Search: “research”

ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models

arXiv:2605.08612v1 Announce Type: new Abstract: Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual

researcharxiv-cs-ro

Research

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval

DGX agent

arXiv:2605.09644v1 Announce Type: new Abstract: Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global att

researcharxiv-cs-cv

12 May 2026

Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography

arXiv:2605.10871v1 Announce Type: cross Abstract: This work proposes Attractor-Vascular Coupling Theory (AVCT), a mathematical framework showing that cardiac attractor geometry encodes blood pressure

Attribution-based Explanations for Markov Decision Processes

arXiv:2605.09780v1 Announce Type: new Abstract: Attribution techniques explain the outcome of an AI model by assigning a numerical score to its inputs. So far, these techniques have mainly focused on

AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs

arXiv:2509.08031v3 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) are rapidly advancing, but evaluating them remains challenging due to inefficient and non-standardized too

Augmented Equivariant Mesh Networks for Anatomical Segmentation

arXiv:2605.08172v1 Announce Type: new Abstract: Anatomical mesh segmentation requires models that operate directly on irregular surface geometry while remaining robust to arbitrary patient pose and me

Automated conjecturing with TxGraffiti

arXiv:2409.19379v2 Announce Type: replace-cross Abstract: TxGraffiti is a data-driven, heuristic-based computer program developed to automate the process of generating conjectures across various mathe

Automated Detection of Abnormalities in Zebrafish Development

arXiv:2605.10464v1 Announce Type: new Abstract: Zebrafish embryos are a valuable model for drug discovery due to their optical transparency and genetic similarity to humans. However, current evaluatio

Automated high-frequency quantification of fish communities and biomass using computer vision

arXiv:2605.10449v1 Announce Type: new Abstract: Quantifying fish community structure is essential for understanding biodiversity and ecosystem responses in a changing environment, yet existing survey

Automated Robotic Moisture Monitoring in Agricultural Fields

arXiv:2605.09050v1 Announce Type: cross Abstract: Monitoring moisture level of land in a large-scale plantation is tedious. The main objective of this project is to use a robotic kit in collaboration

AxiomOcean: Forecasting the Three-Dimensional Structure of the Upper Ocean

arXiv:2605.10455v1 Announce Type: new Abstract: Short-term ocean forecast skill depends strongly on the three-dimensional ocean structure of the upper ocean, which governs stratification, subsurface h

BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models

arXiv:2605.08110v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become the standard for fine-tuning large pre-trained models at reduced computational cost. However, its low-rank point

Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization

arXiv:2605.08214v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) and speaker diarization in Bangla remain challenging due to long form recordings, diverse acoustic conditions, and

BaseCal: Unsupervised Confidence Calibration via Base Model Signals

arXiv:2601.03042v4 Announce Type: replace Abstract: Reliable confidence is essential for trusting the outputs of LLMs, yet widely deployed post-trained LLMs (PoLLMs) typically compromise this trust wi

Batch Bayesian Active Learning with Partial Batch Label Sampling

arXiv:2510.09877v3 Announce Type: replace-cross Abstract: Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice o

Bayesian Optimization with Structured Measurements: A Vector-Valued RKHS Framework

arXiv:2605.09775v1 Announce Type: new Abstract: Bayesian optimization (BO) is an efficient framework for optimizing expensive black-box functions. However, it is typically formulated as learning an en

Bayesian Reasoning for Physics Informed Neural Networks

arXiv:2308.13222v3 Announce Type: replace-cross Abstract: We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights b

BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction

arXiv:2605.09662v1 Announce Type: new Abstract: Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene do not optimize the underlying 3D geometry, making object-leve

Benchmarking ResNet Backbones in RT-DETR: Impact of Depth and Regularization under environmental conditions

arXiv:2605.08136v1 Announce Type: cross Abstract: Visual perception plays a central role in competitive robotics, where environmental variations can directly affect real-time detection performance. Th

Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis

arXiv:2407.12173v2 Announce Type: replace-cross Abstract: Generative diffusion models have emerged as a powerful tool for high-quality image synthesis, yet their iterative nature demands significant c

BetaEdit: Null-Space Constrained Sequential Model Editing

arXiv:2605.09285v1 Announce Type: new Abstract: Null-space-based methods have garnered considerable attention in model editing by constraining updates to the null space of the pre-existing knowledge r

Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editing

arXiv:2601.15686v2 Announce Type: replace Abstract: Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, edits ar

Beyond Majority Voting: Agreement-Based Clustering to Model Annotator Perspectives in Subjective NLP Tasks

arXiv:2605.09955v1 Announce Type: new Abstract: Disagreement in annotation is a common phenomenon in the development of NLP datasets and serves as a valuable source of insight. While majority voting r

Beyond Nearest Neighbor Interpolation in Data Augmentation

arXiv:2504.01527v2 Announce Type: replace Abstract: Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation err

Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure

arXiv:2605.10438v1 Announce Type: cross Abstract: Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership a

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenizatio

arXiv:2605.10780v1 Announce Type: cross Abstract: Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quali

Beyond Thinking: Imagining in 360^irc for Humanoid Visual Search

arXiv:2605.09146v1 Announce Type: new Abstract: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360^irc environments. While prior methods treat this as a monolithic task rel

Black-Box Detection of LLM-Generated Text Using Generalized Jensen-Shannon Divergence

arXiv:2510.07500v2 Announce Type: replace Abstract: We study black-box detection of machine-generated text under practical constraints: the scoring model (proxy LM) may mismatch the unknown source mod

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models

arXiv:2605.09134v1 Announce Type: new Abstract: Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually f

Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction

arXiv:2603.04783v2 Announce Type: replace Abstract: While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

arXiv:2605.10195v1 Announce Type: new Abstract: Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving compl

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning

arXiv:2605.08862v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constit

Building Korean linguistic resource for NLU data generation of banking app CS dialog system

arXiv:2605.10241v1 Announce Type: new Abstract: Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increa

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing

arXiv:2504.21228v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are susceptible to indirect prompt injection attacks, where the model inadvertently responds to instructions inje

CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting

arXiv:2605.09279v1 Announce Type: cross Abstract: Volumetric video (VV) streaming enables real-time, immersive access to remote 3D environments, powering telepresence, ecological monitoring, and robot

CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking

arXiv:2605.09245v1 Announce Type: new Abstract: Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives,

Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges

arXiv:2605.09702v1 Announce Type: cross Abstract: Multi-judge evaluation is increasingly used to assess LLMs and reward models, and the prevailing heuristic is to curate: keep the most accurate judges

Can Language Models Analyze Data? Evaluating Large Language Models for Question Answering over Datasets

arXiv:2605.10419v1 Announce Type: cross Abstract: This paper investigates the effectiveness of large language models (LLMs) in answering questions over datasets. We examine their performance in two sc

Can Language Models Identify Side Effects of Breast Cancer Radiation Treatments?

arXiv:2605.08439v1 Announce Type: new Abstract: Accurately communicating the side effects of cancer treatments to cancer survivors is critical, particularly in settings such as informed consent, where

Can MLLMs Reason About Visual Persuasion? Evaluating the Efficacy and Faithfulness of Reasoning

arXiv:2605.08965v1 Announce Type: new Abstract: Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains ch

Can Muon Fine-tune Adam-Pretrained Models?

arXiv:2605.10468v1 Announce Type: new Abstract: Muon has emerged as an efficient alternative to Adam for pretraining, yet remains underused for fine-tuning. A key obstacle is that most open models are

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

arXiv:2605.06638v2 Announce Type: replace Abstract: Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with t

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing

arXiv:2605.10794v1 Announce Type: cross Abstract: Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidd

cantnlp@DravidianLangTech 2026: organic domain adaptation improves multi-class hope speech detection in Tulu

arXiv:2605.09795v1 Announce Type: new Abstract: This paper presents our systems and results for the Hope Speech Detection in Code-Mixed Tulu Language shared task at the Sixth Workshop on Speech, Visio

CAST: Channel-Aware Spatial Transfer Learning with Pseudo-Image Radar for Sign Language Recognition

arXiv:2605.08663v1 Announce Type: new Abstract: We propose CAST, a dual-stream architecture that utilizes channel-aware spatial transfer learning for isolated sign language recognition addressing the

CATO: Charted Attention for Neural PDE Operators

arXiv:2605.09016v1 Announce Type: new Abstract: Neural operators have emerged as powerful data-driven solvers for PDEs, offering substantial acceleration over classical numerical methods. However, exi

CATS: Curvature Aware Temporal Selection for efficient long video understanding

arXiv:2605.09223v1 Announce Type: new Abstract: Understanding long videos with multimodal large language models (MLLMs) requires selecting a small subset of informative frames under strict computation

Causal Parametric Drift Simulation: A Digital Twin Framework for Classifier Robustness Evaluation

arXiv:2605.09663v1 Announce Type: cross Abstract: Machine learning classifiers in dynamic environments face concept drift -- changes in the data-generating process that degrade performance. Convention