Search: “research”

Non-Stationary Online Structured Prediction with Surrogate Losses

arXiv:2510.07086v2 Announce Type: replace Abstract: Online structured prediction, including online classification as a special case, is the task of sequentially predicting labels from input features.

Numerical exploration of the range of shape functionals using neural networks

DGX agent

arXiv:2602.14881v2 Announce Type: replace-cross Abstract: We introduce a novel numerical framework for the exploration of Blaschke--Santalo diagrams, which are efficient tools characterizing the possi

researcharxiv-cs-ai

15 May 2026

OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidance

arXiv:2605.14458v1 Announce Type: new Abstract: Omni-modal large language models have demonstrated remarkable potential in holistic multimodal understanding; however, the token explosion caused by hig

On the current scale of things the Trump phone is a minor corruption, and only goes to show how incompetent everyone in his family is. If yo…

On the current scale of things the Trump phone is a minor corruption, and only goes to show how incompetent everyone in his family is. If you think that any other president would have done things like

researchyann-lecun--x

On The Hidden Biases of Flow Matching Samplers

arXiv:2512.16768v3 Announce Type: replace-cross Abstract: Flow matching (FM) constructs continuous-time ODE samplers by prescribing probability paths between a base distribution and a target distribut

On the Identifiability of Causal Graphs with the Invariance Principle

arXiv:2510.13583v4 Announce Type: replace-cross Abstract: Causal discovery from i.i.d. observational data is known to be generally ill-posed. We demonstrate that if we have access to the distribution

PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models

arXiv:2505.22394v2 Announce Type: replace Abstract: We present PacTure, a novel framework for generating physically-based rendering (PBR) material textures for an untextured 3D mesh from a text descri

PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting

arXiv:2605.14135v1 Announce Type: new Abstract: We present PanoPlane, an approach for high-fidelity sparse-view indoor novel view synthesis that reconstructs closed room geometry via panoramic scene c

Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods

arXiv:2605.14240v1 Announce Type: new Abstract: The recent large-scale emergence of LLMs has left an open space for dealing with their consequences, such as plagiarism or the spread of false informati

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

arXiv:2605.14098v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctn

researcharxiv-cs-cl

Pelican-Unified 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action

arXiv:2605.15153v1 Announce Type: cross Abstract: We present Pelican-Unified 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unified 1.0 uses a sing

PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation

arXiv:2605.14269v1 Announce Type: cross Abstract: Generating realistic human motion is a central yet unsolved challenge in video generation. While reinforcement learning (RL)-based post-training has d

Predicting Response to Neoadjuvant Chemotherapy in Ovarian Cancer from CT Baseline Using Multi-Loss Deep Learning

arXiv:2605.14991v1 Announce Type: cross Abstract: Ovarian cancer is the most lethal gynecologic malignancy: around 60% of patients are diagnosed at an advanced stage, with an associated 5-year surviva

Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes

arXiv:2412.14291v2 Announce Type: replace-cross Abstract: We present a novel class of projected gradient (PG) methods for minimizing a smooth but not necessarily convex function over a convex compact

Proposal and study of statistical features for string similarity computation and classification

arXiv:2605.15110v1 Announce Type: cross Abstract: Adaptations of features commonly applied in the field of visual computing, co-occurrence matrix (COM) and run-length matrix (RLM), are proposed for th

researcharxiv-cs-cl

PyCSP3-Scheduling: A Scheduling Extension for PyCSP3

arXiv:2605.14559v1 Announce Type: new Abstract: PyCSP^3 provides a productive way to build constraint models for solving combinatorial constrained problems and export them to XCSP^3, preserving a comp

Quantifying Cyber-Vulnerability in Power Electronics Systems via an Impedance-Based Attack Reachable Domain

arXiv:2605.14502v1 Announce Type: cross Abstract: Power electronics systems are increasingly exposed to cyber threats due to their integration with digital controllers and communication networks. Howe

Randomized Atomic Feature Models for Physics-Informed Identification of Dynamic Systems

arXiv:2605.14351v1 Announce Type: cross Abstract: We present a physics-informed framework for system identification based on randomized stable atomic features. Impulse responses are represented as ran

Reactive Planning based Control for Mobile Robots in Obstacle-Cluttered Environments

arXiv:2605.14232v1 Announce Type: new Abstract: This paper addresses the motion control problem for mobile robots in obstacle-cluttered environments. The mobile robot has partial environment informati

researcharxiv-cs-ro

Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization

arXiv:2605.14019v1 Announce Type: cross Abstract: Regret is the cost of uncertainty in algorithmic decision-making. Quantifying regret typically requires computationally expensive simulation via Sampl

Reliability-Gated Source Anchoring for Continual Test-Time Adaptation

arXiv:2605.14063v1 Announce Type: new Abstract: Continual test-time adaptation (CTTA) updates a pretrained model online on an unlabeled, non-stationary stream while anchoring it to a frozen source che

RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model

arXiv:2512.12083v3 Announce Type: replace Abstract: Semantic-rich features from Vision Foundation Models (VFMs) have been leveraged to enhance Latent Diffusion Models (LDMs). However, raw VFM features

Representative Attention For Vision Transformers

arXiv:2605.14913v1 Announce Type: new Abstract: Linear attention has emerged as a promising direction for scaling Vision Transformers beyond the quadratic cost of dense self-attention. A prevalent str

Residual Stream Duality in Modern Transformer Architectures

arXiv:2603.16039v2 Announce Type: replace-cross Abstract: Recent work has made clear that the residual pathway is not mere optimization plumbing; it is part of the model's representational machinery.

Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity

arXiv:2605.14075v1 Announce Type: cross Abstract: Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more i

researcharxiv-cs-cl

Rethinking the Good Enough Embedding for Easy Few-Shot Learning

arXiv:2605.14145v1 Announce Type: new Abstract: The field of deep visual recognition is undergoing a paradigm shift toward universal representations. The Platonic Representation Hypothesis suggests th

Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization

arXiv:2602.05285v2 Announce Type: replace Abstract: A core challenge in structural biophysics is generating biomolecular conformations that are both physically plausible and consistent with experiment

RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution

arXiv:2605.15154v1 Announce Type: cross Abstract: Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attr

RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression

arXiv:2605.14359v1 Announce Type: cross Abstract: Vector quantization is a fundamental tool for compressing high-dimensional embeddings, yet existing multi-codebook methods rely on static codebooks th

SAGE3D: Soft-guided attention and graph excitation for 3D point cloud corner detection

arXiv:2605.15088v1 Announce Type: new Abstract: We present SAGE3D, a hybrid Transformer-based model for corner detection in airborne LiDAR point clouds. We propose a multi-stage solution built on a hi

Scalable Solution of the Stochastic Multi-path Traveling Salesman Problem via Neural Networks

arXiv:2605.14662v1 Announce Type: cross Abstract: The multi-path Traveling Salesman Problem with stochastic travel costs arises in hybrid vehicle routing applications designed for Smart City and City

Scalable Subset Selection in Linear Mixed Models

arXiv:2506.20425v3 Announce Type: replace-cross Abstract: Linear mixed models (LMMs), which incorporate fixed and random effects, are key tools for analyzing heterogeneous data, such as in personalize

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model

arXiv:2605.14567v1 Announce Type: cross Abstract: We propose a simple mechanism by which scaling laws emerge from feature learning in multi-layer networks. We study a high-dimensional hierarchical tar

ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning

arXiv:2510.23818v2 Announce Type: replace Abstract: As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. W

SceneForge: Structured World Supervision from 3D Interventions

arXiv:2605.14399v1 Announce Type: new Abstract: Many multimodal learning tasks require supervision that remains consistent across edits, viewpoints, and scene-level interventions. However, such superv

SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification

arXiv:2504.09549v3 Announce Type: replace Abstract: Aerial-Ground Person Re-IDentification (AG-ReID) aims to retrieve specific persons across cameras with different viewpoints. Previous works focus on

SeaVis: Modeling and Control of a Remotely Operated Towed Vehicle for Seabed Visualization and Mapping

arXiv:2605.14683v1 Announce Type: new Abstract: High-resolution seafloor mapping necessitates stable and precise positioning for underwater robots. This paper introduces a novel mathematical model for

researcharxiv-cs-ro

Semantic Feature Segmentation for Interpretable Predictive Maintenance in Complex Systems

arXiv:2605.14318v1 Announce Type: new Abstract: Predictive maintenance in complex systems is often complicated by the heterogeneity and redundancy of monitored variables,which can obscure fault-releva

Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems

arXiv:2605.15050v1 Announce Type: new Abstract: Recently, deep generative models have been used for posterior inference in inverse problems, including high-stakes applications in medical imaging and s

SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning

arXiv:2605.14619v1 Announce Type: new Abstract: Multi-run chain-of-thought reasoning is usually collapsed to final-answer aggregates, which discard howsampled trajectories share, split, and rejoin thr

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning

arXiv:2605.14659v1 Announce Type: new Abstract: Critical-data-size accounts of grokking suggest a natural post-threshold intuition: once training data is sufficient to identify the underlying rule, ad

SparseOIT: Improving Order-Independent Transparency 3DGS via Active Set Method

arXiv:2605.13855v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has received tremendous popularity over the past few years due to its photorealistic visual appearance. However, 3DGS use

Spontaneous symmetry breaking and Goldstone modes for deep information propagation

arXiv:2605.14685v1 Announce Type: cross Abstract: In physical systems, whenever a continuous symmetry is spontaneously broken, the system possesses excitations called Goldstone modes, which allow cohe

Stochastic Matching via Local Sparsification

arXiv:2605.14195v1 Announce Type: cross Abstract: The classic online stochastic matching problem typically requires immediate and irrevocable matching decisions. However, in many modern decentralized

Streaming Speech-to-Text Translation with a SpeechLLM

arXiv:2605.14766v1 Announce Type: cross Abstract: Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

arXiv:2605.14738v1 Announce Type: cross Abstract: Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE. In this paper, we inves

Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning

arXiv:2605.14636v1 Announce Type: new Abstract: Large language models (LLMs) often fail to reason under temporal cutoffs: when prompted to answer from the standpoint of an earlier time, they exploit k

TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion

arXiv:2605.14136v1 Announce Type: new Abstract: Recent text-to-video diffusion transformers generate visually compelling frames, yet still struggle with temporal coherence, often producing flickering,