research

Beyond Binary: Speech Representations Across the Cognitive Score Hierarchy

arXiv:2605.27189v1 Announce Type: new Abstract: This study examines the relationship between speech representations and the hierarchical structure of cognitive assessment in mild cognitive impairment.

Beyond Differences: Doubly Robust Meta-Learners for Ratio-Based Treatment Effects

DGX agent

arXiv:2605.26288v1 Announce Type: cross Abstract: When treatment effects are naturally expressed as ratios -- as in medicine, pricing, and marketing -- the ratio-based CATE au(x) = E[Y|W=1,X=x] / E[Y|

researcharxiv-cs-lg

27 May 2026

Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens

arXiv:2505.13775v4 Announce Type: replace-cross Abstract: Recent impressive results from large reasoning models have been interpreted as a triumph of Chain of Thought (CoT), and especially of the proc

Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling

arXiv:2605.27023v1 Announce Type: new Abstract: Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite a

BREAKING: Trump just got busted STEALING all the donation money from his “Board of Peace” fund to rebuild Gaza! This one REALLY takes the ca…

BREAKING: Trump just got busted STEALING all the donation money from his “Board of Peace” fund to rebuild Gaza! This one REALLY takes the cake... When Donald Trump announced he would be creating a new

researchyann-lecun--x

BUILD with Precision: Bottom-Up Inference of Linear DAGs

arXiv:2512.16111v2 Announce Type: replace Abstract: Learning the structure of directed acyclic graphs (DAGs) from observational data is a central problem in causal discovery, statistical signal proces

Can LLMs Introspect? A Reality Check

arXiv:2605.26242v1 Announce Type: new Abstract: Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue

Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models

arXiv:2605.27311v1 Announce Type: new Abstract: Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions t

Classification and detection of multiple UAVs using rational Gaussian wavelet neural networks

arXiv:2605.26310v1 Announce Type: new Abstract: The detection of unmanned aerial vehicles (UAVs) is important for the protection of civilian and military infrastructure. In this paper we propose a cos

Clozing the Gap: Exploring Why Language Model Surprisal Outperforms Cloze Surprisal

arXiv:2601.09886v2 Announce Type: replace Abstract: How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).W

Co-folding model guided by structural proteomics

arXiv:2605.26192v1 Announce Type: cross Abstract: Protein structure generative models excel at predicting single protein static structures from sequence, but routinely fail to capture the correct conf

Conceptual Steganography

arXiv:2605.26537v1 Announce Type: new Abstract: Language Models (LMs) emit Chains-of-Thought (CoTs) that drive much of their capability. However, the same sequence that carries useful reasoning can al

Confounder Detection via Treatment Intent: A New Observational Study Design

arXiv:2605.26413v1 Announce Type: cross Abstract: Understanding the effects of interventions is central to scientific progress, with randomized controlled trials (RCTs) regarded as the gold standard f

ContextGuard: Structured Self-Auditing for Context Learning in Language Models

arXiv:2605.26827v1 Announce Type: cross Abstract: Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextua

Continual Model-Based Reinforcement Learning with Hypernetworks

arXiv:2009.11997v3 Announce Type: replace-cross Abstract: Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynam

Convergence of Spectral Descent for Non-smooth Optimization

arXiv:2605.26977v1 Announce Type: new Abstract: The Muon optimizer has recently demonstrated remarkable empirical success in training large language models. However, the theoretical understanding of i

Cordyceps: Covert Control Attacks on LLMs via Data Poisoning

arXiv:2605.26595v1 Announce Type: cross Abstract: Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on

Cross-scale Aligned Supervision for Training GANs

arXiv:2605.26449v1 Announce Type: cross Abstract: Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret the resulting multi-stage synthesis as coarse-to-f

CSV-ViT: A Vision Transformer with the Variable-sized Cortical Supervertices for Detection of Alzheimer's Disease Pathologies

arXiv:2605.26514v1 Announce Type: cross Abstract: Confirming Alzheimer's disease (AD) typically relies on positron emission tomography (PET), which remains costly and invasive, motivating the use of s

Data-driven sparse identification of governing PDEs via knockoff filters and multi-criteria trade-offs

arXiv:2605.26631v1 Announce Type: cross Abstract: We propose KO-PDE-IDENT, a data-driven framework for identifying parsimonious partial differential equations (PDEs) with false discovery rate (FDR) co

Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows

arXiv:2605.26358v1 Announce Type: cross Abstract: Turbulence is ubiquitous in engineering and science, yet direct simulation is prohibitively expensive. The Reynolds-averaged Navier-Stokes (RANS) equa

DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation

arXiv:2602.18907v2 Announce Type: replace-cross Abstract: We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresse

Detached Skip-Links and R-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR

arXiv:2603.20020v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised

Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation

arXiv:2605.26382v1 Announce Type: new Abstract: Deploying high-performing 3D medical image segmenters (e.g., nnU-Net) is often limited by memory footprint and inference latency. Compression is therefo

Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run

arXiv:2605.27292v1 Announce Type: new Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bo

Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detection

arXiv:2605.26468v1 Announce Type: cross Abstract: Latent defect screening is challenged by extremely low failure rates, high-dimensional test data, and absence of labeled anomalies. We propose the fir

DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization

arXiv:2604.00648v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly adv

Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning

arXiv:2505.18603v2 Announce Type: replace Abstract: Document understanding aims to perform question answering and information extraction over document images, where the visual content is highly inform

DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion

arXiv:2601.09239v3 Announce Type: replace-cross Abstract: Speech tokenizers are a key building block of fully discrete Speech LLMs. Existing tokenizers either prioritize semantic encoding, fuse semant

Dual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detection

arXiv:2509.08289v3 Announce Type: replace Abstract: Weakly supervised object detection (WSOD) has attracted significant attention in recent years, as it does not require box-level annotations. State-o

E^3C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control

arXiv:2605.26316v1 Announce Type: cross Abstract: Controllable and physically grounded egocentric video generation is essential for embodied agents to reason about how their own and others' actions ma

EEG-FM-Audit: A Systematic Evaluation and Analysis Pipeline for EEG Foundation Models

arXiv:2605.26910v1 Announce Type: cross Abstract: Large EEG Foundation Models (FMs) have shown great potential for decoding EEG signals across diverse cognitive tasks. However, existing EEG-FM studies

Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNN

arXiv:2210.02573v5 Announce Type: replace Abstract: Learning the physical simulation on large-scale meshes with flat Graph Neural Networks (GNNs) and stacking Message Passings (MPs) is challenging due

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models

arXiv:2602.04931v2 Announce Type: replace-cross Abstract: Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlation

Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention

arXiv:2605.26355v1 Announce Type: cross Abstract: Standard transformer attention computes pairwise token similarity but treats all tokens as equally salient and all positions as equally local, regardl

Equivariant Filter for Relative Attitude and Target's Angular Velocity Estimation

arXiv:2506.06016v3 Announce Type: replace-cross Abstract: Accurate estimation of the relative attitude and angular velocity between two rigid bodies is fundamental in aerospace applications such as sp

researcharxiv-cs-ro

Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception

arXiv:2605.26136v1 Announce Type: cross Abstract: Audio deepfakes have improved rapidly recently, yet their effect on human trust in real speech remains unstudied. We present the largest listening stu

Error Analysis of Discrete Flow with Generator Matching

arXiv:2509.21906v3 Announce Type: replace-cross Abstract: Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performan

ESMFold2 is a state of the art folding model. It's crazy good. The -Fast model does better on antibody-antigen complexes than AF3 with MSAs.

ESMFold2 is described as a high-performance protein structure prediction model that demonstrates particular strength in predicting antibody-antigen complex structures, reportedly outperforming AlphaFo

researchyann-lecun--x

Evaluating the Relevance of Uncertainty Estimators for LLM Hallucination

arXiv:2605.27016v1 Announce Type: cross Abstract: Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input or training data, hindering reliable deployment. I

Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification

arXiv:2605.26663v1 Announce Type: new Abstract: Evidence absence is not evidence insufficiency, but fact verification benchmarks can make them observationally similar. The Not Enough Information (NEI)

Explainable Comparison of Feature-Based and Deep Learning Models for TROPOMI Methane Plume Screening

arXiv:2605.27236v1 Announce Type: new Abstract: Continuous and global detection of large methane emissions is a crucial step for global warming mitigation. Satellite observations, such as from S5P/TRO

Exploring the robustness of TractOracle methods in RL-based tractography

arXiv:2507.11486v2 Announce Type: replace Abstract: Tractography algorithms leverage diffusion MRI to reconstruct the fibrous architecture of the brain's white matter. Among machine learning approache

ExTax: Explainable Disinformation Detection via Persuasion, Emotion, and Narrative Role Taxonomies

arXiv:2605.27045v1 Announce Type: new Abstract: The democratization of LLMs has accelerated the generation and circulation of highly fluent disinformation, making traditional syntax-semantic verificat

Extending Human Intelligence Through AI

researchmicrosoft-research

Understanding AI as an extension of human intelligence—not a replacement for it—offers a more grounded path for building trustworthy AI systems. The post Extending Human Intelligence Through AI appear

First of all, all of this is open sourced. Even the binder design protocol [coming soon], which has been rigorously experimentally validated…

First of all, all of this is open sourced. Even the binder design protocol [coming soon], which has been rigorously experimentally validated. Paper: https://biohub.ai/papers/esm_protein.pdf 🤗: https:/

researchyann-lecun--x

FluxNet: Learning Capacity-Constrained Local Transport Operators for Conservative and Bounded PDE Surrogates

arXiv:2602.01941v2 Announce Type: replace-cross Abstract: Autoregressive learning of time-stepping operators provides an effective approach to data-driven partial differential equation (PDE) simulatio

For over a decade, we’ve accepted that end-to-end backprop is the only way to train deep networks. But holding the entire network in memory …

For over a decade, we’ve accepted that end-to-end backprop is the only way to train deep networks. But holding the entire network in memory all at once is why AI training is hitting a resource wall. W

researchdavid-ha--x