research

Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network

arXiv:2604.10016v1 Announce Type: cross Abstract: Solar eruptions, including flares and coronal mass ejections (CMEs), have a significant impact on Earth. Some flares are associated with CMEs, and som

Research

Preference Learning Unlocks LLMs' Psycho-Counseling Skills

DGX agent

arXiv:2502.19731v2 Announce Type: replace Abstract: Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between p

researcharxiv-cs-cl

14 Apr 2026

PrefPaint: Enhancing Medical Image Inpainting through Expert Human Feedback

arXiv:2506.21834v2 Announce Type: replace Abstract: Inpainting, the process of filling missing or corrupted image parts, has broad applications in medical imaging. However, generating anatomically acc

Prints in the Magnetic Dust: Robust Similarity Search in Legacy Media Images Using Checksum Count Vectors

arXiv:2604.09657v1 Announce Type: new Abstract: Digitizing magnetic media containing computer data is only the first step towards the preservation of early home computing era artifacts. The audio tape

Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation

arXiv:2604.07486v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing syn

Product Review Based on Optimized Facial Expression Detection

arXiv:2604.10885v1 Announce Type: cross Abstract: This paper proposes a method to review public acceptance of products based on their brand by analyzing the facial expression of the customer intending

Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability

arXiv:2604.02653v2 Announce Type: replace Abstract: Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below

Professor Jeffrey Sachs, makes the case that Trump is not only insane, but also a dangerously dumb human being. 😳👇

Professor Jeffrey Sachs, a prominent economist and public policy expert at Columbia University, is cited in a post shared by AI researcher Yann LeCun making critical assessments of former President Do

researchyann-lecun--x

Progressive Deep Learning for Automated Spheno-Occipital Synchondrosis Maturation Assessment

arXiv:2604.10945v1 Announce Type: new Abstract: Accurate assessment of spheno-occipital synchondrosis (SOS) maturation is a key indicator of craniofacial growth and a critical determinant for orthodon

Progressively Texture-Aware Diffusion for Contrast-Enhanced Sparse-View CT

arXiv:2604.11559v1 Announce Type: new Abstract: Diffusion-based sparse-view CT (SVCT) imaging has achieved remarkable advancements in recent years, thanks to its more stable generative capability. How

Property-Preserving Hashing for ell_1-Distance Predicates: Applications to Countering Adversarial Input Attacks

arXiv:2504.16355v2 Announce Type: replace-cross Abstract: Perceptual hashing is used to detect whether an input image is similar to a reference image with a variety of security applications. Recently,

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

arXiv:2604.10949v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of visi

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

arXiv:2505.04842v2 Announce Type: replace-cross Abstract: Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value func

Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

arXiv:2602.19509v3 Announce Type: replace-cross Abstract: We observe that LLM cascading and routing implicitly solves an anytime computation problem -- a class of algorithms, well-studied in classical

Quantifying Weighted Morphological Content of Large-Scale Structures via Simulation-Based Inference

arXiv:2511.03636v2 Announce Type: replace-cross Abstract: We perform a simulation-based forecasting analysis to compare the cosmological constraining power of higher-order summary statistics of the la

Query Lower Bounds for Diffusion Sampling

arXiv:2604.10857v1 Announce Type: cross Abstract: Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by mi

Quotation-Based Data Retention Mechanism for Data Privacy in LLM-Empowered Network Services

arXiv:2503.23001v5 Announce Type: replace Abstract: The deployment of large language models (LLMs) for next-generation network optimization introduces novel data governance challenges. mobile network

R2E-VID: Two-Stage Robust Routing via Temporal Gating for Elastic Edge-Cloud Video Inference

arXiv:2604.09681v1 Announce Type: cross Abstract: With the rapid growth of large-scale video analytics applications, edge-cloud collaborative systems have become the dominant paradigm for real-time in

RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation

arXiv:2604.11164v1 Announce Type: new Abstract: Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotat

ReadMOF: Structure-Free Semantic Embeddings from Systematic MOF Nomenclature for Machine Learning

arXiv:2604.10568v1 Announce Type: new Abstract: Systematic chemical names, such as IUPAC-style nomenclature for metal-organic frameworks (MOFs), contain rich structural and compositional information i

Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting

arXiv:2604.10259v1 Announce Type: new Abstract: We present a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation that operates directly on multi

ReaLiTy and LADS: A Unified Framework and Dataset Suite for LiDAR Adaptation Across Sensors and Adverse Weather Conditions

arXiv:2604.10213v1 Announce Type: cross Abstract: Reliable LiDAR perception requires robustness across sensors, environments, and adverse weather. However, existing datasets rarely provide physically

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty

arXiv:2604.10072v1 Announce Type: new Abstract: Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Tho

Reasoning as Data: Representation-Computation Unity and Its Implementation in a Domain-Algebraic Inference Engine

arXiv:2604.10908v1 Announce Type: new Abstract: Every existing knowledge system separates storage from computation. We show this separation is unnecessary and eliminate it. In a standard triple is_a(A

RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering

arXiv:2604.11229v1 Announce Type: cross Abstract: Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, conte

Reconciling distributed compliance with high-performance control in continuum soft robotics

arXiv:2603.16630v2 Announce Type: replace Abstract: High-performance closed-loop control of truly soft continuum manipulators has remained elusive. Experimental demonstrations have largely relied on s

researcharxiv-cs-ro

Redefining the future of software engineering

Software engineering has experienced two seismic shifts this century. First was the rise of the open source movement, which gradually made code accessible to developers and engineers everywhere. Secon

researchmit-tech-review

RedNote-Vibe: A Dataset for Capturing Temporal Dynamics of AI-Generated Text in Lifestyle Social Media

arXiv:2509.22055v2 Announce Type: replace Abstract: We introduce RedNote-Vibe, a dataset spanning five years (pre-LLM to July 2025) sourced from lifestyle platform RedNote (Xiaohongshu), capturing the

Replicable Composition

arXiv:2604.10423v1 Announce Type: new Abstract: Replicability requires that algorithmic conclusions remain consistent when rerun on independently drawn data. A central structural question is compositi

Representation-Aligned Multi-Scale Personalization for Federated Learning

arXiv:2604.11278v1 Announce Type: new Abstract: In federated learning (FL), accommodating clients with diverse resource constraints remains a significant challenge. A widely adopted approach is to use

Reproduction Beyond Benchmarks: ConstBERT and ColBERT-v2 Across Backends and Query Distributions

arXiv:2604.09982v1 Announce Type: cross Abstract: Reproducibility must validate architectural robustness, not just numerical accuracy. We evaluate ColBERT-v2 and ConstBERT across five dimensions, find

Resource Consumption Threats in Large Language Models

arXiv:2603.16068v3 Announce Type: replace-cross Abstract: Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LL

Rethinking the Diffusion Model from a Langevin Perspective

arXiv:2604.10465v1 Announce Type: cross Abstract: Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically

Retinal Cyst Detection from Optical Coherence Tomography Images

arXiv:2604.10843v1 Announce Type: cross Abstract: Retinal Cysts are formed by leakage and accumulation of fluid in the retina due to the incompetence of retinal vasculature. These cystic spaces have s

Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure

arXiv:2604.11759v1 Announce Type: new Abstract: Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distingu

Riemannian Zeroth-Order Gradient Estimation with Structure-Preserving Metrics for Geodesically Incomplete Manifolds

arXiv:2601.08039v2 Announce Type: replace Abstract: In this paper, we study Riemannian zeroth-order optimization in settings where the underlying Riemannian metric g is geodesically incomplete, and th

@rmaruy Can Code/Symbol Systems Emerge Inside a Single Neural Network? https://medium.com/@rmaruy3/can-code-symbol-systems-emerge-inside-a-s…

This article by @rmaruy explores whether discrete code or symbol systems can spontaneously emerge within a single neural network, examining the conditions under which internal representations might de

researchdavid-ha--x

RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation

arXiv:2511.17441v3 Announce Type: replace Abstract: Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due

researcharxiv-cs-ro

rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training

arXiv:2604.11156v1 Announce Type: new Abstract: Unsupervised remote photoplethysmography (rPPG) promises to leverage unlabeled video data, but its potential is hindered by a critical challenge: traini

RUMLEM: A Dictionary-Based Lemmatizer for Romansh

arXiv:2604.11233v1 Announce Type: new Abstract: Lemmatization -- the task of mapping an inflected word form to its dictionary form -- is a crucial component of many NLP applications. In this paper, we

S^3: Structured Sparsity Specification

arXiv:2604.11315v1 Announce Type: cross Abstract: We introduce the Structured Sparsity Specification (S^3), an algebraic framework for defining, composing, and implementing structured sparse patterns.

S4M: 4-points to Segment Anything

arXiv:2503.05534v3 Announce Type: replace Abstract: Purpose: The Segment Anything Model (SAM) promises to ease the annotation bottleneck in medical segmentation, but overlapping anatomy and blurred bo

Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping

arXiv:2505.13777v2 Announce Type: replace-cross Abstract: We present Sat2Sound, a unified multimodal framework for geospatial soundscape understanding, designed to predict and map the distribution of

Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes

arXiv:2512.12982v2 Announce Type: replace Abstract: The pursuit of a universal AI-generated image (AIGI) detector often relies on aggregating data from numerous generators to improve generalization. H

SciPostLayoutTree: A Dataset for Structural Analysis of Scientific Posters

arXiv:2511.18329v3 Announce Type: replace Abstract: Scientific posters play a vital role in academic communication by presenting ideas through visual summaries. Analyzing reading order and parent-chil

ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching

arXiv:2604.10962v1 Announce Type: new Abstract: Flow Matching (FM) policies have emerged as an efficient backbone for robotic control, offering fast and expressive action generation that underpins rec

researcharxiv-cs-ro

Self-Calibrating Language Models via Test-Time Discriminative Distillation

arXiv:2604.09624v1 Announce Type: new Abstract: Large language models (LLMs) are systematically overconfident: they routinely express high certainty on questions they often answer incorrectly. Existin

Self-Certifying Primal-Dual Optimization Proxies for Large-Scale Batch Economic Dispatch

arXiv:2510.15850v2 Announce Type: replace-cross Abstract: Recent research has shown that optimization proxies can be trained to high fidelity, achieving average optimality gaps under 1% for large-scal