Search: “research”

Computational-Statistical Trade-off in Kernel Two-Sample Testing with Random Fourier Features

arXiv:2407.08976v2 Announce Type: replace-cross Abstract: Recent years have seen a surge in methods for two-sample testing, among which the Maximum Mean Discrepancy (MMD) test has emerged as an effect

Research

Compute Only Once: UG-Separation for Efficient Large Recommendation Models

DGX agent

arXiv:2602.10455v2 Announce Type: replace-cross Abstract: Driven by scaling laws, recommender systems increasingly rely on larger-scale models to capture complex feature interactions and user behavior

researcharxiv-cs-lg

21 May 2026

Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise

arXiv:2605.20999v1 Announce Type: cross Abstract: We establish maximal concentration bounds for the iterates generated by stochastic approximation algorithms with general step sizes, where the noise h

ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning

arXiv:2605.20385v1 Announce Type: new Abstract: Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the

Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards

arXiv:2605.20758v1 Announce Type: cross Abstract: Inference-time guided sampling steers state-of-the-art diffusion and flow models without fine-tuning by interpreting the generation process as a contr

Contradiction Graphs Determine VC Dimension

arXiv:2605.20434v1 Announce Type: cross Abstract: We study the contradiction graphs associated with binary concept classes. For a class H subseteq {0,1}^X, the order-m contradiction graph G_m(H) has a

Control, Optimal Transport and Neural Differential Equations in Supervised Learning

arXiv:2503.15105v4 Announce Type: replace-cross Abstract: We study the fundamental computational problem of approximating optimal transport (OT) equations using neural differential equations (Neural O

Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models

arXiv:2605.20345v1 Announce Type: cross Abstract: Latent Gaussian models (LGMs) are a popular class of Bayesian hierarchical models that include Gaussian processes, as well as certain spatial models a

CRANE: Correcting Errors in Raw Nanopore Signals Using Hidden Markov Models

arXiv:2603.20420v2 Announce Type: replace-cross Abstract: Nanopore sequencing can read substantially longer sequences of nucleic acid molecules, called reads, than other sequencing methods, which has

DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars

arXiv:2605.21001v1 Announce Type: new Abstract: Existing 3D clothed avatar reconstruction methods achieve high visual fidelity but ignore geometric structure and physical plausibility. They either mod

Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum

arXiv:2605.20196v1 Announce Type: new Abstract: We investigate the hypothesis that real-data scaling laws are governed by progressive coverage of a latent predictive contribution spectrum rather than

Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics

arXiv:2605.20580v1 Announce Type: new Abstract: This work explores a dynamics-informed Temporal Fusion Transformer (TFT) as a data-driven surrogate for computationally intensive Earth system simulatio

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models

arXiv:2603.14184v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question an

Deformba: Vision State Space Model with Adaptive State Fusion

arXiv:2605.21308v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as a powerful and efficient alternative to Transformers, demonstrating linear-time complexity and exceptional seq

Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models

arXiv:2411.01141v2 Announce Type: replace Abstract: There are two shortages in the current Large Language Models (LLMs) era. The first is short of multilingual models, where most LLMs are English-cent

Diffuse to Detect: Bi-Level Sample Rebalancing with Pseudo-Label Diffusion for Point-Supervised Infrared Small-Target Detection

arXiv:2605.20766v1 Announce Type: new Abstract: Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two

Direct Translation between Sign Languages

arXiv:2605.20588v1 Announce Type: new Abstract: The field of sign language translation has witnessed significant progress in the translation between sign and spoken languages, but the translation betw

Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration

arXiv:2605.21381v1 Announce Type: new Abstract: Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synt

Disentangling Sampling from Training Budget in Class-Imbalanced CT Body Composition Segmentation

arXiv:2605.20405v1 Announce Type: cross Abstract: Class imbalance is a fundamental challenge in medical image segmentation, where frequent classes typically dominate training at the expense of rare cl

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs

arXiv:2605.20382v1 Announce Type: new Abstract: Language models are trained to follow instructions, but they are also powerful pattern completers. What happens when these two objectives conflict? We c

Donald Trump is running a theft operation in plain sight. Stock trades. Crypto. Pardons. Slush funds. Sick doesn't even cover it.

I can't provide a summary of this content because the URL appears inconsistent with the stated source (it shows a Gavin Newsom URL but attributes the post to Yann LeCun), and I cannot verify the actua

researchyann-lecun--x

DrawMotion: Generating 3D Human Motions by Freehand Drawing

arXiv:2605.20955v1 Announce Type: new Abstract: Text-to-motion generation, which translates textual descriptions into human motions, faces the challenge that users often struggle to precisely convey t

Dual Quaternion Based Contact Modeling for Fast and Smooth Collision Recovery of Quadrotors

arXiv:2603.14698v3 Announce Type: replace Abstract: Unmanned aerial vehicles (UAVs) operating in cluttered environments require efficient and accurate impact modeling to maintain stability post collis

researcharxiv-cs-ro

Dynamic Shapley Computation

arXiv:2605.20620v1 Announce Type: new Abstract: Shapley-based data valuation provides a principled way to quantify the contribution of training data, but its high computational cost makes it impractic

Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting

arXiv:2605.20678v1 Announce Type: new Abstract: Non-stationary time series forecasting is challenged by evolving distribution shifts that static models struggle to capture. While Mixture-of-Experts (M

E-PCN: Jet Tagging with Explainable Particle Chebyshev Networks Using Kinematic Features

arXiv:2512.07420v2 Announce Type: cross Abstract: The identification and classification of collimated particle sprays, or jets, are essential for interpreting data from high-energy collider experiment

Early High-Frequency Injection for Geometry-Sensitive OOD Detection

arXiv:2605.20728v1 Announce Type: new Abstract: Post-hoc OOD detectors score logits or features after training, so their success depends on the geometry already encoded in the representation. We revis

Effective Model Pruning: Measure The Redundancy of Model Components

arXiv:2509.25606v3 Announce Type: replace Abstract: This article initiates the study of a basic question about model pruning. Given a vector s of importance scores assigned to model components, how ma

Efficient Learning of Deep State Space Models via Importance Smoothing

arXiv:2605.21108v1 Announce Type: new Abstract: Latent state space systems are ubiquitous in statistical modelling, arising naturally when a time series is observed through a noisy measurement functio

Efficient training for compact compression models via sequential distillation

arXiv:2601.05639v2 Announce Type: replace Abstract: Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high

EllipseLIO: Adaptive LiDAR Inertial Odometry with an Ellipsoid Representation

arXiv:2605.21150v1 Announce Type: new Abstract: LiDAR Inertial Odometry (LIO) is a critical component for many mobile robots that need to navigate without relying on external positioning (e.g., GPS).

researcharxiv-cs-ro

END: Early Noise Dropping for Efficient and Effective Context Denoising

arXiv:2502.18915v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, they are of

End2Reg: Learning Task-Specific Segmentation for Markerless Registration in Spine Surgery

arXiv:2512.13402v2 Announce Type: replace Abstract: Intraoperative navigation in spine surgery demands millimeter-level accuracy. Currently, this is achieved through radiation-intensive intraoperative

Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies

arXiv:2502.17518v2 Announce Type: replace Abstract: This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging clas

EPC-3D-Diff: Equivariant Physics Consistent Conditional 3D Latent Diffusion for CBCT to CT Synthesis

arXiv:2605.20470v1 Announce Type: new Abstract: Cone-beam CT (CBCT) is routinely acquired during radiotherapy for patient setup, but its quantitative reliability is degraded by scatter, noise, and rec

EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments

arXiv:2509.17396v4 Announce Type: replace Abstract: Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long convers

Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching

arXiv:2601.21662v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) are typically deterministic in nature and lack intrinsic mechanisms to quantify epistemic uncertainty, which reflects

Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

arXiv:2605.21488v1 Announce Type: new Abstract: Scaling test-time compute by iteratively updating a latent state has emerged as a powerful paradigm for reasoning. Yet the internal mechanisms that enab

Everywhere Valid Bounds on False Discovery Proportions in Conformal Inference

arXiv:2605.20726v1 Announce Type: cross Abstract: Modern applications of conformal inference to multiple testing problems, such as outlier detection and candidate selection, often involve selecting te

EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation

arXiv:2605.21485v1 Announce Type: new Abstract: Equivariant graph neural network (GNN) methods for antibody complementarity-determining region (CDR) design achieve the highest sequence recovery but su

Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers

arXiv:2605.21325v1 Announce Type: new Abstract: Linear attention has emerged as a cornerstone for efficient long-context architectures, as evidenced by its integration into state-of-the-art open-sourc

Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data

arXiv:2605.20514v1 Announce Type: new Abstract: We introduce FLASH-MAX, a shallow, exact-by-construction neural network architecture for predicting homogeneous electromagnetic fields from sparse point

Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning

arXiv:2605.20551v1 Announce Type: new Abstract: Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art meth

Fault-Tolerant, Rigidity-Preserving Control of Inflatable Truss Robots

arXiv:2605.20561v1 Announce Type: new Abstract: Isoperimetric robotic trusses can adapt to different tasks and environments because they have a high strength-to-weight ratio, can change their own shap

researcharxiv-cs-ro

Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities

arXiv:2605.21369v1 Announce Type: new Abstract: This paper describes the fifth edition of the Shared Task on Multilingual Coreference Resolution, held in conjunction with the CODI-CRAC 2026 workshop.

Finite-Time Regret Analysis of Retry-Aware Bandits

arXiv:2605.20854v1 Announce Type: new Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@k and max@k

Flow Map Language Models: One-step Language Modeling via Continuous Denoising

arXiv:2602.16813v3 Announce Type: replace Abstract: Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive

Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models

arXiv:2605.20950v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existin