnetic resonance (CMR) segmentation underpins quantitative assessment of ventricular structure and function, yet reliable delineation remain

Restoration-Aligned Generative Flow Models for Blind Motion Deblurring

arXiv:2605.08854v1 Announce Type: new Abstract: Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deb

Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models

arXiv:2602.01698v3 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-tra

Rethinking Constraint Awareness for Efficient State Embedding of Neural Routing Solver

arXiv:2605.10122v1 Announce Type: new Abstract: Heavy-Encoder-Light-Decoder (HELD) neural routing solvers have emerged as a promising paradigm due to their broad applicability across multiple vehicle

Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning

arXiv:2605.08825v1 Announce Type: new Abstract: Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion an

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning

arXiv:2512.11470v2 Announce Type: replace-cross Abstract: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ funda

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models

arXiv:2602.11824v2 Announce Type: replace Abstract: Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visu

Revisiting Mixture Policies in Entropy-Regularized Actor-Critic

arXiv:2605.09157v1 Announce Type: cross Abstract: Mixture policies theoretically offer greater flexibility than unimodal policies in continuous action reinforcement learning, but the practical benefit

Revisiting the syntax of imperatives in Yemeni Arabic: An Agree across phases approach

arXiv:2605.08447v1 Announce Type: new Abstract: This article revisits the syntax of imperatives in Yemeni Arabic proposing an Agree acros phases (AAP) approach. I argue that the AAP approach successfu

RL Fine-Tuning Heals OOD Forgetting in SFT

arXiv:2509.12235v3 Announce Type: replace-cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (L

Robust Building Damage Detection in Cross-Disaster Settings Using Domain Adaptation

arXiv:2603.14694v2 Announce Type: replace-cross Abstract: Rapid structural damage assessment from remote sensing imagery is essential for timely disaster response. Within human-machine systems (HMS) f

S2P-Net: A Spectral-Spatial Polar Network for Rotation-Invariant Object Recognition in Low-Data Regimes

arXiv:2605.09667v1 Announce Type: cross Abstract: We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance

SAFformer:Improving Spiking Transformer via Active Predictive Filtering

arXiv:2605.08270v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) offer notable advantages in biological plausibility and energy efficiency, making them promising candidates for buildin

SAMOFT: Robust Multi-Object Tracking via Region and Flow

arXiv:2605.09417v1 Announce Type: new Abstract: Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent i

Sanity Checks for Long-Form Hallucination Detection

arXiv:2605.08346v1 Announce Type: cross Abstract: Hallucination detection methods for large language models increasingly operate on chain-of-thought reasoning traces, yet it remains unclear whether th

Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes

arXiv:2605.10681v1 Announce Type: cross Abstract: Forward error correction is essential for reliable communication over noisy channels. Attention-based model-free neural decoders have shown strong per

SciLT: Long-tailed Image Classification under Scientific Image Domains

arXiv:2604.03687v2 Announce Type: replace Abstract: Long-tailed recognition has benefited from foundation models and fine-tuning paradigms, yet existing studies and benchmarks are mainly confined to n

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

arXiv:2605.09630v1 Announce Type: new Abstract: Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants furth

SDG-MoE: Signed Debate Graph Mixture-of-Experts

arXiv:2605.08322v1 Announce Type: cross Abstract: Sparse MoE models achieve a good balance between capacity and compute by routing each token to a small subset of experts. However, in most MoE archite

SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis

arXiv:2605.09956v1 Announce Type: cross Abstract: High-quality, real-time talking head synthesis remains a fundamental challenge in computer vision. Existing reconstruction- and rendering-based method

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks

arXiv:2605.09038v1 Announce Type: new Abstract: Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especia

SeasonScapes: Learning Large-scale Re-lightable 3D Landscapes with Seasonal Variation from Sparse Webcams

arXiv:2605.09039v1 Announce Type: new Abstract: We introduce SeasonScapes framework and a the SeasonScapes dataset: Swiss Sparse-view Mountain Scenes with Seasonal Changes that covers over 50 km x 60

SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge

arXiv:2407.11906v3 Announce Type: replace Abstract: Surgical data science has seen rapid advancement with the excellent performance of end-to-end deep neural networks (DNNs). Despite their successes,

SEIS: Subspace-based Equivariance and Invariance Scores for Neural Representations

arXiv:2602.04054v2 Announce Type: replace-cross Abstract: Understanding how neural representations respond to geometric transformations is essential for evaluating whether learned features preserve me

Self-Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition

arXiv:2605.10466v1 Announce Type: new Abstract: Large language models (LLMs) exhibit two striking and ostensibly unrelated behaviours: in-context learning (ICL) and repetitive generation. In both, the

Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models

arXiv:2605.08145v1 Announce Type: cross Abstract: Current vision language models face hallucination and robustness issues against ambiguous or corrupted modalities. We hypothesize that these issues ca

Semantic Voting: Execution-Grounded Consensus for LLM Code Generation

arXiv:2605.08680v1 Announce Type: cross Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix