Search: “research”

Pre-trained Tabular Foundation Models as Versatile Summary Networks for Neural Posterior Estimation

arXiv:2605.07765v1 Announce Type: new Abstract: In this work, we study TabPFN as a training-free, modular summary network for simulation-based Bayesian inference (SBI). Tabular foundation models such

Research

Pre-training Enables Extraordinary All-optical Image Denoising

DGX agent

arXiv:2605.07810v1 Announce Type: cross Abstract: Optical neural networks are emerging as powerful machine learning and information processing tools because of their potential advantages in speed and

researcharxiv-cs-cv

11 May 2026

Pretty Good Measurement for Radiomics: A Quantum-Inspired Multi-Class Classifier for Lung Cancer Subtyping and Prostate Cancer Risk Stratification

arXiv:2603.00223v2 Announce Type: replace Abstract: We investigate a quantum-inspired approach to supervised multi-class classification based on the Pretty Good Measurement (PGM), viewed as an operato

Privately Estimating Black-Box Statistics

arXiv:2510.00322v3 Announce Type: replace-cross Abstract: Standard techniques for differentially private estimation, such as Laplace or Gaussian noise addition, require guaranteed bounds on the sensit

ProteinJEPA: Latent prediction complements protein language models

arXiv:2605.07554v1 Announce Type: cross Abstract: Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask wh

ProtSent: Protein Sentence Transformers

arXiv:2605.06830v1 Announce Type: cross Abstract: Protein language models (pLMs) produce per-residue representations that capture evolutionary and structural information, yet their mean-pooled sequenc

QuadNorm: Resolution-Robust Normalization for Neural Operators

arXiv:2605.07375v1 Announce Type: new Abstract: Normalization layers in neural operators usually compute statistics by uniformly averaging discrete grid values, making the normalization itself discret

R^3L: Reasoning 3D Layouts from Relative Spatial Relations

arXiv:2605.06758v1 Announce Type: cross Abstract: Relative spatial relations provide a compact representation of spatial structure and are fundamental to relative spatial reasoning in 3D layout genera

Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions

arXiv:2605.07945v1 Announce Type: new Abstract: We present CoopNet, an approach that improves the cooperation of co-trained networks by dynamically adapting the apportionment of gradient, to ensure eq

Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning

arXiv:2605.07155v1 Announce Type: new Abstract: Agnostic online learning is classically solved via a reduction to the realizable setting, utilizing Littlestone's Standard Optimal Algorithm (SOA) as a

Regulating Branch Parallelism in LLM Serving

arXiv:2605.06914v1 Announce Type: cross Abstract: Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute

Relay Buffer Independent Communication over Pooled HBM for Efficient MoE Inference on Ascend

arXiv:2605.06055v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) inference requires large-scale token exchange across devices, making dispatch and combine major bottlenecks in both p

Reliable Chain-of-Thought via Prefix Consistency

arXiv:2605.07654v1 Announce Type: cross Abstract: Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority

Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts

arXiv:2605.07307v1 Announce Type: new Abstract: Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must

Rethinking Experience Utilization in Self-Evolving Language Model Agents

arXiv:2605.07164v1 Announce Type: new Abstract: Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is const

Retrieval from Within: An Intrinsic Capability of Attention-Based Models

arXiv:2605.05806v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decode

Retrieval Heads are Dynamic

arXiv:2602.11162v2 Announce Type: replace Abstract: Recent studies have identified 'retrieval heads' in Large Language Models (LLMs) responsible for extracting information from input contexts. However

Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning

arXiv:2605.07106v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence int

Revisiting Adam for Streaming Reinforcement Learning

arXiv:2605.06764v1 Announce Type: cross Abstract: Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, holds the promise of

RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection

arXiv:2602.19974v2 Announce Type: replace Abstract: Recent advancements in image generation have achieved impressive results in producing high-quality images. However, existing image generation models

Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling

arXiv:2605.07634v1 Announce Type: cross Abstract: We consider a first order stochastic optimization framework where, at each iteration, K independent identically distributed (i.i.d.) data point sample

Saliency-Aware Regularized Quantization Calibration for Large Language Models

arXiv:2605.05693v2 Announce Type: replace Abstract: Post-training quantization (PTQ) is an effective approach for deploying large language models (LLMs) under memory and latency constraints. Most exis

SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild

arXiv:2605.07604v1 Announce Type: cross Abstract: 3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scene

Sample Complexity of Stochastic Optimization with Integer Variables

arXiv:2605.07239v1 Announce Type: new Abstract: We establish sample complexity results for stochastic optimization over the integers, especially with a view to understand the complexity with respect t

Saving Foundation Flow-Matching Priors for Inverse Problems

arXiv:2511.16520v2 Announce Type: replace-cross Abstract: Foundation flow-matching (FM) models promise a universal prior for solving inverse problems (IPs), yet today they trail behind domain-specific

Scalable Equilibrium Propagation via Intermediate Error Signals for Deep Convolutional CRNNs

arXiv:2508.15989v2 Announce Type: replace Abstract: Equilibrium Propagation (EP) is a biologically inspired local learning rule first proposed for convergent recurrent neural networks (CRNNs), in whic

Scalable Option Learning in High-Throughput Environments

arXiv:2509.00338v3 Announce Type: replace-cross Abstract: Hierarchical reinforcement learning (RL) has the potential to enable effective decision-making over long timescales. Existing approaches, whil

Model Releases

Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts

model-releasesarxiv-cs-cv

arXiv:2602.03473v2 Announce Type: replace-cross Abstract: Continual learning, especially class-incremental learning (CIL), on the basis of a pre-trained model (PTM) has garnered substantial research i

SEIF: Self-Evolving Reinforcement Learning for Instruction Following

arXiv:2605.07465v1 Announce Type: new Abstract: Instruction following is a fundamental capability of large language models (LLMs), yet continuously improving this capability remains challenging. Exist

Self-Consolidating Language Models: Continual Knowledge Incorporation from Context

arXiv:2605.07076v1 Announce Type: new Abstract: Large language models (LLMs) increasingly receive information as streams of passages, conversations, and long-context workflows. While longer context wi

Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics

arXiv:2605.06730v1 Announce Type: new Abstract: We introduce Semantic State Abstraction Interfaces (SSAI): a methodological template for mapping sparse unstructured text into K auditable, named coordi

Semiparametric Efficient Test for Interpretable Distributional Treatment Effects

arXiv:2605.08034v1 Announce Type: cross Abstract: Distributional treatment effects can be invisible to means: a treatment may preserve average outcomes while changing tails, modes, dispersion, or rare

SGD for Variational Inference: Tackling Unbounded Variance via Preconditioning and Dynamic Batching

arXiv:2605.07531v1 Announce Type: new Abstract: Black-Box Variational Inference (BBVI) typically relies on Stochastic Gradient Descent (SGD) to optimize the Evidence Lower Bound (ELBO). However, the s

Shaping the Future of Mathematics in the Age of AI

arXiv:2603.24914v2 Announce Type: replace-cross Abstract: Artificial intelligence is transforming mathematics at a speed and scale that demand active engagement from the mathematical community. We exa

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion

arXiv:2605.07482v1 Announce Type: cross Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous

Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise

arXiv:2602.07425v2 Announce Type: replace-cross Abstract: While adaptive gradient methods are the workhorse of modern machine learning, sign-based optimization algorithms such as Lion and Muon have re

Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models

arXiv:2509.25584v2 Announce Type: replace Abstract: Vision-language models achieve incredible performance across a wide range of tasks, but their large size makes inference costly. Recent work has sho

SMT-Based Active Learning of Weighted Automata

arXiv:2605.07758v1 Announce Type: cross Abstract: We present an SMT-based active learning algorithm for nondeterministic weighted automata (WFAs) as a practical and robust alternative to Hankel/L*-sty

SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration

arXiv:2605.07346v1 Announce Type: new Abstract: Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods

Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks

arXiv:2605.07113v1 Announce Type: new Abstract: Exact solution of hard combinatorial optimization problems often relies on strong convex relaxations, but solving these relaxations repeatedly inside a

Sparse Attention as Compact Kernel Regression

arXiv:2601.22766v3 Announce Type: replace Abstract: Recent work has revealed a link between self-attention mechanisms in transformers and test-time kernel regression via the Nadaraya-Watson estimator,

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting

arXiv:2605.07243v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters f

Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer

arXiv:2605.07870v1 Announce Type: cross Abstract: We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mea

Spectral Filtering for Complex Linear Dynamical Systems

arXiv:2601.22400v2 Announce Type: replace-cross Abstract: We study the problem of learning complex-valued linear dynamical systems (CLDS) with sector-bounded spectrum. This class captures oscillatory

Spectral Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation

arXiv:2605.07790v1 Announce Type: cross Abstract: The Hessian spectrum of trained deep networks exhibits a characteristic structure: a continuous bulk of near-zero eigenvalues and a small number of la

Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers

arXiv:2605.07297v1 Announce Type: cross Abstract: Understanding why trained Transformers generalize well is a fundamental problem in modern machine learning theory, and complexity-based generalization

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere

arXiv:2605.08003v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods

SSP-based construction of evaluation-annotated data for fine-grained aspect-based sentiment analysis

arXiv:2605.07446v1 Announce Type: new Abstract: We report the construction of a Korean evaluation-annotated corpus, hereafter called 'Evaluation Annotated Dataset (EVAD)', and its use in Aspect-Based