research

From Markov to Laplace: How Mamba In-Context Learns Markov Chains

arXiv:2502.10178v2 Announce Type: replace Abstract: While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viabl

From Zipf's Law to Neural Scaling through Heaps' Law and Hilberg's Hypothesis

DGX agent

arXiv:2512.13491v3 Announce Type: replace-cross Abstract: We inspect the deductive connection between the neural scaling law and Zipf's law -- two statements discussed in machine learning and quantita

researcharxiv-cs-lg

23 Jun 2026

Full Nonlinear Nonholonomic Dynamics and Motion Analysis of a 3-DoF Underactuated Spherical Rolling Robot

arXiv:2606.22169v1 Announce Type: new Abstract: This paper presents a full nonlinear constrained dynamic model of MonoRollBot, a novel 3-DoF spherical rolling robot driven by a single motor, a lead-sc

researcharxiv-cs-ro

G-MASt3R-SfM: Graph-based View Pruning and Multi-stage Optimization for Robust SfM

arXiv:2606.22856v1 Announce Type: new Abstract: Structure from Motion (SfM) is essential for multi-view 3D reconstruction, however, its accuracy heavily relies on the accuracy of image matching. While

Gated MLPs as Symmetry-Broken Rank-1 Bilinear Attention

arXiv:2606.22172v1 Announce Type: new Abstract: We show that the conventional gated MLP can be viewed as a rank-1 approximation to a bilinear attention mechanism with two distinct factors correspondin

Generative Modeling via Kernelized Stochastic Interpolants

arXiv:2602.20070v3 Announce Type: replace Abstract: We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear system

Generative Relightable Avatars

arXiv:2606.22718v1 Announce Type: new Abstract: We present Generative Relightable Avatars (GRA), a person-specific method for photorealistic free-view rendering and environment-map relighting of full-

GeoFlow-SLAM++: A Robust Multi-Camera Visual-Inertial SLAM System with Relocalization

arXiv:2606.22051v1 Announce Type: new Abstract: Monocular and RGB-D visual-inertial SLAM systems remain susceptible to limited field of view, sensor-specific failure modes, and unreliable cross-sessio

researcharxiv-cs-ro

Geometric and Information Compression of Representations in Deep Learning

arXiv:2606.21593v1 Announce Type: new Abstract: Deep neural networks transform input data into latent representations that support a wide range of downstream tasks. These representations can be charac

Geometric Reconstruction of Extrinsic Contact Trajectories using Tactile Sensing and Proprioception for Tool Manipulation

arXiv:2606.22251v1 Announce Type: new Abstract: Tactile sensing enables robots to perceive rich contact information at the grasp, supporting tasks such as object recognition, in-hand pose estimation,

researcharxiv-cs-ro

GIM-ENDO: A Multimodal Endoscopic Image and Video Dataset for Gastric Intestinal Metaplasia Morphology and Pathology

arXiv:2606.20919v1 Announce Type: new Abstract: Gastric intestinal metaplasia (GIM) is a precursor lesion to gastric dysplasia and adenocarcinoma whose early detection is crucial for intervening in th

Go-with-the-Track: Video Compositing and Motion Control with Point Tracking

arXiv:2606.20891v1 Announce Type: new Abstract: Filmmaking demands precise motion control and reference image compositing -- capabilities that existing methods treat separately. Point-track-conditione

Gradient-Descent Steps to Success over Mean Accuracy: A Paradigm Shift for ML

arXiv:2606.22053v1 Announce Type: new Abstract: Traditional evaluation of machine learning (ML) models typically focuses on achieving the maximum possible accuracy irrespective of the computational co

Gradual Capacity Growth for Sparse Network Discovery

arXiv:2509.25665v2 Announce Type: replace Abstract: Sparse neural network methods typically assume that the target sparsity (or density) is fixed in advance, even though the relationship between netwo

GRAIN: Group Aggregation via Min-Norm Objective

arXiv:2606.22917v1 Announce Type: new Abstract: Learning instability is a long-standing problem across machine learning, but it is especially acute in the overparameterized regime that defines modern

GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs

arXiv:2606.23299v1 Announce Type: new Abstract: Configuring the hyperparameters of Mixed-integer programming (MIP) solvers is a high-dimensional, instance-dependent optimization problem where suboptim

Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation

arXiv:2606.19636v2 Announce Type: replace Abstract: Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal

Heads in the game

The Argentina v. France final of the 2022 Men’s World Cup in Qatar was shaping up to be one of the most epic games in soccer history. With just 12 minutes remaining in the extra time added to the game

researchmit-tech-review

HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning

arXiv:2509.22645v2 Announce Type: replace Abstract: Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-traine

HERO: Hypothesis-Driven Evidence Retrieval from Omics for Multi-Task Breast Cancer Analysis

arXiv:2606.21174v1 Announce Type: new Abstract: Matched multi-omics can improve WSI-based biomarker and prognosis prediction, but most existing pipelines use omics as a paral lel feature stream or tex

Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation

arXiv:2602.03448v2 Announce Type: replace Abstract: Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following text

Hierarchical Pooling for Sheaf Neural Networks

arXiv:2606.20932v1 Announce Type: new Abstract: Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction

High-Dimensional Differentially Private Quantile Regression: Distributed Estimation and Statistical Inference

arXiv:2508.05212v2 Announce Type: replace-cross Abstract: With the development of big data and machine learning, privacy concerns have become increasingly critical, especially when handling heterogene

How Well Can Your Video Model Remember? Measuring Memory-Budget Trade-offs in Long Video Understanding

arXiv:2606.20726v1 Announce Type: new Abstract: We introduce a compact empirical model that quantifies how answer accuracy degrades as a function of frame budget B and temporal distance D in long vide

HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning

arXiv:2606.21734v1 Announce Type: new Abstract: Understanding long videos requires fine-grained perception and multi-step, higher-order reasoning over complex, long-range spatio-temporal dynamics. Vis

Human and AI collaboration for pulmonary nodule segmentation

arXiv:2606.22486v1 Announce Type: new Abstract: Medical expert annotators are scarce, and blind reliance on artificial intelligence (AI) can be misleading, motivating approaches in which humans, parti

'I do not believe that AI is likely to cure cancer anytime soon'—@2plus2makes5 https://www.theatlantic.com/technology/2026/06/ai-cancer-prog…

'I do not believe that AI is likely to cure cancer anytime soon'—@2plus2makes5 https://www.theatlantic.com/technology/2026/06/ai-cancer-progress/687654/?gift=yDcMMOSj-3oJk8475KVVBne5CfZXWcmKJJrUAGArmL

researchyann-lecun--x

IDAG-Edit: Multi-Object Video Editing via Instance-Decoupled Attention and Guidance

arXiv:2606.22042v1 Announce Type: new Abstract: Diffusion-based video editing has made significant progress; however, achieving precise and temporally consistent object-level control, especially in mu

In software, complexity is a tax you pay on every future change. You might think, 'as long as it works, I'm good, I don't care about aesthet…

researchfrancois-chollet--x

In software, complexity is a tax you pay on every future change. You might think, 'as long as it works, I'm good, I don't care about aesthetics', but elegant code is about maintainability, not aesthet

Incremental Learning in Mirror Flows

arXiv:2606.23198v1 Announce Type: cross Abstract: We study mirror flows generated by a convex quadratic loss and a general convex lower semicontinuous mirror potential. We show that, when initialized

Input-schema identifiability limits in physics-informed surrogates for mechanics-governed flow

arXiv:2606.20655v1 Announce Type: cross Abstract: Physics-informed and data-driven surrogates are increasingly used to approximate mechanics-governed flow fields, but the target quantities assigned to

Integrated Marketing Attribution: A Bayesian Framework for Privacy-Safe Granular Measurement Anchored in MMM

arXiv:2606.16878v3 Announce Type: replace Abstract: Retail marketing measurement increasingly requires granular campaign-level insights without relying on user-level tracking. However, the two dominan

InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars

arXiv:2606.22905v1 Announce Type: new Abstract: Recent diffusion-based models have enabled realistic audio-driven avatar generation in real-time streaming. However, existing approaches struggle to mai

Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization

arXiv:2606.22353v1 Announce Type: new Abstract: Fidelity and perceptual quality are two inherently competing and conflicting objectives in the image super-resolution (SR) task. Different loss function

Interleaved Speech Language Models Latently Work In Text

arXiv:2606.22473v1 Announce Type: cross Abstract: Speech language models (SLMs) have been extensively studied, with the common paradigm incorporating text data and pre-trained text LMs. A leading appr

Interpretable Kolmogorov-Arnold Network with Feature-Isolated Temporal Attention Mechanism for Electricity Load Forecasting

arXiv:2606.23425v1 Announce Type: new Abstract: Accurate electricity load forecasting is a crucial prerequisite for stable power system operations. While prevalent deep learning models present competi

Interpretable machine learning of halo gas density profiles: a sensitivity analysis of cosmological hydrodynamical simulations

arXiv:2512.09021v3 Announce Type: replace-cross Abstract: Stellar and AGN-driven feedback processes affect the distribution of gas on a wide range of scales, from within galaxies well into the interga

Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition

arXiv:2606.22725v1 Announce Type: new Abstract: Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distrib

Intrinsic Flow Matching on Quantum Pure-State Manifolds with Phase-Aligned Transport

arXiv:2606.21256v1 Announce Type: new Abstract: Quantum pure-state ensembles live on complex projective space, making flat Euclidean generative modeling geometrically mismatched. We introduce Intrinsi

Is Oracle Pruning the True Oracle?

arXiv:2412.00143v2 Announce Type: replace-cross Abstract: Oracle pruning, which selects unimportant weights by minimizing the pruned train loss, has served as the foundation for most neural network pr

Iterative Diffusion-Refined Neural Attenuation Fields for Multi-Source Stationary CT Reconstruction: NAF Meets Diffusion Model

arXiv:2511.14310v2 Announce Type: replace Abstract: Multi-source stationary computed tomography (CT) has recently attracted attention for its ability to achieve rapid image reconstruction, making it s

Jacobian-Adaptive Weighting for Stability: Enhancing Long-term Rollout of Neural Partial Differential Equation Solvers via Spatially-Adaptive Regularization

arXiv:2603.05538v3 Announce Type: replace Abstract: Data-driven surrogate models can significantly accelerate the simulation of continuous dynamical systems, yet the step-wise accumulation of errors d

Jacobian-Aware Posterior Sampling for Inverse Problems

arXiv:2511.18471v3 Announce Type: replace Abstract: Diffusion models provide powerful generative priors for solving inverse problems by sampling from a posterior distribution conditioned on corrupted

Kernel of Partition Paths: A Unified Representation for Tree Ensembles

arXiv:2606.18853v2 Announce Type: replace-cross Abstract: A recent line of work has reframed individual decision trees as linear models on engineered features associated with their splits, opening rou

Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification

arXiv:2606.22369v1 Announce Type: cross Abstract: In this paper, we present Kiwano, an open-source toolkit designed to advance research and evaluation for speaker verification. Kiwano provides a light

Kolmogorov-Arnold Reservoir Computing

arXiv:2606.19984v2 Announce Type: replace Abstract: Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle to capture long-range dependencies due to limi

Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization

arXiv:2512.09678v2 Announce Type: replace-cross Abstract: In this article, we explore the use of various matrix norms for optimizing functions of weight matrices, a crucial problem in deep learning. M

Lane Change Intention Prediction of two distinct Populations using a Transformer

arXiv:2509.06529v2 Announce Type: replace Abstract: In complex traffic scenarios, intention prediction of surrounding vehicles can improve the strategy of automated driving functions. Existing work on