Search: “research”

Ambient-robust Inverse Rendering using Active RGB-NIR Imaging

arXiv:2605.30250v1 Announce Type: new Abstract: Inverse rendering aims to reconstruct geometry and reflectance of objects from images. Despite recent progress, existing methods often produces inaccura

An accuracy-aware extension to LRP-based pruning for CNNs to prevent cascading accuracy degradation in data-scarce transfer learning

DGX agent

arXiv:2511.10861v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) pre-trained on large-scale datasets such as ImageNet are widely used as feature extractors to construct h

researcharxiv-cs-ai

29 May 2026

Analyzing Persona Effects in Generated Explanations from Multimodal LLM Agents in Urban Perception

arXiv:2605.29064v1 Announce Type: new Abstract: We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations fr

researcharxiv-cs-cl

Anchorless Diversification for Parallel LLM Ideation

arXiv:2605.30150v1 Announce Type: new Abstract: LLMs are increasingly used to generate candidate-idea pools for creative tasks where broad exploration is valuable. Parallel inference can be attractive

Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables

arXiv:2605.30229v1 Announce Type: new Abstract: We use a mean-field-based transformer model to theoretically investigate how auxiliary variables, such as positional encoding, prevent mode collapse of

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

arXiv:2605.29488v1 Announce Type: cross Abstract: Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are

Approximate Proportionality in Online Fair Division

arXiv:2508.03253v2 Announce Type: replace-cross Abstract: We study the online fair division problem, where indivisible goods arrive sequentially and must be allocated immediately and irrevocably. Prio

Archon: A Unified Multimodal Model for Holistic Digital Human Generation

arXiv:2605.30311v1 Announce Type: cross Abstract: Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visu

Model Releases

AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materials

model-releasesarxiv-cs-ai

arXiv:2510.04704v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to propert

Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics

arXiv:2605.29351v1 Announce Type: new Abstract: We study minimal attention-only transformers under all-token corruption and show they admit a two-stage empirical Bayes interpretation. A single attenti

Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurements

arXiv:2510.27663v3 Announce Type: replace-cross Abstract: Modern imaging techniques heavily rely on Bayesian statistical models to address difficult image reconstruction and restoration tasks. This pa

Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction

arXiv:2605.29168v1 Announce Type: new Abstract: Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic operatio

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

arXiv:2605.30231v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-ans

Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?

arXiv:2510.16060v2 Announce Type: replace-cross Abstract: The recent development of foundation models for time series data has generated considerable interest in using such models across a variety of

Beyond MSE: Improving Precipitation Nowcasting with Multi-Quantile Regression

arXiv:2605.30122v1 Announce Type: cross Abstract: Deep-learning precipitation nowcasting models are often optimized using pointwise losses such as mean squared error or mean absolute error, which can

Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR

arXiv:2602.12642v2 Announce Type: replace-cross Abstract: Reward-maximizing RL methods have shown to be capable of enhancing the reasoning performance of LLMs, but often lead to reduced generation div

BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression

arXiv:2605.29583v1 Announce Type: new Abstract: High-capacity watermarking is necessary for 3D Gaussian Splatting (3DGS) assets to embed rich information (e.g., ownership, provenance, and authenticati

Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation

arXiv:2605.30269v1 Announce Type: new Abstract: Over the past decades, numerous Image Quality Assessment (IQA) models have emerged, aiming to predict the perceptual quality of images. However, individ

Boosting Zero-Shot 3D Style Transfer with 2D Pre-trained Priors

arXiv:2605.30065v1 Announce Type: new Abstract: In this work, we focus on zero-shot 3D style transfer that can generate multi-view consistent stylized views of the 3D scene given an arbitrary style im

Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm

arXiv:2603.26668v2 Announce Type: replace-cross Abstract: As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the

Bridging Chemists and AI: An Expert-Augmented Framework for Interpretable Route Evaluation

arXiv:2605.29108v1 Announce Type: new Abstract: Selecting efficient multi-step synthetic routes is a central challenge in organic synthesis, particularly in medicinal and process chemistry, where rout

Bridging Functional and Representational Similarity via Usable Information

arXiv:2601.21568v2 Announce Type: replace Abstract: We present a unified framework for quantifying the similarity between representations through the lens of extit{usable} information, offering a rigo

Calibrating Generative Models to Distributional Constraints

arXiv:2510.10020v4 Announce Type: replace-cross Abstract: Generative models frequently suffer miscalibration, wherein statistics of the sampling distribution, such as the fraction of generations in a

CapTalk: Text-Guided Stylization and Speech-Driven 3D Head Animation

arXiv:2605.29316v1 Announce Type: new Abstract: Audio-driven 3D facial animation aims to generate synchronized lip movements and vivid facial expressions from arbitrary audio clips. While existing met

Causal Label Recovery in Payment Networks

arXiv:2605.29272v1 Announce Type: cross Abstract: Fraud detection models in payment networks train on chargeback labels that are systematically biased. Every label must survive three sequential gates:

CCS: Clinical Consensus Selection for Radiology Report Generation

arXiv:2605.30131v1 Announce Type: new Abstract: Radiology report generation (RRG) is commonly formulated as a single-path generation task, where a multimodal large language model (MLLM) produces one d

researcharxiv-cs-cl

Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing

arXiv:2605.29809v1 Announce Type: cross Abstract: Large-scale text-to-image (T2I) diffusion models have enabled unprecedented creative applications, but their unauthorized use has raised serious intel

City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images

arXiv:2605.30310v1 Announce Type: cross Abstract: City-scale 3D surface reconstruction from multiview images for downstream 3D simulation, poses highly challenging problems due to the scale and comple

Model Releases

CLUBench: A Clustering Benchmark

model-releasesarxiv-cs-lg

arXiv:2605.29933v1 Announce Type: new Abstract: Clustering is a fundamental problem in data science with a long-standing research history, yielding numerous insightful algorithms. Despite this progres

Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models

arXiv:2605.29607v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free

Coarse-Grained Boltzmann Generators

arXiv:2602.10637v2 Announce Type: replace Abstract: Sampling equilibrium molecular configurations from the Boltzmann distribution is a longstanding challenge. Boltzmann Generators (BGs) address this b

Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning

arXiv:2604.06805v2 Announce Type: replace Abstract: Multi-step Chain-of-Thought (CoT) has significantly advanced the mathematical reasoning capabilities of LLMs by leveraging explicit reasoning steps.

researcharxiv-cs-cl

CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning

arXiv:2605.29602v1 Announce Type: new Abstract: Multi-modal Retrieval-Augmented Generation (MMRAG) has emerged as a powerful paradigm for enhancing Multimodal Large Language Models in knowledge-intens

CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval

arXiv:2605.29271v1 Announce Type: new Abstract: Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the

Collaborative Threshold Watermarking

arXiv:2602.10765v2 Announce Type: replace Abstract: In federated learning (FL), K clients jointly train a model without sharing raw data. Because each participant invests data and compute, clients nee

COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings

arXiv:2605.29628v1 Announce Type: cross Abstract: Contrastive Language-Audio Pretraining (CLAP) models are widely used for audio understanding and support modality-agnostic condition swapping in many

Comment on 'Spin-1/2 Kagome Heisenberg Antiferromagnet: Machine Learning Discovery of the Spinon Pair-Density-Wave Ground State'

arXiv:2605.28861v1 Announce Type: cross Abstract: A recent article [Phys. Rev. X 15, 011047 (2025)] utilizes group-equivariant convolutional neural networks to study the ground state of the kagome Hei

Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection

arXiv:2605.28977v1 Announce Type: cross Abstract: Recent advances in deep learning have enabled increasingly accurate electroencephalography (EEG)-based classification of Major Depressive Disorder (MD

Computational Modeling of Antibody-Antigen Complexes: PLM-Based and MSA-Based Approaches

arXiv:2605.28886v1 Announce Type: cross Abstract: Antibodies play a central role in the immune response by specifically recognizing and neutralizing antigens, and therapeutic antibodies have become ma

Computationally Efficient Replicable Learning of Parities and Applications

arXiv:2602.09499v2 Announce Type: replace Abstract: We study the computational relationship between replicability (Impagliazzo et al. [STOC `22], Ghazi et al. [NeurIPS `21]) and other stability notion

Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits

arXiv:2605.29268v1 Announce Type: cross Abstract: LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existing system

Conf-Gen: Conformal Uncertainty Quantification for Generative Models

arXiv:2605.28920v1 Announce Type: cross Abstract: Conformal prediction (CP) and its extension, conformal risk control (CRC), are established frameworks for quantifying uncertainty in supervised machin

Conformal Certification of Reasoning Trace Prefixes

arXiv:2605.30085v1 Announce Type: new Abstract: Language model reasoning traces are rarely all-or-nothing; they frequently contain valid intermediate steps before a critical error occurs. Existing unc

Constructing efficient channels for ideal observers using the conjugate gradient method

arXiv:2605.29415v1 Announce Type: cross Abstract: Task-based assessment of image quality (IQ) is critically important for the design and optimization of medical imaging systems. Ideal observers, inclu

Context Distillation as Latent Memory Management

arXiv:2605.28889v1 Announce Type: cross Abstract: Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories

Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models

arXiv:2605.28866v1 Announce Type: cross Abstract: Token-based time series large language models (TS-LLMs) have emerged as a promising direction for time series analysis and reasoning. However, prior s

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting

arXiv:2510.02480v3 Announce Type: replace Abstract: Large language models (LLMs) can be influenced by harmful or irrelevant context, which can significantly harm model performance on downstream tasks.

Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability

arXiv:2605.30103v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as generators in iterative neural architecture search (NAS), yet no formal convergence theory exists