Search: “research”

Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions

arXiv:2110.12907v2 Announce Type: replace-cross Abstract: Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo (HMC) algorithm use Gaussian auxiliary momentum variables, which are

Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation

DGX agent

arXiv:2605.08210v1 Announce Type: new Abstract: Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and i

researcharxiv-cs-cv

12 May 2026

HEART: A High-Efficiency Adaptive Real-Time Telemonitoring Framework for Secure Electrocardiogram Signal Transmission Using Chaotic Encryption

arXiv:2605.08456v1 Announce Type: cross Abstract: The realtime analysis and secure transmission of electrocardiogram ECG signals are critical for accurate diagnosis and safeguarding patient privacy in

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds

arXiv:2605.10536v1 Announce Type: cross Abstract: Rare semantic innovations in high-dimensional, mission-critical domains are often obscured by dense background contexts, a challenge we define as exti

Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers

arXiv:2602.01442v3 Announce Type: replace-cross Abstract: Gradient-based attribution is the workhorse of mechanistic interpretability, yet whether it reliably tracks causal importance at the component

Hierarchical Attention-based Graph Neural Network with Relevance-driven Pruning

arXiv:2605.09308v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) excel at relational reasoning but face two persistent challenges: the lack of interpretable attribution for heterogeneous

Hierarchical Mixture-of-Experts with Two-Stage Optimization

arXiv:2605.08292v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models scale capacity by routing each token to a small subset of experts. However, their routers exhibit a fundamental

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

arXiv:2512.21815v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertaint

High-probability zeroth-order online convex optimisation beyond Euclidean geometry

arXiv:2509.21484v3 Announce Type: replace Abstract: We study online convex optimisation with ell_q-Lipschitz losses, ell_p-regularised FTRL, and randomised two-point finite-difference gradient estimat

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

arXiv:2504.10766v2 Announce Type: replace-cross Abstract: As the post-training of large language models (LLMs) advances from instruction-following to complex reasoning tasks, understanding how differe

How Mobile World Model Guides GUI Agents?

arXiv:2605.10347v1 Announce Type: new Abstract: Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable predi

How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits

arXiv:2605.08348v1 Announce Type: new Abstract: The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by

researcharxiv-cs-cl

How open model ecosystems compound

This article examines how open-source AI model ecosystems create compounding effects through community contributions, fine-tuning, and iterative improvements that accelerate innovation and accessibili

researchinterconnects

How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue

arXiv:2605.10199v1 Announce Type: new Abstract: Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (

researcharxiv-cs-cl

How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors

arXiv:2605.08817v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) recently thrives in large language model (LLM) reasoning tasks. However, the reward sparsity and t

Hyperbolic Distillation: Geometry-Guided Cross-Modal Transfer for Robust 3D Object Detection

arXiv:2605.09899v1 Announce Type: cross Abstract: Cross-modal knowledge distillation has emerged as an effective strategy for integrating point cloud and image features in 3D perception tasks. However

Hypergraph-Enhanced Training-Free and Language-Free Few-Shot Anomaly Detection

arXiv:2605.10628v1 Announce Type: new Abstract: Few-shot anomaly detection (FSAD) has made significant strides, yet existing methods still face critical challenges: (i) dependence on task- or dataset-

Hyperparameter Transfer for Dense Associative Memories

arXiv:2605.10164v1 Announce Type: new Abstract: Dense Associative Memory (DenseAM) is a promising family of AI architectures that is represented by a neural network performing temporal dynamics on an

HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation

arXiv:2605.10100v1 Announce Type: cross Abstract: We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperb

HyperTransport: Amortized Conditioning of T2I Generative Models

arXiv:2605.08254v1 Announce Type: cross Abstract: As foundation models grow in capability, the ability to efficiently and reliably control their behavior becomes critical. Fine-tuning these models can

ICT-NLP at SemEval-2026 Task 3: Less Is More -- Multilingual Encoder with Joint Training and Adaptive Ensemble for Dimensional Aspect Sentiment Regression

arXiv:2605.10560v1 Announce Type: new Abstract: This paper describes our system to SemEval-2026 Task 3 Track A Subtask 1 on Dimensional Aspect Sentiment Regression (DimASR). We propose a lightweight a

researcharxiv-cs-cl

Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API Access

arXiv:2605.10407v1 Announce Type: new Abstract: Modern LLM APIs often reveal only top-K logit scores and censor the remaining vocabulary. We study the per-position distribution-recovery limits of this

Impact of Connectivity on Laplacian Representations in Reinforcement Learning

arXiv:2603.08558v2 Announce Type: replace Abstract: Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-sc

Implicit Hypothesis Testing and Divergence Preservation in Neural Network Representations

arXiv:2601.20477v3 Announce Type: replace Abstract: We study the training dynamics of neural classifiers through the lens of binary hypothesis testing. We re-formalize classification as a collection o

Improved Mean Flows: On the Challenges of Fastforward Generative Models

arXiv:2512.02012v2 Announce Type: replace Abstract: MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key chal

Improving Temporal Action Segmentation via Constraint-Aware Decoding

arXiv:2605.10149v1 Announce Type: new Abstract: Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challe

In KAME, a fast speech model starts replying instantly, while a backend LLM runs in parallel to inject deep knowledge on the fly. It’s a com…

In KAME, a fast speech model starts replying instantly, while a backend LLM runs in parallel to inject deep knowledge on the fly. It’s a completely different way to approach conversational AI, making

researchdavid-ha--x

Incorporating rank-free coupling and external field via an incoherent modulated spatial photonic Ising machine

arXiv:2512.21587v2 Announce Type: replace-cross Abstract: Spatial photonic Ising machines offer a novel optical platform for optimization and spin-model simulation, but existing diffraction-based sche

Increasing the Efficiency of DETR for Maritime High-Resolution Images

arXiv:2605.10269v1 Announce Type: new Abstract: Maritime object detection is critical for the safe navigation of unmanned surface vessels (USVs), requiring accurate recognition of obstacles from small

INFANiTE: Implicit Neural representation for high-resolution Fetal brain spatio-temporal Atlas learNing from clinical Thick-slicE MRI

arXiv:2605.09977v1 Announce Type: new Abstract: Spatio-temporal fetal brain atlases are important for characterizing normative neurodevelopment and identifying congenital anomalies. However, existing

Infinite Mask Diffusion for Few-Step Distillation

arXiv:2605.10518v1 Announce Type: cross Abstract: Masked Diffusion Models (MDMs) have emerged as a promising alternative to autoregressive models in language modeling, offering the advantages of paral

Instance-Adaptive Online Multicalibration

arXiv:2605.09273v1 Announce Type: new Abstract: We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-ca

Integrated Hierarchical Decision-Making in Inverse Kinematic Planning and Control

arXiv:2412.01324v4 Announce Type: replace Abstract: This work presents a novel and efficient nonlinear programming framework that tightly integrates hierarchical decision-making with whole-body invers

researcharxiv-cs-ro

Interpretable Coreference Resolution Evaluation Using Explicit Semantics

arXiv:2605.10627v1 Announce Type: cross Abstract: Coreference resolution is typically evaluated using aggregate statistical metrics such as CoNLL-F1, which measure structural overlap between predicted

Interpretable Machine Learning for Football Performance Analysis: Evidence of Limited Transferability from Elite Leagues to University Competition

arXiv:2605.10796v1 Announce Type: new Abstract: Machine learning has become increasingly prevalent in football performance analysis, yet most studies prioritize predictive accuracy while implicitly as

Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs

arXiv:2605.10633v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignm

Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds

arXiv:2605.09238v1 Announce Type: cross Abstract: Muon and related norm-constrained matrix optimizers have become central to large-scale learning problems. They are formulated as a linear maximization

Inverse Design for Conditional Distribution Matching

arXiv:2605.09439v1 Announce Type: new Abstract: Generative models are powerful tools for sampling from a learned distribution P(Y mid X), and inverse-design methods invert this map to find an input x

Is Data Shapley Not Better than Random in Data Selection? Ask NASH

arXiv:2605.10684v1 Announce Type: cross Abstract: Data selection studies the problem of identifying high-quality subsets of training data. While some existing works have considered selecting the subse

It's All Connected: Topology-Aware Structural Graph Encoding Improves Performance on Polymer Prediction

arXiv:2605.10551v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have achieved strong results in molecular property prediction, but polymers present distinct challenges: labeled datasets a

Joint sparse coding and temporal dynamics support context reconfiguration

arXiv:2605.10178v1 Announce Type: cross Abstract: Adaptive behavior requires the brain to transition between distinct contexts while maintaining representations of prior experience. The ability to rec

Kaczmarz Linear Attention

arXiv:2605.08587v1 Announce Type: cross Abstract: Long-context language modeling remains central to modern sequence modeling, but the quadratic cost of Transformer attention makes scaling computationa

Kernel-Gradient Drifting Models

arXiv:2605.10727v1 Announce Type: new Abstract: We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting model

Key-Value Means

arXiv:2605.09877v1 Announce Type: cross Abstract: We present Key-Value Means ('KVM'), a novel block-recurrence for attention that can accommodate either fixed-size or growing state. Equipping a strong

Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech

arXiv:2605.09386v1 Announce Type: cross Abstract: Metric-induced discrete flow matching (MI-DFM) exploits token-latent geometry for discrete generation, but its practical use is limited by two issues:

Kinetic theory for Transformers and the lost-in-the-middle phenomenon

arXiv:2605.09213v1 Announce Type: cross Abstract: We study causal self-attention dynamics -- a toy model for decoder Transformers -- which we interpret as a non-exchangeable interacting particle syste

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation

arXiv:2605.10253v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is a widely adopted paradigm for enhancing LLMs in medical applications by incorporating expert multimodal knowle

L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation

arXiv:2605.08806v1 Announce Type: new Abstract: Existing 2D-3D lifting human pose estimation methods have achieved strong performance. But the utilization of historical pose representations across net