Search: “research”

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

arXiv:2603.12529v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables th

Research

Text-Dependent Speaker Verification (TdSV) Challenge 2024: Team Naive System Report

DGX agent

arXiv:2605.14896v1 Announce Type: cross Abstract: This paper presents a system for the 2024 Text-Dependent Speaker Verification (TdSV) Challenge. The system achieved a Minimum Detection Cost Function

researcharxiv-cs-lg

15 May 2026

The Download: China’s AI drama factory and the WHO’s missing health targets

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. How Chinese short dramas became AI content machines China’s sh

researchmit-tech-review

The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale

arXiv:2605.15011v1 Announce Type: new Abstract: Scientific contributions rarely develop in isolation, but instead build upon prior discoveries. We formulate the task of automated technological roadmap

The Velocity Deficit: Initial Energy Injection for Flow Matching

arXiv:2605.14819v1 Announce Type: new Abstract: While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity

The world is on track to miss its health targets

Every year the World Health Organization publishes a global health statistics report. It features the numbers behind world health trends and, importantly, assesses whether we’re on track to reach ambi

researchmit-tech-review

There is a case to be made that the future of Mathematics is very bright. In my mind, proofs have always been a tool to achieve a goal. The …

There is a case to be made that the future of Mathematics is very bright. In my mind, proofs have always been a tool to achieve a goal. The goal was and still is to understand, and reading/writing pro

researchyann-lecun--x

Tokenizing Single-Channel EEG with Time-Frequency Motif Learning

arXiv:2502.16060v5 Announce Type: replace-cross Abstract: Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokeni

TopoPrimer: The Missing Topological Context in Forecasting Models

arXiv:2605.15035v1 Announce Type: new Abstract: We introduce TopoPrimer, a framework that makes the global topological structure of the series population an explicit input to any forecasting model. To

Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach

arXiv:2605.14601v1 Announce Type: new Abstract: Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remai

Towards Label-Free Single-Cell Phenotyping Using Multi-Task Learning

arXiv:2605.14717v1 Announce Type: cross Abstract: Label-free single-cell imaging offers a scalable, non-invasive alternative to fluorescence-based cytometry, yet inferring molecular phenotypes directl

TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning

arXiv:2510.07118v3 Announce Type: replace Abstract: Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However

Uncertainty Quantification for Large Language Diffusion Models

arXiv:2605.14570v1 Announce Type: new Abstract: Large Language Diffusion Models (LLDMs) are emerging as an alternative to autoregressive models, offering faster inference through higher parallelism. S

Uncovering Trajectory and Topological Signatures in Multimodal Pediatric Sleep Embeddings

arXiv:2605.14156v1 Announce Type: new Abstract: While generative models have shown promise in pediatric sleep analysis, the latent structure of their multimodal embeddings remains poorly understood. T

Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning

arXiv:2605.14785v1 Announce Type: cross Abstract: Neural networks suffer from catastrophic forgetting in class-incremental learning (CIL) settings. Rehearsalnicode{x2013}replaying a subset of past sam

Unsupervised simulation of incompressible flows with physics- and equality- constrained artificial neural networks

arXiv:2511.18820v2 Announce Type: replace-cross Abstract: Physics-informed neural networks (PINNs) have shown promise for solving partial differential equations, yet their success in simulating incomp

VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation

arXiv:2603.18943v2 Announce Type: replace Abstract: This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-indep

VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction

arXiv:2605.15186v1 Announce Type: cross Abstract: High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environ

Video-Zero: Self-Evolution Video Understanding

arXiv:2605.14733v1 Announce Type: new Abstract: Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to

Vision-Based Water Level and Flow Estimation

arXiv:2605.14645v1 Announce Type: cross Abstract: With the rapid evolution of computer vision, vision-based methodologies for water level and river surface velocity estimation have reached significant

VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting

arXiv:2605.14597v1 Announce Type: new Abstract: Precipitation nowcasting is a vital spatio-temporal prediction task for meteorological applications but faces challenges due to the chaotic property of

Wahkon: A Statistically Principled Deep RKHS Superposition Network

arXiv:2605.14041v1 Announce Type: cross Abstract: Deep learning excels at prediction but often lacks finite-sample guarantees and calibrated uncertainty; RKHS (Reproducing Kernel Hilbert Space)-based

WarmPrior: Straightening Flow-Matching Policies with Temporal Priors

arXiv:2605.13959v1 Announce Type: cross Abstract: Generative policies based on diffusion and flow matching have become a dominant paradigm for visuomotor robotic control. We show that replacing the st

Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games

arXiv:2605.14283v1 Announce Type: cross Abstract: Watermarking techniques for large language models (LLMs), which encode hidden information in the output so its source can be verified, have gained sig

Wavelet-Based Observables for Koopman Analysis: An Extended Dynamic Mode Decomposition Framework

arXiv:2605.14224v1 Announce Type: cross Abstract: We present an in-depth analysis of the Koopman semigroup via wavelet transform. Towards this goal, we start by introducing the wavelet-based observabl

When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition

arXiv:2605.14449v1 Announce Type: cross Abstract: Hallucination detection in large language models (LLMs) requires balancing accu racy, efficiency, and robustness to distribution shift. Black-box cons

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability

arXiv:2605.15183v1 Announce Type: new Abstract: Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite.

When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering

arXiv:2605.14115v1 Announce Type: new Abstract: Biomedical retrieval-augmented large language models (LLMs) often face evidence that is incomplete, misleading, or internally contradictory, yet evaluat

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement

arXiv:2605.14368v1 Announce Type: cross Abstract: Continuous diffusion language models lag behind autoregressive transformers, partly because diffusion is applied in spaces poorly suited to language d

Why Retrieval-Augmented Generation Fails: A Graph Perspective

arXiv:2605.14192v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in ret

WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition

arXiv:2603.09921v3 Announce Type: replace Abstract: Open-domain visual entity recognition (VER) seeks to associate images with entities in encyclopedic knowledge bases such as Wikipedia. Recent genera

Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm

arXiv:2605.13979v1 Announce Type: cross Abstract: Quantum machine learning (QML) aims to accelerate machine learning tasks by exploiting quantum computation. Previous work studied a QML algorithm for

XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles

arXiv:2605.13922v1 Announce Type: cross Abstract: During the last few years, the term Mechanistic Interpretability, a specific area, under the umbrella of explainable artificial intelligence (XAI), ha

Yann LeCun says LLMs are strongest in domains where language itself is the substrate of reasoning, like math and code They can solve problem…

Yann LeCun says LLMs are strongest in domains where language itself is the substrate of reasoning, like math and code They can solve problems, prove theorems, and write programs — but they are not cre

researchyann-lecun--x

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers

arXiv:2605.14893v1 Announce Type: cross Abstract: Contrastively pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors. Yet, their shared latent spaces are prone to structural

3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling

arXiv:2505.21238v3 Announce Type: replace Abstract: Novel view synthesis for underwater scene reconstruction presents unique challenges due to complex light-media interactions. Optical scattering and

A Constraint Programming Approach for n-Day Lookahead Playoff Clinching

arXiv:2605.13142v1 Announce Type: new Abstract: In professional sports, a team has clinched the playoffs if they are guaranteed a postseason spot, regardless of the outcomes of any remaining games. As

A Faster Generalized Two-Stage Approximate Top-K

arXiv:2506.04165v3 Announce Type: replace Abstract: We consider the Top-K selection problem, which aims to identify the largest K elements in an array. Top-K selection arises in many machine learning

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning

arXiv:2605.13687v1 Announce Type: cross Abstract: We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context

A Horn extension of DL-Lite with NL data complexity

arXiv:2605.13367v1 Announce Type: cross Abstract: The literature on ontology-mediated query answering (OMQA) has been shaped by two key results: first-order rewritability for DL-Lite, and PTime-hardne

A Markov Categorical Framework for Language Modeling

arXiv:2507.19247v5 Announce Type: replace-cross Abstract: Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes

A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data

arXiv:2605.12706v1 Announce Type: new Abstract: RSNet is an open-source R package that provides a resampling-based framework for robust and interpretable network inference, designed to address the lim

A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention

arXiv:2605.12697v1 Announce Type: cross Abstract: Length-dependent logit rescaling is widely used to stabilize long-context self-attention, but existing analyses and methods suggest conflicting invers

Accelerating Particle-based Energetic Variational Inference

arXiv:2504.03158v2 Announce Type: replace-cross Abstract: In this work, we propose a new particle-based variational inference (ParVI) method for accelerating the Energetic Variational Inference with I

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

arXiv:2605.13301v1 Announce Type: new Abstract: Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving, with several systems now reachi

Amortized Guidance for Image Inpainting with Pretrained Diffusion Models

arXiv:2605.13010v1 Announce Type: cross Abstract: We study image inpainting with generative diffusion models. Existing methods typically either train dedicated task-specific models, or adapt a pretrai

Amortized Neural Clustering of Time Series based on Statistical Features

arXiv:2605.13128v1 Announce Type: cross Abstract: This paper introduces an algorithm-agnostic approach to feature-based time series clustering via amortized neural inference. By training neural networ

Anatomy-Slot: Unsupervised Anatomical Factorization for Homologous Bilateral Reasoning in Retinal Diagnosis

arXiv:2605.12929v1 Announce Type: cross Abstract: Retinal diagnosis is inherently bilateral: clinicians compare homologous structures across eyes (e.g., optic disc asymmetry), yet most deep models ope