research

Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles

arXiv:2604.17156v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a promising framework for solving inverse problems governed by partial differential equations (

Research

Understanding Counting Mechanisms in Large Language and Vision-Language Models

DGX agent

arXiv:2511.17699v2 Announce Type: replace Abstract: Counting is one of the fundamental abilities of large language models (LLMs) and large vision-language models (LVLMs). This paper examines how these

researcharxiv-cs-cv

21 Apr 2026

Understanding the Prompt Sensitivity

arXiv:2604.18389v1 Announce Type: new Abstract: Prompt sensitivity, which refers to how strongly the output of a large language model (LLM) depends on the exact wording of its input prompt, raises con

UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models

arXiv:2604.17565v1 Announce Type: new Abstract: Camera-controllable image editing aims to synthesize novel views of a given scene under varying camera poses while strictly preserving cross-view geomet

UniMesh: Unifying 3D Mesh Understanding and Generation

arXiv:2604.17472v1 Announce Type: new Abstract: Recent advances in 3D vision have led to specialized models for either 3D understanding (e.g., shape classification, segmentation, reconstruction) or 3D

Universal Diffusion-Based Probabilistic Downscaling

arXiv:2602.11893v3 Announce Type: replace Abstract: We introduce a universal diffusion-based downscaling framework that lifts deterministic low-resolution weather forecasts into probabilistic high-res

Upper Approximation Bounds for Neural Oscillators

arXiv:2512.01015v2 Announce Type: replace Abstract: Neural oscillators, originating from second-order ordinary differential equations (ODEs), have demonstrated strong performance in stably learning ca

Using Perspectival Words Is Harder Than Vocabulary Words for Humans and Even More So for Multimodal Language Models

arXiv:2506.00065v2 Announce Type: replace Abstract: Multimodal language models (MLMs) increasingly demonstrate human-like communication, yet their use of everyday perspectival words remains poorly und

Variational Autoencoder Domain Adaptation for Cross-System Generalization in ML-Based SOP Monitoring

arXiv:2604.18035v1 Announce Type: new Abstract: Machine learning (ML) models trained to detect physical-layer threats on one optical fiber system often fail catastrophically when applied to a differen

VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis

arXiv:2509.16538v3 Announce Type: replace-cross Abstract: We propose VC-Inspector, a lightweight, open-source large multimodal model (LMM) for reference-free evaluation of video captions, with a focus

View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity

arXiv:2604.17801v1 Announce Type: new Abstract: Text-driven 3D scene editing has recently attracted increasing attention. Most existing methods follow a render-edit-optimize pipeline, where multi-view

ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes

arXiv:2604.17623v1 Announce Type: new Abstract: Kinematic rigs provide a structured interface for articulating 3D meshes, but they lack an inherent representation of the plausible manifold of joint co

Vision Language Models are Biased

arXiv:2505.23941v4 Announce Type: replace-cross Abstract: Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that helps them on downstream tasks but also may noto

ViT^3: Unlocking Test-Time Training in Vision

arXiv:2512.01643v2 Announce Type: replace Abstract: Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an o

Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic

arXiv:2510.17001v2 Announce Type: replace Abstract: Large language models (LLMs) often encode word-form variation (e.g., walk vs. walked) as linear directions in the embedding space. However, standard

Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk

arXiv:2604.18546v1 Announce Type: new Abstract: We propose a distributionally robust approach to risk-sensitive estimation of an unknown signal x from an observed signal y. The unknown signal and obse

Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains

arXiv:2601.08184v3 Announce Type: replace-cross Abstract: Non-asymptotic central limit theorem (CLT) rates play a central role in modern machine learning and operations research. In this paper, we stu

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

arXiv:2603.19880v2 Announce Type: replace Abstract: Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving

What is born of light is light

This post likely discusses how light or illumination (literal or metaphorical) generates or produces similar qualities, potentially referencing philosophical, scientific, or spiritual concepts about t

researchnous-research--x

What makes an entity salient in discourse?

arXiv:2508.16464v2 Announce Type: replace Abstract: Entities in discourse vary in salience: main participants, objects and locations stay prominent, while others are quickly forgotten, raising questio

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

arXiv:2604.17318v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, pos

When Informal Text Breaks NLI: Tokenization Failure, Distribution Shift, and Targeted Mitigations

arXiv:2604.16787v1 Announce Type: new Abstract: We study how informal surface forms degrade NLI accuracy in ELECTRA-small (14M) and RoBERTa-large (355M) across four transforms applied to SNLI and Mult

When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms

arXiv:2604.16767v1 Announce Type: new Abstract: Audio platforms have evolved beyond entertainment. They have become central to public discourse, from podcasts and radio to WhatsApp voice notes and liv

When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation

arXiv:2601.04609v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used to make visual content accessible via text-based descriptions. In current systems, however, desc

When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models

arXiv:2507.13868v2 Announce Type: replace Abstract: Vision-language models (VLMs) increasingly combine visual and textual information to perform complex tasks. However, conflicts between their interna

Where is the Mind? Persona Vectors and LLM Individuation

arXiv:2604.17031v1 Announce Type: new Abstract: The individuation problem for large language models asks which entities associated with them, if any, should be identified as minds. We approach this pr

Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains

arXiv:2604.17393v1 Announce Type: new Abstract: Automatic evaluation metrics are central to the development of machine translation systems, yet their robustness under domain shift remains unclear. Mos

Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals

arXiv:2604.16745v1 Announce Type: cross Abstract: Training-free token reduction methods for Vision Transformers (ToMe, ToFu, PiToMe, and MCTF) employ different scoring mechanisms, yet they share a clo

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

arXiv:2506.05760v2 Announce Type: replace Abstract: Recent advances in Large Language Models(LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited:

x1: Learning to Think Adaptively Across Languages and Cultures

arXiv:2604.16917v1 Announce Type: new Abstract: Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single domi

ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection

arXiv:2604.17949v1 Announce Type: new Abstract: Deep learning-based industrial anomaly detectors often behave as black boxes, making it hard to justify decisions with physically meaningful defect evid

(1D) Ordered Tokens Enable Efficient Test-Time Search

arXiv:2604.15453v1 Announce Type: cross Abstract: Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, token

A Reconfigurable Pneumatic Joint Enabling Localized Selective Stiffening and Shape Locking in Vine-Inspired Robots

arXiv:2604.15907v1 Announce Type: new Abstract: Vine-inspired robots achieve large workspace coverage through tip eversion, enabling safe navigation in confined and cluttered environments. However, th

researcharxiv-cs-ro

A Structure-Preserving Graph Neural Solver for Parametric Hyperbolic Conservation Laws

arXiv:2604.15617v1 Announce Type: cross Abstract: Hyperbolic conservation laws govern a wide range of transport-driven dynamics featuring shocks, contact discontinuities, and complex wave interactions

A Tale of Two Learning Algorithms: Multiple Stream Random Walk and Asynchronous Gossip

arXiv:2504.09792v2 Announce Type: replace Abstract: Although gossip and random walk-based learning algorithms are widely known for decentralized learning, there has been limited theoretical and experi

Acoustic and Facial Markers of Perceived Conversational Success in Spontaneous Speech

arXiv:2604.15322v1 Announce Type: cross Abstract: Individuals often align their speaking patterns with their interlocutors, a phenomenon linked to engagement and rapport. While well documented in task

Adaptive Spatio-temporal Estimation on the Graph Edges via Line Graph Transformation

arXiv:2311.00656v4 Announce Type: replace-cross Abstract: Spatial-temporal estimation of signals on graph edges is challenging because most conventional Graph Signal Processing techniques are defined

Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba

arXiv:2503.18970v3 Announce Type: replace Abstract: Structured State Space Models (SSMs) have emerged as a transformative paradigm in sequence modeling, addressing critical limitations of Recurrent Ne

Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow

arXiv:2604.15809v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grou

Anthropomorphism and Trust in Human-Large Language Model interactions

arXiv:2604.15316v1 Announce Type: cross Abstract: With large language models (LLMs) becoming increasingly prevalent in daily life, so too has the tendency to attribute to them human-like minds and emo

ArrayTac: A Closed-loop Piezoelectric Tactile Platform for Continuously Tunable Rendering of Shape, Stiffness, and Friction

arXiv:2603.13829v2 Announce Type: replace-cross Abstract: Human touch depends on the integration of shape, stiffness, and friction, yet existing tactile displays cannot render these cues together as c

AST: Adaptive, Seamless, and Training-Free Precise Speech Editing

arXiv:2604.16056v1 Announce Type: cross Abstract: Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Existing methods rely on task-speci

Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks

arXiv:2603.11487v5 Announce Type: replace Abstract: Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. Are sinks a byproduct of the opti

ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning

arXiv:2602.09953v2 Announce Type: replace Abstract: Large reasoning models trained with reinforcement learning and verifiable rewards (RLVR) achieve strong performance on complex reasoning tasks, yet

Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review

arXiv:2602.11173v2 Announce Type: replace Abstract: Author response (rebuttal) writing is a critical stage of scientific peer review that demands substantial author effort. In practice, authors posses

Automatic Combination of Sample Selection Strategies for Few-Shot Learning

arXiv:2402.03038v2 Announce Type: replace-cross Abstract: In few-shot learning, the selection of samples has a significant impact on the performance of the model. While effective sample selection stra

Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations

arXiv:2604.16217v1 Announce Type: cross Abstract: Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilitie

Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration

arXiv:2604.15829v1 Announce Type: new Abstract: Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to impl