Search: “papers”

SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation

arXiv:2605.30894v1 Announce Type: new Abstract: The shortage of legally compliant data for face recognition training has sparked growing interest in using synthetic data as an alternative. While recen

researcharxiv-cs-cv

Safety

Supervised Learning as Lossy Compression: Characterizing Generalization and Sample Complexity via Finite Blocklength Analysis

DGX agent

arXiv:2602.04107v2 Announce Type: replace Abstract: This paper presents a novel information-theoretic perspective on generalization in machine learning by framing the learning problem within the conte

safetyarxiv-cs-lg

1 Jun 2026

The Information Geometry of Softmax: Probing and Steering

arXiv:2602.15293v2 Announce Type: replace-cross Abstract: This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The

Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows

model-releasesarxiv-cs-cl

arXiv:2605.31452v1 Announce Type: new Abstract: Building on our previous work, this paper develops practical, low-barrier methods for freelance translators and smaller language service providers to ev

Two Degree-of-Freedom Vibratory Transport in a Grasp

arXiv:2605.30780v1 Announce Type: new Abstract: In this paper, we use asymmetric vibrations to demonstrate two degree-of-freedom (DoF) in-hand manipulation of grasped parts. The asymmetric vibrations

researcharxiv-cs-ro

A Novel Tensor Product-Based Neural Network for Solving Partial Differential Equations

model-releasesarxiv-cs-lg

arXiv:2605.29688v1 Announce Type: new Abstract: This paper presents the Tensor Product Network (TPNet), a novel neural architecture for efficient and accurate function approximation and PDE solving. T

A Study on Question-Answer Dataset for LLM Safety Evaluation with a Focus on Illegal Activities

arXiv:2605.29340v1 Announce Type: new Abstract: In this paper, we discuss question-answer dataset for LLM safety evaluation, with a focus on illegal activities. Specifically, on the basis of manual an

safetyarxiv-cs-cl

Achieving Linear Speedup for Composite Federated Learning

arXiv:2602.03357v2 Announce Type: replace Abstract: This paper proposes FedNMap, a normal map-based method for composite federated learning, where the objective consists of a smooth loss and a possibl

Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation

model-releasesarxiv-cs-cl

arXiv:2605.29992v1 Announce Type: new Abstract: Sentence embeddings are a foundational component for semantic search, clustering, classification, and retrieval-augmented generation. This paper present

BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders

arXiv:2605.30162v1 Announce Type: new Abstract: Biosecurity evaluations of language models typically ask whether models produce hazardous output. This paper asks a complementary question: when a model

COMPOSE: Composing Future Theorems from Citations and Formal Structure

model-releasesarxiv-cs-cl

arXiv:2605.30333v1 Announce Type: new Abstract: A plausible future mathematical claim must satisfy two constraints: it should follow the direction of prior work and respect the formal dependencies tha

Industry

Databricks at SIGMOD 2026

Databricks announced its participation or contributions at SIGMOD 2026, a premier international conference on database systems and management. The blog post likely covers Databricks' research papers,

industrydatabricks

DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation

arXiv:2605.29522v1 Announce Type: new Abstract: As scientific literature grows rapidly, automated survey generation has become a key capability for AI scientists and human researchers. However, existi

Diffusion differentiable resampling

model-releasesarxiv-cs-lg

arXiv:2512.10401v3 Announce Type: replace-cross Abstract: This paper is concerned with differentiable resampling in the context of sequential Monte Carlo (e.g., particle filtering). Drawing on reparam

Gesture-Aware Indoor THz ISAC Systems for Adaptive Resource Allocation

arXiv:2605.29913v1 Announce Type: cross Abstract: This paper investigates a multi-user indoor integrated sensing and communication (ISAC) system operating in the terahertz (THz) band, designed for ada

Agents

Human-in-the-Loop Swarms: A Bionic Swarm Approach to Real-World Soil Mapping

arXiv:2605.29091v1 Announce Type: new Abstract: Swarm and field robotics face significant barriers to real-world validation due to the high cost and development time to deploy hardware. This paper int

agentsarxiv-cs-ro

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

arXiv:2605.29245v1 Announce Type: cross Abstract: This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-conte

researcharxiv-cs-cl

It`s All About Speed: AI`s Impact on Workflow in Music Production

arXiv:2605.29931v1 Announce Type: new Abstract: In this paper, we present the results of an ethnographic study into the impact of AI and automated tools on music production workflow. Focusing specific

applicationsarxiv-cs-ai

Learning A Simulation-based Visual Policy for Real-world Peg In Unseen Holes

arXiv:2205.04297v2 Announce Type: replace-cross Abstract: This paper proposes a learning-based visual peg-in-hole that enables training with several shapes in simulation, and adapting to arbitrary uns

Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms

arXiv:2401.08197v3 Announce Type: replace Abstract: This paper considers the problem of completing a rating matrix based on sub-sampled matrix entries as well as observed social graphs and hypergraphs

MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC-Regularized Optimization

arXiv:2605.29635v1 Announce Type: cross Abstract: In this paper, we study a structured class of nonconvex constrained stochastic problems with difference-of-convex (DC) regularization, where the feasi

Multifingered force-aware control for humanoid robots

arXiv:2603.08142v2 Announce Type: replace Abstract: In this paper, we address force-aware control and force distribution in robotic platforms with multi-fingered hands. Given a target goal and force e

researcharxiv-cs-ro

Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation

arXiv:2605.29407v1 Announce Type: new Abstract: This paper presents a phase-conditioned, force-aware framework for robust deformable object manipulation. Standard imitation learning policies such as A

safetyarxiv-cs-ro

Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning

arXiv:2506.08354v2 Announce Type: replace-cross Abstract: This position paper argues that text embedding research should move beyond surface meaning and embrace implicit semantics as a central modelin

applicationsarxiv-cs-ai

ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure

arXiv:2605.30284v1 Announce Type: new Abstract: Scientific discovery is an inherently creative and uncertain process, requiring reasoning beyond the recall of known knowledge. While many benchmarks ha

Real-Time Retargeting Using Controllability Boundary for Chandrayaan-3 Lunar Landing

arXiv:2605.29412v1 Announce Type: cross Abstract: This paper presents the real-time retargeting guidance policy developed for the Chandrayaan-3 lunar landing mission. The baseline guidance generates a

safetyarxiv-cs-lg

SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?

model-releasesarxiv-cs-lg

arXiv:2605.30329v1 Announce Type: new Abstract: Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. How

The Hamilton-Jacobi Theory of Deep Learning

arXiv:2605.28983v1 Announce Type: cross Abstract: In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selec

Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI Exploration

arXiv:2605.29096v1 Announce Type: new Abstract: This paper examines records retrieved from the ClinicalTrials.gov registry to characterize temporal trends in AI terminology and the geographical distri

Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting

arXiv:2506.12444v2 Announce Type: replace-cross Abstract: In this paper, we propose Adjusted Shuffling SARAH, a novel algorithm that integrates shuffling strategies into the recursive SARAH framework

Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective

arXiv:2605.27962v1 Announce Type: new Abstract: This paper describes our approach for the 8th UG2+ Workshop (CVPR 2026) Track~2, which targets semantic segmentation of outdoor scenes degraded by five

researcharxiv-cs-cv

Eliot: Interactively nderline{E}xploring Fast-Changing Scientific nderline{Li}terature Trends with nderline{O}nline Danderline{t}a and Learning

arXiv:2605.27610v1 Announce Type: cross Abstract: The rapid growth of scientific publishing has made it increasingly difficult to track how fast-moving areas evolve. Search engines and LLM-based assis

Evaluating the Generation Capabilities of Large Chinese Language Models

arXiv:2308.04823v5 Announce Type: replace Abstract: This paper unveils CG-Eval, the first-ever comprehensive and automated evaluation framework designed for assessing the generative capabilities of la

researcharxiv-cs-cl

Tutorials

Formula-One Prompting: A Composable Equation-First Prefix for Applied Mathematics

arXiv:2601.19302v3 Announce Type: replace Abstract: This paper introduces Formula Prompting (FP) and Formula-One Prompting (F-1), two single-call methods that elicit governing equations before solving

tutorialsarxiv-cs-cl

Agents

From Instructor to Collaborator: What a 90-Participant Study Reveals about Human-Agent Collaboration in a Mobile Serious Game

arXiv:2605.27384v1 Announce Type: cross Abstract: This position paper reflects empirical data collected during my PhD from a large-scale within-subjects study (N = 90). The study compared a highly hum

agentsarxiv-cs-ai

Implicit Regularization in Perturbed Deep Matrix Factorization: Spectral Conditions and Stability

arXiv:2605.28613v1 Announce Type: cross Abstract: This paper studies the stability of low-rank implicit regularization in perturbed deep matrix factorization, where the target matrix is corrupted by a

Inpainting-Style Conditional Diffusion for Multivariable Time Series Forecasting

model-releasesarxiv-cs-cv

arXiv:2605.28324v1 Announce Type: new Abstract: In this paper, we propose a novel conditional diffusion-based framework for multivariable time-series solar power forecasting. The proposed method refor

Learning after COVID-19 and the ICT career aspirations: Are students entering the AI era with weaker skills?

arXiv:2605.27391v1 Announce Type: cross Abstract: This paper examines whether students are entering the generative AI era with sufficiently strong educational foundations, focusing on the relationship

applicationsarxiv-cs-ai

Learning to target with network interference

arXiv:2605.27794v1 Announce Type: cross Abstract: This paper studies adaptive targeting under network interference in a bandit setting, where treatments applied to one individual may affect others thr

applicationsarxiv-cs-lg

Magnet-Based Soft Robotic Skin Using a 3D-Printed Multi-Lattice Structure and CNN-Based Tactile Super-Resolution

arXiv:2605.28352v1 Announce Type: new Abstract: This paper presents a magnet-based robotic skin that integrates a multilayer soft lattice with distributed Hall-effect sensor arrays and a tactile super

researcharxiv-cs-ro

Opus 4.8 formulated the hypotheses in advance, conducting data cleaning, did research on references, conducted analyses, did robustness chec…

model-releasesethan-mollick--x

Opus 4.8 formulated the hypotheses in advance, conducting data cleaning, did research on references, conducted analyses, did robustness checks, and put out the whole paper in LaTEX style. GPT-5.5 foun

Position: Retire the 'Positive Backdoor' Label -- Secret Alignment Requires Strict and Systematic Evaluation

arXiv:2605.28597v1 Announce Type: cross Abstract: This position paper argues that the AI/ML community should stop overclaiming and retire the label 'positive backdoor,' and instead treat trigger-activ

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

arXiv:2605.28553v1 Announce Type: new Abstract: In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on

Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities

arXiv:2410.04096v2 Announce Type: replace-cross Abstract: In this paper, we propose to use Sinc interpolation in the context of Kolmogorov-Arnold Networks, neural networks with learnable activation fu

Snowveil: A Framework for Decentralised Preference Discovery

arXiv:2512.18444v2 Announce Type: replace-cross Abstract: Aggregating subjective preferences in social choice traditionally assumes a trusted central authority. In contrast, this paper formalises Dece

Agents

The Optimal Sample Complexity of Linear Contracts

arXiv:2601.01496v2 Announce Type: replace-cross Abstract: In this paper, we settle the problem of learning optimal linear contracts from data in the offline setting, where agent types are drawn from a

agentsarxiv-cs-ai

2-ASP(Q) programs with weak constraints: Complexity and efficient implementation

arXiv:2605.27338v1 Announce Type: new Abstract: ASP(Q) extends Answer Set Programming (ASP) with Quantifiers over answer sets. In this paper we focus on the class of ASP(Q) programs with two quantifie

27 May 2026

AI evaluation may bias perceptions: The importance of context in interpreting academic writing

arXiv:2605.26662v1 Announce Type: cross Abstract: This paper examines how estimates of AI use in scientific writing can be biased when evaluation methods ignore contextual differences across countries