Search: “research”

SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding

arXiv:2511.17411v2 Announce Type: replace-cross Abstract: Robotic Foundation Models (RFMs) hold great promise as generalist, end-to-end systems for robot control. Yet their ability to generalize acros

Spectro-Temporal Modulation Representation Framework for Human-Imitated Speech Detection

DGX agent

arXiv:2604.23241v1 Announce Type: cross Abstract: Human-imitated speech poses a greater challenge than AI-generated speech for both human listeners and automatic detection systems. Unlike AI-generated

researcharxiv-cs-cl

28 Apr 2026

STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning

arXiv:2604.23309v1 Announce Type: new Abstract: Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored vid

STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator

arXiv:2604.24544v1 Announce Type: new Abstract: The increasing reliance on Large Language Models (LLMs) across diverse sectors highlights the need for robust domain-specific and language-specific eval

Stochastic simultaneous optimistic optimization

arXiv:2604.24537v1 Announce Type: new Abstract: We study the problem of global maximization of a function f given a finite number of evaluations perturbed by noise. We consider a very weak assumption

Supporting Family-School Partnerships with Robot-Facilitated Home-Based Activities

arXiv:2604.23978v1 Announce Type: new Abstract: Family-school partnerships (FSP) are critical to children's development, yet families often face barriers such as time constraints, fragmented communica

researcharxiv-cs-ro

Surface Sensitivity in Lean 4 Autoformalization

arXiv:2604.23135v1 Announce Type: new Abstract: Natural-language variation poses a key challenge in Lean autoformalization: semantically equivalent paraphrases of the same theorem statements can induc

Symbolic recovery of PDEs from measurement data

arXiv:2602.15603v2 Announce Type: replace Abstract: Models based on partial differential equations (PDEs) are powerful for describing a wide range of complex phenomena in the natural sciences. Accurat

Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling

arXiv:2604.23586v1 Announce Type: cross Abstract: Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existi

Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction

arXiv:2604.23964v1 Announce Type: cross Abstract: Patients with dementia typically exhibit cognitive impairment, which is routinely assessed using the Mini-Mental State Examination (MMSE). Concurrentl

TEMPO: Transformers for Temporal Disease Progression from Cross-Sectional Data

arXiv:2604.23368v1 Announce Type: new Abstract: Event-Based Models (EBMs) infer biomarker progression from cross-sectional data but typically only as ordinal sequences and rely on rigid model assumpti

Tessera: Secure, Near-Line-Rate Weight Streaming for UMA Edge Accelerators

arXiv:2604.23205v1 Announce Type: cross Abstract: Deploying proprietary Deep Neural Networks (DNNs) on commodity edge devices demands hardware-backed Digital Rights Management (DRM) capable of withsta

Test of Time LLM from some legends...pretty fun!

researchsoumith-chintala--x

Test of Time LLM from some legends...pretty fun! Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it bel

Text Tells the Cost: Predicting and Analyzing Repayment Effort of Self-Admitted Technical Debt

arXiv:2309.06020v3 Announce Type: replace-cross Abstract: Technical debt refers to the consequences of sub-optimal decisions made during software development that prioritize short-term benefits over l

The Shape of Attraction in UMAP: Exploring the Embedding Forces in Dimensionality Reduction

arXiv:2503.09101v4 Announce Type: replace-cross Abstract: Uniform manifold approximation and projection (UMAP) is among the most popular neighbor embedding methods. The method samples pairs of point i

The Spectral Lifecycle of Transformer Training: Transient Compression Waves, Persistent Spectral Gradients, and the Q/K--V Asymmetry

arXiv:2604.22778v1 Announce Type: cross Abstract: We present the first systematic study of weight matrix singular value spectra during transformer pretraining, tracking full SVD decompositions of ever

TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog

arXiv:2604.23602v1 Announce Type: cross Abstract: Early, tool-free prediction of post-synthesis timing remains a key obstacle to rapid RTL iteration. We introduce TimingLLM, a two-stage retrieval-augm

Touchless Intraoperative Image Access System Based on Vision-Based Hand Tracking

arXiv:2604.24235v1 Announce Type: new Abstract: Touchless interaction with medical images is becoming increasingly important in the surgical field, where sterility and continuity of the operational wo

Toward Theoretical Insights into Diffusion Trajectory Distillation via Operator Merging

arXiv:2505.16024v2 Announce Type: replace-cross Abstract: Diffusion trajectory distillation accelerates sampling by training a student model to approximate the multi-step denoising trajectories of a p

Towards Causally Interpretable Wi-Fi CSI-Based Human Activity Recognition with Discrete Latent Compression and LTL Rule Extraction

arXiv:2604.22979v1 Announce Type: new Abstract: We address Human Activity Recognition (HAR) utilizing Wi-Fi Channel State Information (CSI) under the joint requirements of causal interpretability, sym

Towards Understanding the Expressive Power of GNNs with Global Readout

arXiv:2604.22870v1 Announce Type: cross Abstract: We study the expressive power of message-passing aggregate-combine-readout graph neural networks (ACR-GNNs). Particularly, we focus on the first-order

Trajectory Planning for an Articulated Commercial Vehicle using Model Predictive Contouring Control

arXiv:2604.24064v1 Announce Type: new Abstract: This paper presents a trajectory planning method for articulated commercial vehicles, specifically tractor-semitrailers, based on Model Predictive Conto

researcharxiv-cs-ro

Transferable Human Mobility Network Reconstruction with neuroGravity

arXiv:2604.23678v1 Announce Type: new Abstract: Accurate modeling of human mobility is critical for tackling urban planning and public health challenges. In undeveloped regions, the absence of compreh

Transformer as an Euler Discretization of Score-based Variational Flow

arXiv:2604.23740v1 Announce Type: new Abstract: Despite the Transformer's dominance across machine learning, its architecture remains largely heuristic and lacks a unified theoretical foundation. We i

Translate or Simplify First: An Analysis of Cross-lingual Text Simplification in English and French

arXiv:2604.23844v1 Announce Type: new Abstract: Cross-Lingual Text Simplification (CLTS) aims to make content more accessible across languages by simultaneously addressing both linguistic complexity a

TRINITY: An Evolved LLM Coordinator

arXiv:2512.04695v3 Announce Type: replace Abstract: Combining diverse foundation models is promising, but weight-merging is limited by mismatched architectures and closed APIs. Trinity addresses this

Triple-Phase Sequential Fusion Network for Hepatobiliary Phase Liver MRI Synthesis

arXiv:2604.22904v1 Announce Type: cross Abstract: Gadoxetate disodium-enhanced MRI is essential for the detection and characterization of hepatocellular carcinoma. However, acquisition of the hepatobi

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

arXiv:2604.24763v1 Announce Type: new Abstract: Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creatin

Universal Approximation of Operators with Transformers and Neural Integral Operators

arXiv:2409.00841v3 Announce Type: replace Abstract: We study the universal approximation properties of transformers and neural integral operators for operators in Banach spaces. In particular, we show

Unstable Rankings in Bayesian Deep Learning Evaluation

arXiv:2604.23102v1 Announce Type: new Abstract: Standard evaluations of Bayesian deep learning methods assume that metric estimates are reliable, but we show this assumption fails under data scarcity.

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training

arXiv:2604.24350v1 Announce Type: cross Abstract: Fast Adversarial Training (FAT) has attracted significant attention due to its efficiency in enhancing neural network robustness against adversarial a

Urban Flood Observations (UFO): A hand-labeled training and validation dataset of post-flood inundation

arXiv:2604.23066v1 Announce Type: new Abstract: Urban flooding affects lives and infrastructure worldwide. Mapping inundation in complex urban environments from satellite imagery remains challenging d

Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks

arXiv:2511.07410v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have become popular tools for embodied high-level planning. However, their depl

VAMP-Net: An Interpretable Multi-Path Network of Genomic Permutation-Invariant Set Attention and Quality-Aware 1D-CNN for MTB Drug Resistance

arXiv:2512.21786v2 Announce Type: replace Abstract: Genomic prediction of drug resistance in Mycobacterium tuberculosis is often hindered by complex epistatic interactions and variable sequencing qual

VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning

arXiv:2604.23641v1 Announce Type: new Abstract: This paper introduces VDLF-Net, which attaches a compact VAE to a multi-scale CNN backbone. Latent vectors and softmax-gate support the backbone feature

Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Unified and Generalized Approach

arXiv:2604.23953v1 Announce Type: cross Abstract: Blind omnidirectional image quality assessment (BOIQA) presents a great challenge to the visual quality assessment community, due to different storage

Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models

arXiv:2512.10362v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) demonstrate impressive reasoning capabilities, but often fail to perceive fine-grained visual details

VitaminP: cross-modal learning enables whole-cell segmentation from routine histology

arXiv:2604.23799v1 Announce Type: new Abstract: Accurate whole-cell and nuclear segmentation is essential for precision pathology and spatial omics, yet routine hematoxylin and eosin (H&E) staining pr

VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation

arXiv:2604.22942v1 Announce Type: cross Abstract: Diffusion models produce high-quality synthetic data but suffer from slow inference. We propose 3D Variable-Step Denoising Diffusion Probabilistic Mod

Weakly Supervised Multicenter Nancy Index Scoring in Ulcerative Colitis Using Foundation Models

arXiv:2604.23706v1 Announce Type: new Abstract: Histologic assessment of ulcerative colitis (UC) activity is an important endpoint in clinical trials and routine care, but manual grading with indices

Well-Conditioned Oblivious Perturbations in Linear Space

arXiv:2604.23193v1 Announce Type: cross Abstract: Perturbing a deterministic n-dimensional matrix with small Gaussian noise is a cornerstone of smoothed analysis of algorithms [Spielman and Teng, JACM

What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models

arXiv:2510.03075v3 Announce Type: replace-cross Abstract: Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models.

What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts

arXiv:2505.13360v3 Announce Type: replace Abstract: Prompt underspecification is a common challenge when interacting with LLMs. In this paper, we present an in-depth analysis of this problem, showing

Applications

What Understanding Means in AI-Laden Astronomy

arXiv:2601.10038v2 Announce Type: replace-cross Abstract: Artificial intelligence is rapidly transforming astronomical research, yet the scientific community has largely treated this transformation as

applicationsarxiv-cs-ai

When Chain-of-Thought Fails, the Solution Hides in the Hidden States

arXiv:2604.23351v1 Announce Type: cross Abstract: Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant

When Context Sticks: Studying Interference in In-Context Learning

arXiv:2604.23371v1 Announce Type: new Abstract: This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's

When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions

arXiv:2604.23528v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) provide a promising machine learning framework for solving partial differential equations, but their training o

When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models

arXiv:2604.23994v1 Announce Type: cross Abstract: Discrete diffusion language models (dLLMs) enable parallel token updates with bidirectional attention, yet practical generation typically adopts block