Search: “research”

Analytic Bridge Diffusions for Controlled Path Generation

arXiv:2605.02961v1 Announce Type: new Abstract: Most modern bridge-diffusion methods achieve finite-time transport by specifying an interpolation, Schrodinger-bridge, or stochastic-control objective a

Are we Doomed to an AI Race? Why Self-Interest Could Drive Countries Towards a Moratorium on Superintelligence

DGX agent

arXiv:2605.01297v1 Announce Type: cross Abstract: This paper uses game theory to argue that, contrary to the prevailing view, a moratorium on Artificial Superintelligence (ASI) can be in a state's sel

researcharxiv-cs-ai

6 May 2026

AsymK-Talker: Real-Time and Long-Horizon Talking Head Generation via Asymmetric Kernel Distillation

arXiv:2605.02948v1 Announce Type: new Abstract: Recent advances in diffusion models have markedly enhanced the visual fidelity of audio-driven talking head generation. Nevertheless, existing methods a

Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial

arXiv:2605.03916v1 Announce Type: new Abstract: Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline docume

researcharxiv-cs-cl

Attribution-Guided Masking for Robust Cross-Domain Sentiment Classification

arXiv:2605.03091v1 Announce Type: new Abstract: While pre-trained Transformer models achieve high accuracy on in-domain sentiment classification, they frequently experience severe performance degradat

Bandits on graphs and structures

arXiv:2605.03493v1 Announce Type: new Abstract: The goal of this thesis is to investigate the structural properties of certain sequential problems in order to bring the solutions closer to a practical

Behavior-dLDS: A decomposed linear dynamical systems model for neural activity partially constrained by behavior

arXiv:2603.05612v2 Announce Type: replace-cross Abstract: Brain-wide recordings of large-scale networks of neurons now provide an unprecedented view into how the brain drives behavior. However, brain

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

arXiv:2603.10384v2 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework th

BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection

arXiv:2604.06022v2 Announce Type: replace Abstract: Incorrect information poses significant challenges by disrupting content veracity and integrity, yet most detection approaches struggle to jointly b

researcharxiv-cs-cl

Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction

arXiv:2605.03148v1 Announce Type: new Abstract: Reliable wildfire spread prediction is vital for risk-aware emergency planning, yet most deep learning models lack principled uncertainty quantification

Caliper-in-the-Loop: Black-Box Optimization for Hyperledger Fabric Performance Tuning

arXiv:2605.02690v1 Announce Type: cross Abstract: Hyperledger Fabric performance depends on many interacting configuration parameters, making manual tuning difficult. We study automated throughput tun

Can Blockchains Reliably Train Machine Learning Models?

arXiv:2307.07066v2 Announce Type: replace-cross Abstract: Large proof of work (PoW) networks allow anyone to earn rewards by running computation-intensive hash puzzles for profit, yet they typically c

Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology

arXiv:2605.03352v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated robust capabilities in recognizing everyday human activities, yet their potential for analyzi

Cascade Token Selection for Transformer Attention Acceleration

arXiv:2605.03110v1 Announce Type: new Abstract: A method is presented for reducing the cost of representative token selection in transformer attention layers by exploiting the coherence of the represe

CellxPert: Inference-Time MCMC Steering of a Multi-Omics Single-Cell Foundation Model for In-Silico Perturbation

arXiv:2605.00930v1 Announce Type: cross Abstract: In this work, we introduce CellxPert, a scalable multimodal foundation model that unifies single-cell and spatial multi-omics within a common represen

Certified Purity for Cognitive Workflow Executors: From Static Analysis to Cryptographic Attestation

arXiv:2605.01037v2 Announce Type: cross Abstract: We present a certified purity architecture that converts governance enforcement in cognitive workflow systems from a runtime convention into a structu

CLAPS: Aleatoric-Epistemic Scaling via Last-Layer Laplace for Conformal Regression

arXiv:2512.01384v4 Announce Type: replace Abstract: Conformal regression provides finite-sample marginal coverage, but it does not by itself determine how interval width should adapt across heterogene

Client-Conditional Federated Learning via Local Training Data Statistics

arXiv:2603.11307v2 Announce Type: replace Abstract: Federated learning (FL) under data heterogeneity remains challenging: existing methods either ignore client differences (FedAvg), require costly clu

Co-Generative De Novo Functional Protein Design

arXiv:2605.00948v1 Announce Type: cross Abstract: De novo functional protein design aims to generate protein sequences that realize specified biochemical functions without relying on evolutionary temp

Code World Model Preparedness Report

arXiv:2605.00932v1 Announce Type: cross Abstract: This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conduc

Complex Equation Learner: Rational Symbolic Regression with Gradient Descent in Complex Domain

arXiv:2605.03841v1 Announce Type: new Abstract: Symbolic regression aims to discover interpretable equations from data, yet modern gradient-based methods fail for operators that introduce singularitie

Complexity is not an intrinsic property of a problem. It's a property of the relationship between a problem and an observer. Once you know t…

researchfrancois-chollet--x

Complexity is fundamentally relative rather than absolute—it depends on the knowledge, perspective, and tools available to a particular observer rather than being an inherent feature of the problem it

Conditional Diffusion Sampling

arXiv:2605.04013v1 Announce Type: cross Abstract: Sampling from unnormalized multimodal distributions with limited density evaluations remains a fundamental challenge in machine learning and natural s

Conditions for well-posed color recovery in scattering media

arXiv:2605.03837v1 Announce Type: new Abstract: Recovering scene color from images captured in scattering media is a fundamental inverse problem in optical imaging. Yet the problem is intrinsically il

Context-Aware Wireless Token Communication via Joint Token Masking and Detection

arXiv:2605.02123v1 Announce Type: cross Abstract: The increasing use of token-based representations in language-driven applications has motivated wireless token communication, where tokens are treated

Controllable and Verifiable Process Data Synthesis for Process Reward Models

arXiv:2605.02395v1 Announce Type: new Abstract: Process reward models (PRMs) rely on high-quality process supervision data, yet existing construction methods often provide limited control over error l

Corruption, part N

Corruption, part N Palm Beach International Airport is now officially renamed to Donald J. Trump International Airport. The airport will be required to purchase official Trump merchandise, directly vi

researchyann-lecun--x

Corruption, part N+1

Corruption, part N+1 Someone quietly placed a massive $920 million crude oil short at 3:40 a.m. ET this morning. Just 70 minutes later, Axios reported the U.S. and Iran were close to a 14 point deal t

researchyann-lecun--x

CoVSpec: Efficient Device-Edge Co-Inference for Vision-Language Models via Speculative Decoding

arXiv:2605.02218v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devi

DARTH-PUM: A Hybrid Processing-Using-Memory Architecture

arXiv:2602.16075v2 Announce Type: replace-cross Abstract: Analog processing-using-memory (PUM; a.k.a. in-memory computing) makes use of electrical interactions inside memory arrays to perform bulk mat

Data driven approach for Outdoor Channel Prediction in 5G and Beyond

arXiv:2605.01777v1 Announce Type: cross Abstract: An evolution of Wireless Communications towards 5G and beyond provides improved user experience in terms of quality of services. Understanding and est

DeRelayL: Sustainable Decentralized Relay Learning

arXiv:2605.02935v1 Announce Type: new Abstract: In the era of big data, large-scale machine learning models have revolutionized various fields, driving significant advancements. However, large-scale m

deSEO: Physics-Aware Dataset Creation for High-Resolution Satellite Image Shadow Removal

arXiv:2605.03610v1 Announce Type: new Abstract: Shadows cast by terrain and tall structures remain a major obstacle for high-resolution satellite image analysis, degrading classification, detection, a

Diffusion Masked Pretraining for Dynamic Point Cloud

arXiv:2605.03639v1 Announce Type: new Abstract: Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing

Discover Fast Power Allocation Solution for Multi-Target Tracking via AlphaEvolve Evolution

arXiv:2605.01794v1 Announce Type: cross Abstract: Efficient radar resource allocation is a fundamental yet computationally challenging problem, as optimal solutions typically require iterative optimiz

Disease Is a Spectral Perturbation

arXiv:2605.02949v1 Announce Type: new Abstract: We propose a novel method of understanding disease transformation from a healthy baseline with biomarker-level explainability. By modeling the biomarker

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding

arXiv:2605.02290v1 Announce Type: new Abstract: Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Exi

Distributed Learning with Adversarial Gradient Perturbations

arXiv:2605.03313v1 Announce Type: new Abstract: Privacy concerns in distributed learning often lead clients to return intentionally altered gradient information. We consider the problem of learning co

Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamics

arXiv:2605.03722v1 Announce Type: new Abstract: We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited syntheti

Do LLMs have core beliefs?

arXiv:2605.03255v1 Announce Type: new Abstract: The rise of Large Language Models (LLMs) has sparked debate about whether these systems exhibit human-level cognition. In this debate, little attention

Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling

arXiv:2601.21684v2 Announce Type: replace Abstract: Test-Time Scaling enhances the reasoning capabilities of Large Language Models by allocating additional inference compute to broaden the exploration

researcharxiv-cs-cl

Double Rectified Linear Unit-based Modular Semantics for Quantitative Bipolar Argumentation Framework

arXiv:2605.02551v1 Announce Type: new Abstract: Quantitative Bipolar Argumentation Frameworks (QBAFs) provide an alternative approach to computing argument acceptability in Bipolar Argumentation Frame

Dynamic Distillation and Gradient Consistency for Robust Long-Tailed Incremental Learning

arXiv:2605.03364v1 Announce Type: new Abstract: The task of Long-tailed Class Incremental Learning (LT-CIL) addresses the sequential learning of new classes from datasets with imbalanced class distrib

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems

arXiv:2605.00955v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) equips large language models (LLMs) with external evidence by retrieving documents at inference time, but it also

Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data

arXiv:2605.03914v1 Announce Type: cross Abstract: Training data for bioacoustics is scattered across taxa, regions, and institutions. Centralizing it all is often infeasible. We show that independentl

Effect-Transparent Governance for AI Workflow Architectures: Semantic Preservation, Expressive Minimality, and Decidability Boundaries

arXiv:2605.01030v2 Announce Type: new Abstract: We present a machine-checked formalization of structurally governed AI workflow architectures and prove that effect-level governance can be imposed with

EFGPP: Exploratory framework for genotype-phenotype prediction

arXiv:2605.02954v1 Announce Type: cross Abstract: Predicting complex human traits from genetic data is challenging because different genetic, clinical, and molecular data sources often contain differe

EMOVIS: Emotion-Optimized Image Processing

arXiv:2605.03131v1 Announce Type: cross Abstract: In cinematography, visual attributes such as color grading, contrast, and brightness are manipulated to reinforce the emotional narrative of a scene.