research

Convergent Representations of Linguistic Constructions in Human and Artificial Neural Systems

arXiv:2603.29617v2 Announce Type: replace-cross Abstract: Understanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent comput

Research

Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas

DGX agent

arXiv:2605.15848v1 Announce Type: cross Abstract: Conversational interfaces powered by large language models (LLMs) are widely used for ideation and analysis, yet their linear structure limits explora

researcharxiv-cs-cl

18 May 2026

CrystalBoltz: End-to-End Protein Structure Determination via Experiment-Guided Diffusion for X-Ray Crystallography

arXiv:2605.15564v1 Announce Type: new Abstract: Generative models trained on public databases of protein structures, most of which have been determined by X-ray crystallography, now provide powerful p

CUBE: Contrastive Understanding by Balanced Experiments

arXiv:2509.10825v5 Announce Type: replace-cross Abstract: Explaining a trained model requires a clear account of how explanatory evidence is generated. We propose CUBE, a post-hoc explanation framewor

DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer

arXiv:2605.15681v1 Announce Type: cross Abstract: Recently, diffusion-based material transfer methods rely on image fine-tuning or complex architectures with auxiliary networks but face challenges suc

Decision making was the bottleneck all along. Productivity is the rate at which you make open-ended decisions, the rate at which you reduce …

researchfrancois-chollet--x

Francois Chollet argues that decision-making, rather than execution, is the true limiting factor in productivity. He defines productivity as the rate at which one makes open-ended decisions and reduce

DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation

arXiv:2605.15728v1 Announce Type: cross Abstract: Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. Howeve

Degradation-Aware Blur-Segmentation of Brain Tumor

arXiv:2605.15671v1 Announce Type: cross Abstract: Multimodal 3D MRI brain tumor segmentation is a pivotal step in radiotherapy target delineation, surgical planning and post-treatment assessment. Exis

Density Estimation via Binless Multidimensional Integration

arXiv:2407.08094v3 Announce Type: replace-cross Abstract: We introduce the Binless Multidimensional Thermodynamic Integration (BMTI) method for nonparametric, robust, and data-efficient density estima

Designing for Robot Wranglers: A Synthesis of Literature and Practice

arXiv:2605.15892v1 Announce Type: new Abstract: Robots are increasingly present in human spaces, such as for conducting deliveries in hospitals, interacting with visitors at museums, and stocking item

researcharxiv-cs-ro

DiLA: Disentangled Latent Action World Models

arXiv:2605.15725v1 Announce Type: cross Abstract: Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However

DIPA: Distilled Preconditioned Algorithms for Solving Imaging Inverse Problems

arXiv:2605.15456v1 Announce Type: cross Abstract: Solving imaging inverse problems has usually been addressed by designing proper prior models of the underlying signal. However, minimizing the data fi

DiscoExplorer: An Open Interface for the Study of Multilingual Discourse Relations

arXiv:2605.15304v1 Announce Type: new Abstract: The relations connecting propositions in discourse such as cause (A because B) or concession (A although B) are a subject of intense interest in Computa

Do Chinese models speak Chinese languages?

arXiv:2504.00289v3 Announce Type: replace-cross Abstract: The release of top-performing open-weight LLMs has cemented China's role as a leading force in AI development. Do these models support languag

DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding

arXiv:2605.15542v1 Announce Type: new Abstract: GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability in understanding and executing user instructions.

Dynamics-Level Watermarking of Flow Matching Models with Random Codes

arXiv:2605.16239v1 Announce Type: new Abstract: We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the wate

Effective Harness Engineering for Algorithm Discovery with Coding Agents

arXiv:2605.15221v1 Announce Type: cross Abstract: AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm d

Efficient Image Synthesis with Sphere Latent Encoder

arXiv:2605.15592v1 Announce Type: new Abstract: Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Desp

Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking

arXiv:2510.04930v2 Announce Type: replace Abstract: Grokking is the phenomenon whereby, unlike the training performance, which peaks early in the training process, the test/generalization performance

Empowering Robot Teleoperation: Exploring the Synergies Between Devices and Manipulator Controllers in a Comparative Study

arXiv:2511.07720v2 Announce Type: replace Abstract: Robot learning empowers the robot system with human brain-like intelligence to autonomously acquire and adapt skills through experience, enhancing f

researcharxiv-cs-ro

Enabling Adversarial Robustness in AI Models through Kubeflow MLOps

arXiv:2605.15249v1 Announce Type: cross Abstract: AI models are increasingly deployed in cloud-native environments to support scalable and automated services. However, while platforms such as Kubernet

EndoGSim: Physics-Aware 4D Dynamic Endoscopic Scene Simulations via MLLM-Guided Gaussian Splatting

arXiv:2605.16022v1 Announce Type: new Abstract: In robot-assisted minimally invasive surgery, high-fidelity dynamic endoscopic scene reconstruction and simulation are crucial to enhancing downstream t

Enhancing Medical Image Segmentation via Heat Conduction Equation

arXiv:2511.03260v2 Announce Type: replace Abstract: Medical image segmentation models struggle to achieve efficient global context modeling and long-range dependency reasoning under practical computat

Entropic Auto-Encoding via Implicit Free-Energy Minimization

arXiv:2605.16164v1 Announce Type: new Abstract: Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectiv

Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrodinger Samplers

arXiv:2605.16126v1 Announce Type: cross Abstract: For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few functio

Entropy-Based Characterisation of the Polarised Regime in Latent Variable Models

arXiv:2605.15965v1 Announce Type: new Abstract: Variational Autoencoders (VAEs) often exhibit a polarised regime in which latent variables separate into active, passive, and mixed subsets. Existing cr

Evaluating Design Video Generation: Metrics for Compositional Fidelity

arXiv:2605.16223v1 Announce Type: cross Abstract: Generative video models are increasingly used in design animation tasks, yet no standardized evaluation framework exists for this domain. Unlike natur

Evaluation of Anatomical Shape Priors in Deep Learning-Based Cardiac Multi-Compartment Segmentation

arXiv:2605.15707v1 Announce Type: cross Abstract: Whole-heart multi-compartment CT segmentation is clinically important, but standard CNNs do not explicitly enforce anatomical plausibility. Based on s

Extrapolation Guarantees for Perturbation Modeling Under the Additive Latent Shift Assumption

arXiv:2504.18522v3 Announce Type: replace-cross Abstract: We consider the problem of modeling the effects of perturbations like gene knockouts on measurements such as single-cell RNA counts. Given dat

Fault tolerance estimation in digital circuits with visualised generative networks

arXiv:2605.15212v1 Announce Type: cross Abstract: We propose a new numerical method to estimate the fault tolerance of failure modes in digital circuit structures with a generative network sampling te

Few-Step Diffusion Language Models via Trajectory Self-Distillation

arXiv:2602.12262v3 Announce Type: replace Abstract: Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decodin

Flatness-based trajectory planning for 3D overhead cranes with friction compensation and collision avoidance

arXiv:2510.24457v2 Announce Type: replace Abstract: This paper presents an optimal trajectory generation method for 3D overhead cranes by leveraging differential flatness. This framework enables the d

researcharxiv-cs-ro

Fluency and Faithfulness in Human and Machine Literary Translation

arXiv:2605.15282v1 Announce Type: new Abstract: Literary translation requires balancing target-language fluency with faithfulness to the source. Recent large language models (LLMs) often produce fluen

Frequency-domain Event-based Imaging for Selective Surveillance

arXiv:2605.15392v1 Announce Type: cross Abstract: Event-based cameras (EBCs) are an attractive sensing modality for surveillance due to their reporting of pixel-level radiance changes with microsecond

From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding

arXiv:2605.15951v1 Announce Type: new Abstract: Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grou

From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation

arXiv:2605.16026v1 Announce Type: cross Abstract: Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performan

From Guidelines to Guarantees: A Graph-Based Evaluation Harness for Domain-Specific Evaluation of LLMs

arXiv:2508.20810v3 Announce Type: replace Abstract: Rigorous evaluation of domain-specific language models requires benchmarks that are comprehensive, contamination-resistant, and maintainable. Static

From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares Certificates

arXiv:2605.15445v1 Announce Type: new Abstract: Automated proving of polynomial inequalities is a fundamental challenge in automated mathematical reasoning, where rich algebraic structure and a rapidl

From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint

arXiv:2605.15862v1 Announce Type: new Abstract: Adaptive biomechanical systems may show similar observable gait performance while differing in latent organization and longitudinal behavior. This study

FSCM: Frequency-Enhanced Spatial-Spectral Coupled Mamba for Infrared Hyperspectral Image Colorization

arXiv:2605.15880v1 Announce Type: cross Abstract: Thermal infrared imaging is robust to illumination variations and smoke interference, making it important for all-weather perception. However, the lac

GenAI-Driven Approach to RISC-V Supply Chain Exploration

arXiv:2605.15223v1 Announce Type: cross Abstract: This paper presents an LLM-empowered workflow for RISC-V supply chain analysis, integrating Vision-Language Models (VLMs) and Model-Driven Engineering

Generative Long-term User Interest Modeling for Click-Through Rate Prediction

arXiv:2605.15905v1 Announce Type: cross Abstract: Modeling long-term user interests with massive historical user behaviors enhances click-through rate (CTR) prediction performance in advertising and r

GeoGS-CE: Learning Delay--Beam Channel Priors with 3D Gaussians for High-Mobility Scenarios

arXiv:2605.16094v1 Announce Type: cross Abstract: Wideband channel estimation (CE) in high-mobility scenarios remains challenging because channel responses vary rapidly, while practical systems can al

GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction

arXiv:2605.15852v1 Announce Type: new Abstract: Streaming 3D reconstruction from long monocular video sequences requires maintaining a key-value (KV) cache that grows linearly with sequence length, cr

Gradient-Based Join Ordering

arXiv:2511.14482v2 Announce Type: replace-cross Abstract: Join ordering is the NP-hard problem of selecting the most efficient order in which to evaluate joins (conjunctive, binary operators) in a dat

GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions

arXiv:2605.15764v1 Announce Type: cross Abstract: Understanding social interactions requires reasoning over subtle non-verbal cues, yet current multimodal large language models (MLLMs) often fail to i

Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets

arXiv:2605.15787v1 Announce Type: cross Abstract: Why does a Transformer that has memorized its training set wait thousands of steps before it generalizes? Existing accounts locate this delay in norm

Hallucinations are inevitable but can be made statistically negligible

arXiv:2502.12187v3 Announce Type: replace Abstract: Hallucinations, a phenomenon where a language model (LM) generates nonfactual content, pose a significant challenge to the practical deployment of L