Search: “research”

Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models

arXiv:2607.21636v1 Announce Type: new Abstract: Synthetic tabular data is valued for preserving not only each column's marginal distribution but the dependencies between columns -- structure that carr

Research

MemNMF: Memory-Augmented NMF on LPC Spectra for Anomalous Sound Detection

DGX agent

arXiv:2607.22086v1 Announce Type: cross Abstract: Autoencoder-based anomalous sound detection is attractive for machine condition monitoring because it can be trained using only normal recordings and

researcharxiv-cs-lg

27 Jul 2026

MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond

arXiv:2607.22100v1 Announce Type: new Abstract: Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into t

MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion

arXiv:2607.21634v1 Announce Type: new Abstract: Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence r

Moving Beyond Diversity: Visual Token Pruning as Subspace Reconstruction for Efficient VLMs

arXiv:2606.18681v2 Announce Type: replace Abstract: Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual token

Multi-Horizon Consistency as Geometry: When Latent Dynamics Contract, and When They Do Not

arXiv:2607.21645v1 Announce Type: new Abstract: Multi-horizon latent consistency is a common training knob in video predictors and world models, but practitioners rarely know what it does to transitio

Natural Invariant Measures for Chaotic Game Dynamics: Finding Order in Chaos

arXiv:2607.21805v1 Announce Type: cross Abstract: We study the long-term behavior of the Multiplicative Weights Update (MWU) algorithm in game settings where learning dynamics frequently fail to conve

Numerical Fragility in Transformers: A Layer-wise Theory for Risk Estimation and Selective Stabilization

arXiv:2510.21770v2 Announce Type: replace Abstract: Low-precision execution can induce substantial forward discrepancies in Transformers even for fixed weights and input, yet these discrepancies are u

On Improving Faithfulness of Podcasts from Documents

arXiv:2607.21961v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate long-form conversational content such as podcasts from textual sources. While these syste

On the Convergence of Stochastic Low-Rank Adaptation

arXiv:2607.21975v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) optimizes J(B,A)=mathcal L(W_base+sBA) over two adapters B in R^{m imes r} and A in R^{r imes n} that form a low-rank update

On the Depth Scalability of Logic Gate Networks

arXiv:2607.21633v1 Announce Type: new Abstract: Logic Gate Networks (LGNs) implement computation through compositions of Boolean operations, yet unlike classical Boolean circuits, existing LGNs do not

OpenAI called the Hugging Face attack unprecedented. But we’ve been here before.

This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Reading OpenAI’s account last week of how some of its models b

researchmit-tech-review

Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On

arXiv:2607.21694v1 Announce Type: new Abstract: We present Oxygen-TryOn, a unified foundation model for any-item virtual try-on. Rather than repurposing a general-purpose image editor, Oxygen-TryOn is

Phylogenetic signal in marine mammal and bird vocalizations captured by audio foundation models: the limited benefit of domain-specific pretraining

arXiv:2607.22458v1 Announce Type: new Abstract: Do learned audio embeddings encode structure that nobody told them to encode? We probe four large pretrained audio models (AST, CLAP, BEATs-bio and Bird

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection

arXiv:2607.21776v1 Announce Type: cross Abstract: Talking-face (TF) deepfake generation synthesizes photore- alistic facial video from a static source image and an au- dio signal, producing forgeries

Plug, Play, and Comply: A Modular Framework for Online Variable Impedance with Arbitrarily Oriented Compliance Axes

arXiv:2607.22483v1 Announce Type: new Abstract: The paper proposes a robot-agnostic compliant-control framework that extends the ROS control ecosystem with standardized joint and Cartesian command int

researcharxiv-cs-ro

Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases

arXiv:2602.09572v3 Announce Type: replace-cross Abstract: The purpose of predictive modeling on relational data is to predict future or missing values in a relational database, for example, future pur

Prior laundering: learned priors with inherited, undetectable overconfidence

arXiv:2607.21721v1 Announce Type: cross Abstract: Learned generative priors are increasingly used for ill-posed Bayesian inverse problems, their posterior uncertainty treated as earned from data. But

Probing Speaker Identity Sensitivity in Audio Deepfake Detectors

arXiv:2607.21820v1 Announce Type: cross Abstract: Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same d

Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning

arXiv:2511.02130v2 Announce Type: replace-cross Abstract: We propose Re-FORC, an adaptive reward prediction method that, given a query, enables prediction of the expected future rewards as a function

Really interesting concept -- instead of optimizing against static benchmarks or internally generated reward models, agents are evaluated th…

researchfrancois-chollet--x

Really interesting concept -- instead of optimizing against static benchmarks or internally generated reward models, agents are evaluated through real economic interactions. Using an external market a

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

arXiv:2607.22098v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers. While these traces may contain useful signals for halluci

Reflector: Arrangement-Aware Harmonic Retrieval for Sample-Based Composition

arXiv:2607.22413v1 Announce Type: cross Abstract: Sample retrieval tools can help composers find harmonically compatible material, but querying from a fixed reference sample becomes less informative a

Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling

arXiv:2607.21797v1 Announce Type: cross Abstract: Previous work has shown that the simple dataflow primitives of the Lustre language allow the natural, semantically unambiguous, and compact representa

Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement

arXiv:2607.21885v1 Announce Type: new Abstract: Coarsening-based training for graph neural networks (GNNs), i.e. training on coarsened graphs rather than the original large ones, has become a promisin

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification in the Foundation-Model Era

arXiv:2607.22068v1 Announce Type: new Abstract: Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combinin

Robot Learning to Communicate through Projected Visual Abstractions

arXiv:2607.22434v1 Announce Type: new Abstract: Humans routinely communicate through abstractions of their bodies, including shadows, silhouettes, and reflections. Yet robots remain largely confined t

researcharxiv-cs-ro

Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

arXiv:2607.21673v1 Announce Type: cross Abstract: Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynam

Shallower ReLU Network Representations via Exact Linear Algebra

arXiv:2607.21651v1 Announce Type: new Abstract: We prove that the maximum of n real numbers is exactly representable by a ReLU network with two hidden layers for every nle 10. The constructions are ob

SiPhy: Single-Image Physical Property Reasoning

arXiv:2607.22355v1 Announce Type: new Abstract: Inferring physical properties such as mass, stiffness, and elasticity from a single image is essential for simulation and embodied AI, yet most existing

SLIP: Segmentation with Low-latency Interactive Prompting for 3D Medical Images

arXiv:2607.22332v1 Announce Type: new Abstract: Interactive deep image segmentation enables efficient medical image annotation by iteratively refining predictions from user prompts, such as positive a

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

arXiv:2607.22034v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor li

Smart predict-then-robustly-optimize

arXiv:2607.21773v1 Announce Type: new Abstract: In this paper, we propose and study a robust variant of the smart predict-then-optimize approach that accounts for prediction shifts due to disturbance

StARS: Socially Appropriate Robot Actions via a Recommender System-Driven Approach

arXiv:2607.21802v1 Announce Type: new Abstract: Social appropriateness in human-robot interaction (HRI) is not universal: different people can judge the same robot action differently in the same situa

researcharxiv-cs-ro

Susceptible Reservoir Architectures for Regime-Conditional Volatility Forecasting

arXiv:2607.22491v1 Announce Type: new Abstract: Volatility forecasting is dominated by persistence and measurement noise, leaving limited residual structure for nonlinear models to exploit. We introdu

TDiR: Transformer based Diffusion for Image Restoration Tasks

arXiv:2506.20302v2 Announce Type: replace Abstract: Images captured in challenging environments often experience various types of degradation, such as noise, color cast, blur, and light scattering. Th

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

arXiv:2607.21971v1 Announce Type: cross Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We h

The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data

arXiv:2205.07739v4 Announce Type: replace-cross Abstract: Self-training (ST) is a simple yet effective semi-supervised learning method. However, why and how ST improves generalization performance by u

TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complex

arXiv:2607.22143v1 Announce Type: new Abstract: Molecular glue degraders have emerged as a promising strategy for targeted protein degradation by inducing ternary complex formation between an E3 ubiqu

Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability

arXiv:2607.22428v1 Announce Type: cross Abstract: Explainable AI (XAI) in creative practice can be less about technocentric explanation and more about enabling artists to inspect modify and debug mode

Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models

arXiv:2607.22397v1 Announce Type: cross Abstract: Frozen EEG encoders proliferate; per-model fine-tune defaults do not scale. We present Nimbus Personalizer: one contract encode to Bayesian head to Br

Vector-Valued Reproducing Kernel Banach Spaces for Neural Networks and Operators

arXiv:2509.26371v3 Announce Type: replace-cross Abstract: Recently, there has been growing interest in characterizing the function spaces underlying neural networks. While shallow and deep scalar-valu

Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation

arXiv:2510.04602v4 Announce Type: replace-cross Abstract: Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient spa

What Happens to Accuracy When Photo Lineups Contain Non-Mated Rank-One Images From Large Galleries?

arXiv:2607.21792v1 Announce Type: new Abstract: One-to-many facial identification is commonly used to match a probe image from surveillance video against a gallery of driver's licenses and/or booking

Multi-Tenant SaaS: Which Architecture Would You Choose? [D]

researchr-machinelearning

NOTE -> I expect answer from people who actually have experience and strong understanding of these. please give something beneficial. I'm building a SaaS platform in Sri Lanka that handles documents a

26 Jul 2026

Recent discussions about open-sourcing make me feel that I should go back and revisit these important open-source works in representation le…

Recent discussions about open-sourcing make me feel that I should go back and revisit these important open-source works in representation learning that pushed the field forward and eventually made vis

researchyann-lecun--x

26 Jul 2026

The Top AI Papers of the Week (July 20 - July 26): - GAMUT - PRO-LONG - Harness Handbook - From Memory to Skills - Progressive Disclosure - …

The Top AI Papers of the Week (July 20 - July 26): - GAMUT - PRO-LONG - Harness Handbook - From Memory to Skills - Progressive Disclosure - Global Workspace in LLMs - Structured Output Collapses Diver

researchdair-ai--x

26 Jul 2026

3D-Aware VLMs with Implicit and Explicit Geometries