Search: “research”

Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation

arXiv:2606.23157v1 Announce Type: new Abstract: This paper presents a modular training-free framework for zero-shot, language-guided robotic manipulation in semi-structured environments. The architect

Research

C^2GR: Coupled Comprehensive Generative Replay for a Continually Learnable Universal Segmentation Model

DGX agent

arXiv:2606.23473v1 Announce Type: new Abstract: Universal segmentation models exhibit significant potential for diverse tasks involving different imaging modalities and segmentation objectives. Task-I

researcharxiv-cs-cv

23 Jun 2026

Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning

arXiv:2606.16214v3 Announce Type: replace Abstract: Modern deep learning models remain notoriously prone to overconfidence, limiting their reliability in high-stakes applications. Bayesian methods aim

Can Reasoning Models Detect Changes to their Chains of Thought?

arXiv:2606.22085v1 Announce Type: cross Abstract: There are many reasons one may want to edit a model's chain of thought (CoT) -- e.g., to prefill it with reasoning from a stronger model or to remove

Can Single-View Mesh Reconstruction Generalize to Robot Camera Rotation?

arXiv:2606.22987v1 Announce Type: new Abstract: Single-view mesh reconstruction predicts object meshes and spatial layouts from a single observation, making it attractive for fast robot spatial reason

Casual: Token maxxing Sweaty: Token minning Meta: Token min-maxing

researchfrancois-chollet--x

Francois Chollet presents a framework for understanding different approaches to token usage in AI models: casual users maximize tokens for flexibility, competitive users minimize tokens for efficiency

Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition

arXiv:2412.06190v2 Announce Type: replace Abstract: Benefiting from the generalization capability of CLIP, recent vision language pre-training (VLP) models have demonstrated the ability to capture a w

Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation

arXiv:2606.23280v1 Announce Type: new Abstract: Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis. Howeve

Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images

arXiv:2606.21806v1 Announce Type: new Abstract: Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains. A common sourc

Central limit theorem for the averaged Adam optimizer

arXiv:2606.21433v1 Announce Type: cross Abstract: In this article, we analyse convergence of the averaged Adam optimizer to an attracting zero of the Adam vector field. We provide a central limit theo

Certified World Models: Predictability Across Configuration, Horizon, and Resolution

arXiv:2606.13092v2 Announce Type: replace Abstract: Scale buys interpolation; structure buys certifiable transfer. A world model's average error does not say whether a particular rollout can be truste

C’est elle qui a jeté Fauci en pâture relayé ensuite par RFK et Musk… Je vous le dis Le RN au pouvoir ça sera ça. On peut ne pas être conten…

C’est elle qui a jeté Fauci en pâture relayé ensuite par RFK et Musk… Je vous le dis Le RN au pouvoir ça sera ça. On peut ne pas être content. Vouloir du changement. Mais le changement ça peut être en

researchyann-lecun--x

CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks

arXiv:2606.20747v1 Announce Type: new Abstract: Explainable Artificial Intelligence aims to make black-box models more trustworthy by presenting, in a human-understandable manner, the elements that le

Circuit realization and hardware linearization of monotone operator equilibrium networks

arXiv:2509.13793v2 Announce Type: replace-cross Abstract: It is shown that the port behavior of a resistor-diode network corresponds to the solution of a ReLU monotone operator equilibrium network (a

Circuit Synchronization Precedes Generalization: A Causal Precursor to Grokking

arXiv:2606.12966v2 Announce Type: replace Abstract: Grokking is the delayed generalisation phenomenon where a transformer trained on modular arithmetic abruptly transitions from near-chance to near-pe

CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition

arXiv:2606.22837v1 Announce Type: new Abstract: Sensors are critical components of modern intelligent devices. The proliferation of the Internet of Things (IoT) and wearable mobile devices has enabled

Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA

arXiv:2606.22836v1 Announce Type: new Abstract: We present Cloak, a training recipe that endows a Vision-Language-Action (VLA) model with zero-shot cross-embodiment transfer by cloaking the end-effect

CLoE: Expert Consistency Learning for Robust Missing Modality Segmentation

arXiv:2603.09316v2 Announce Type: replace Abstract: Multimodal medical image segmentation often faces missing modalities at inference, which induces disagreement among modality experts and makes fusio

Closing the Calibration Gap in Semantic Caching

arXiv:2606.19719v2 Announce Type: replace-cross Abstract: Semantic caching cuts LLM inference costs by serving a cached response to semantically similar queries. Standard practice evaluates these syst

CogniRoute: Learning to Route Social Evidence in Omni-Modal Models

arXiv:2606.20970v1 Announce Type: new Abstract: Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence.

Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning

arXiv:2606.21083v1 Announce Type: cross Abstract: Large language models (LLMs) deployed for logical reasoning in knowledge-intensive domains exhibit a subtle but critical failure: coherence can be vac

Collapsed Effective Operators for Higher-order Structures

arXiv:2606.23517v1 Announce Type: new Abstract: Higher-order structures are powerful relational modeling tools, yet existing spectral operators decompose the topology into separate ranks, leaving prac

Combinatorial Allocation Bandits with Nonlinear Arm Utility

arXiv:2603.07005v2 Announce Type: replace Abstract: A matching platform is a system that matches participants of different types, such as companies and job-seekers. In such a platform, maximizing matc

Compression and Retrieval: Implicit Memory Retrieval for Video World Models

arXiv:2606.23105v1 Announce Type: new Abstract: Video world models hold promise for simulating interactive environments, yet maintaining consistent long-term memory across complex camera trajectories

Conceptual Design of an Ecosystem for Real Farm Data Collection toward Agricultural AI Foundation Models

arXiv:2606.23258v1 Announce Type: new Abstract: Data scarcity is a fundamental challenge in developing AI and foundation models for agricultural robots. Existing open-source data platforms do not prov

Conditional neural control variates for variance reduction in Bayesian inverse problems

arXiv:2602.21357v2 Announce Type: replace-cross Abstract: Bayesian inference for inverse problems involves computing expectations under posterior distributions--e.g., posterior means, variances, or pr

Conformal and kNN Predictive Uncertainty Quantification Algorithms in Metric Spaces

arXiv:2507.15741v2 Announce Type: replace-cross Abstract: This paper introduces a framework for uncertainty quantification in regression models defined on metric spaces. Using a proposed notion of hom

Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models

arXiv:2606.22945v1 Announce Type: cross Abstract: Realistic integration of user-specified textures into scene images is a fundamental task in computer graphics and image editing. While existing materi

Convergence Analysis of Nystrom Subsampling in Covariate Shift Adaptation for Misspecified case

arXiv:2606.22259v1 Announce Type: cross Abstract: This paper investigates convergence properties of regularized Nystrom subsampling applied to the unsupervised domain adaptation problem under covariat

Convergence of Gradient Descent for General Neural Network Architectures Beyond the NTK Regime

arXiv:2606.23364v1 Announce Type: new Abstract: Training dynamics is central to understanding neural networks, yet its theoretical analysis remains difficult even for simple architectures and becomes

Convergence Rate Analysis of LION

arXiv:2411.07724v2 Announce Type: replace Abstract: The LION (evoLved sIgn mOmeNtum) optimizer for deep neural network training was found by Google via program search, with the simple sign update yet

Coupled Routing and Configuration Optimization for Multi-Viewpoint Robotic Inspection

arXiv:2606.20739v1 Announce Type: new Abstract: We present a unified framework that turns a set of 6-DoF inspection viewpoints into a time-optimal, collision-free route for a 9-DoF robotic system. Unl

Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring

arXiv:2606.22094v1 Announce Type: new Abstract: Accurate yaw estimation is a bottleneck in cross-view localization between ground view and Bird's Eye View (BEV). Existing methods couple yaw with trans

Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples

arXiv:2603.02370v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) have grown increasingly powerful in recent years, but can also exhibit harmful biases. Prior studies investigat

CuratorKIT : Data Curation and Synthetic Data Generation for LLM Post-Training

arXiv:2606.21631v1 Announce Type: cross Abstract: Data curation is a critical part of post-training pipelines for large language models, yet existing tools often treat ingestion, deduplication, synthe

DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagery

arXiv:2603.14837v2 Announce Type: replace Abstract: Analyzing street-view imagery with computer vision models offers a promising approach for rapid, hyperlocal disaster damage assessment, but existing

Data Evolution by Wittgenstein's Rule Following

arXiv:2606.22674v1 Announce Type: cross Abstract: This paper introduces Wittgenstein's Rule Following (WRF) data evolution, a framework in philomatics for evolving or generating a new dataset from a s

Data Selection Through Iterative Self-Filtering for Vision-Language Settings

arXiv:2606.23611v1 Announce Type: new Abstract: The availability of large amounts of clean data is paramount to training neural networks. However, at large scales, manual oversight is impractical, res

DE-FIVE: Detecting Malicious Image Prompts via Fourier Features and Image Vector Embeddings

arXiv:2606.22779v1 Announce Type: cross Abstract: Vision language models (VLMs) employ both visual and textual modalities to enable advanced vision-language inference. However, incorporating visual mo

Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers

arXiv:2606.21678v1 Announce Type: new Abstract: Language models can generate plausible rationales for their predictions, but these explanations may not faithfully represent the model's internal reason

Deep learning-based detection of cessation of breathing in pre-term infants

arXiv:2606.23213v1 Announce Type: new Abstract: Apnoea of prematurity is characterised by recurrent episodes of cessation of breathing and remains difficult to detect reliably using routinely monitore

Deep Learning for Soil Moisture Estimation: Fusing Satellite Data with Optimally-Lagged Meteorological Features

arXiv:2606.21475v1 Announce Type: new Abstract: Accurate soil moisture estimation in semi-arid agricultural regions requires integrating remote sensing and meteorological information while accounting

Deep material network for homogenization of piezoelectric composites

arXiv:2606.22566v1 Announce Type: cross Abstract: Piezoelectric composites are widely used in sensors, actuators, transducers, and energy-harvesting devices because their effective electromechanical p

Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining

arXiv:2606.16246v2 Announce Type: replace Abstract: As AI labs approach a data ceiling where compute capacity outpaces the rate of new high-quality text generation, language model pretraining is shift

Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation

arXiv:2606.21956v1 Announce Type: new Abstract: Infrared small target detection (IRSTD) in high-resolution images is crucial for many practical applications, such as surveillance of unmanned aerial ve

Detecting Satellites in Radio-Frequency Data via Semi-Supervised Learning

arXiv:2606.20976v1 Announce Type: new Abstract: Radio-frequency (RF) monitoring is essential for space domain awareness, but it often generates large, variable, and sparsely populated datasets with fe

Applications

Development and Design of FLKit: A Structured Onboarding Toolkit for Federated Learning in Health and Life Sciences

arXiv:2606.23500v1 Announce Type: cross Abstract: Federated learning lets institutions train shared models without moving their data, which makes it a natural fit for health and life sciences research

applicationsarxiv-cs-lg

DevoTG: Temporal Graph Neural Networks for Modeling C. elegans Developmental Connectomics

arXiv:2606.21940v1 Announce Type: new Abstract: Understanding how a nervous system wires itself from birth to adulthood is a fundamental challenge in developmental neuroscience. We present DevoTG, a t