Search: “research”

Active Embodiment Identification with Reinforcement Learning for Legged Robots

arXiv:2605.08020v1 Announce Type: new Abstract: We present an active embodiment identification method for legged robots that jointly learns information-seeking behavior and explicit embodiment predict

AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers

DGX agent

arXiv:2602.13357v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive infer

researcharxiv-cs-ai

11 May 2026

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation

arXiv:2604.02525v2 Announce Type: replace Abstract: Hadamard transforms have become a key tool for stabilizing low-precision training, but existing methods apply them uniformly across tensors and comp

Adaptive auditing of AI systems with anytime-valid guarantees

arXiv:2605.07002v1 Announce Type: new Abstract: A major bottleneck in characterizing the failure modes of generative AI systems is the cost and time of annotation and evaluation. Consequently, adaptiv

Adaptive Domain Decomposition Physics-Informed Neural Networks for Traffic State Estimation with Sparse Sensor Data

arXiv:2605.08028v1 Announce Type: new Abstract: Traffic state estimation from sparse fixed sensors is challenging because physics-informed neural networks (PINNs) tend to over-smooth the shockwaves ad

AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning

arXiv:2605.07121v1 Announce Type: new Abstract: Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, exis

AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting

arXiv:2605.06876v1 Announce Type: new Abstract: Adaptive density control in 3D Gaussian Splatting (3DGS) repeatedly grows the Gaussian population through fixed-cardinality random splitting to discover

Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge

arXiv:2605.06912v1 Announce Type: new Abstract: The proliferation of generative video technologies has intensified the need for reliable methods to detect and characterize synthetic media. To address

AERO-VIS: Asynchronous Event-based Real-time Onboard Visual-Inertial SLAM

arXiv:2605.07885v1 Announce Type: new Abstract: The robustness of event cameras to high dynamic range and motion blur holds the potential to improve visual odometry systems in challenging environments

AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks

arXiv:2605.06218v2 Announce Type: replace Abstract: Piecewise affine neural networks (PANNs) provide a principled geometric perspective on neural network expressivity by characterizing the input--outp

AGA3DNet: Anatomy-Guided Gaussian Priors with Multi-view xLSTM for 3D Brain MRI Subtype Classification

arXiv:2605.07142v1 Announce Type: new Abstract: Accurate 3D brain MRI subtype classification benefits from both localized anatomical cues and long-range contextual reasoning. We present AGA3DNet, a re

Model Releases

Agentick: A Unified Benchmark for General Sequential Decision-Making Agents

model-releasesarxiv-cs-ai

arXiv:2605.06869v1 Announce Type: new Abstract: AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no u

Aggregation in conformal e-classification

arXiv:2605.07963v1 Announce Type: new Abstract: Aggregating conformal predictors is a standard way of balancing their predictive and computational efficiency while retaining their validity, at least a

AirBender: Adaptive Transportation of Bendable Objects Using Dual UAVs

arXiv:2605.07003v1 Announce Type: new Abstract: The interaction of robots with bendable objects in midair presents significant challenges in control, often resulting in performance degradation and pot

Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift

arXiv:2605.07104v1 Announce Type: new Abstract: Establishing almost sure convergence rates for stochastic approximation and reinforcement learning under Markovian noise is a fundamental theoretical ch

Amortized-Precision Quantization for Early-Exit Vision Transformers

arXiv:2605.07317v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Exis

An abstract effective convergence theorem for stochastic processes, with applications to stochastic approximation

arXiv:2504.12922v3 Announce Type: replace-cross Abstract: We provide a general theorem on the asymptotic behavior of stochastic processes that conform to a relaxed supermartingale condition. The disti

Aquatic Neuromorphic Optical Flow

arXiv:2605.07653v1 Announce Type: new Abstract: Underwater environments impose severe constraints on conventional imaging systems and demand solutions that balance high-quality sensing with strict res

Arrow: A Foundation Model for Causal Discovery

arXiv:2605.07204v1 Announce Type: new Abstract: We introduce Arrow, a foundation model for zero-shot causal discovery on observational tabular data. Arrow factorizes a directed acyclic graph into an u

Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means

arXiv:2605.07964v1 Announce Type: cross Abstract: Confidence sequences based on test martingales provide time-uniform uncertainty quantification for the mean of bounded IID observations without parame

AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes

arXiv:2605.07192v1 Announce Type: new Abstract: 3D reconstruction methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) achieve impressive photorealism but fail when input ima

Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering

arXiv:2603.18636v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, motivating spar

Model Releases

Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks

model-releasesarxiv-cs-lg

arXiv:2605.06834v1 Announce Type: new Abstract: Continual learning research attempts to conserve two fundamental capabilities: new knowledge acquisition and the preservation of previously acquired kno

Automated Evaluation can Distinguish the Good and Bad AI Responses to Patient Questions about Hospitalization

arXiv:2510.00436v2 Announce Type: replace Abstract: Automated approaches to answer patient-posed health questions are rising, but selecting among systems requires reliable evaluation. The current gold

Automatic Image-Level Morphological Trait Annotation for Organismal Images

arXiv:2604.01619v3 Announce Type: replace-cross Abstract: Morphological traits are physical characteristics of biological organisms that provide vital clues on how organisms interact with their enviro

BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning

arXiv:2605.07394v1 Announce Type: cross Abstract: Image captioning is one of the most fundamental tasks in computer vision. Owing to its open-ended nature, it has received significant attention in the

Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation

arXiv:2505.22842v4 Announce Type: replace Abstract: Transformer-based language models rely on positional encoding (PE) to handle token order and support context length extrapolation. However, existing

Bayesian Conformal Prediction as a Decision Risk Problem

arXiv:2602.03331v2 Announce Type: replace Abstract: We propose Bayesian Conformal Prediction (BCP), a framework that combines Bayesian posterior predictive distributions with PAC-style conformal risk

Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

arXiv:2605.07590v1 Announce Type: new Abstract: Despite extensive progress in point cloud robustness, existing methods primarily improve performance through augmentation or defense mechanisms, while o

Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning

arXiv:2605.07557v1 Announce Type: new Abstract: Semi-supervised learning faces significant challenges in realistic scenarios where labeled data is scarce and unlabeled data follows unknown, arbitrary

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs

arXiv:2605.07153v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge rema

Bilevel Graph Structure Learning, Revisited: Inner-Channel Origins of the Reported Gain

arXiv:2605.07577v1 Announce Type: new Abstract: Bilevel graph structure learning is widely understood to improve graph neural networks by jointly optimizing model parameters and a learned graph struct

Black-box model classification under the discriminative factorization

arXiv:2605.07878v1 Announce Type: new Abstract: Access to modern generative systems is often restricted to querying an API (the ``black-box' setting) and many properties of the system are unknown to t

Bloom Filter Encoding for Machine Learning

arXiv:2512.19991v2 Announce Type: replace Abstract: We present a method that uses a Bloom filter transform to preprocess data for machine learning. Each sample is encoded into a compact bit-array repr

Bounded Fitting for Expressive Description Logics

arXiv:2605.07452v1 Announce Type: new Abstract: Bounded fitting is an attractive paradigm for learning logical formulas from labeled data examples that offers PAC-style generalization guarantees and c

Breaking QAOA's Fixed Target Hamiltonian Barrier: A Fully Connected Quantum Boltzmann Machine via Bilevel Optimization

arXiv:2605.07473v1 Announce Type: cross Abstract: To overcome the limitations of classical partially connected Boltzmann machines and mainstream quantum Boltzmann machines (QBMs), this work extends th

Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding

arXiv:2605.06679v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are frequently undermined by object hallucination, generating content that contradicts visual reality, due to an over-reli

Bridging Textual Profiles and Latent User Embeddings for Personalization

arXiv:2605.06981v1 Announce Type: cross Abstract: Personalized systems rely on user representations to connect behavioral history with downstream recommendation applications. Existing methods typicall

CARMEN: CORDIC-Accelerated Resource-Efficient Multi-Precision Inference Engine for Deep Learning

arXiv:2605.06878v1 Announce Type: cross Abstract: This paper presents CARMEN, a runtime-adaptive, CORDIC-accelerated multi-precision vector engine for resource-efficient deep learning inference. The k

CASCADE: Context-Aware Relaxation for Speculative Image Decoding

arXiv:2605.07230v1 Announce Type: cross Abstract: Autoregressive generation is a powerful approach for high-fidelity image synthesis, but it remains computationally demanding and slow even on the most

CellScientist: Dual-Space Hierarchical Orchestration for Closed-Loop Refinement of Virtual Cell Models

arXiv:2605.07335v1 Announce Type: new Abstract: Virtual Cell Modeling (VCM) requires models that not only predict perturbation responses, but also support targeted revision when predictions fail. Curr

CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption

arXiv:2602.01621v3 Announce Type: replace-cross Abstract: Homomorphic encryption (HE) is a prominent framework for privacy-preserving machine learning, enabling inference directly on encrypted data. H

CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization

arXiv:2605.07162v1 Announce Type: new Abstract: Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However,

Closed-Form Last Layer Optimization

arXiv:2510.04606v2 Announce Type: replace Abstract: Neural networks are typically optimized with variants of stochastic gradient descent. Under a squared loss, however, the optimal solution to the lin

Cloud-top infrared observations reveal the four-dimensional precipitation structure

arXiv:2605.07499v1 Announce Type: new Abstract: Accurate four-dimensional (4D) precipitation information is essential for understanding the Earth's energy and water cycles, yet remains observationally

Model Releases

Cluster-level reliability for trillion-parameter models on TPUs

model-releasesgoogle-cloud-ai

Frontier AI models have redefined the unit of compute. At trillion-parameter scale, AI training requires thousands of interconnected components, orchestrated in industrial-scale deployments to operate

Code Generation and Conic Constraints for Model-Predictive Control on Microcontrollers with Conic-TinyMPC

arXiv:2403.18149v3 Announce Type: replace Abstract: Model-predictive control (MPC) is a state-of-the-art control method for constrained robotic systems, yet deployment on resource-limited hardware rem

Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation

arXiv:2510.07926v2 Announce Type: replace Abstract: Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce o