research

Separating quantum circuits from classical LLMs

arXiv:2608.03962v1 Announce Type: cross Abstract: Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generatio

Shaping Wind-Tunnel Airflow for Unmanned Aerial Vehicles using Online Learning

DGX agent

arXiv:2608.03378v1 Announce Type: cross Abstract: The development and testing of advanced aerial robots require experiments in controlled environments with tailored airflow profiles. This paper presen

researcharxiv-cs-ai

5 Aug 2026

ShielDroid: A Hybrid Approach Integrating Machine and Deep Learning for Android Malware Detection

arXiv:2608.03250v1 Announce Type: cross Abstract: The rapid advancement of modern technology has led to a significant increase in the use of smart devices, such as smartphones and tablets, resulting i

Shooting for Contact: Contact-Implicit Multiple Shooting for Dynamic Motion Retargeting

arXiv:2608.03116v1 Announce Type: new Abstract: Motion retargeting approaches often prioritize kinematic similarity over whole-body dynamics, contact consistency, and actuation limits, yielding refere

researcharxiv-cs-ro

Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking

arXiv:2608.03469v1 Announce Type: cross Abstract: We study score learning for reflected diffusion on bounded domains. Reflection keeps trajectories feasible but does not ensure that the learned score

Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations

arXiv:2608.03970v1 Announce Type: new Abstract: Human input reaches language models by typing or speaking, and each channel leaves a distinct signature: orthographic noise for keyboards; for voice, di

Simulation-free and finite-time diffusion model

arXiv:2608.03117v1 Announce Type: new Abstract: The performance of generative diffusion models is determined by the choice of the reference diffusion process connecting the empirical and prior distrib

SkillTrace: Traversing a Query-Skill Graph for Composable LLM Agents

arXiv:2608.02356v2 Announce Type: replace Abstract: Large language model agents increasingly solve complex tasks by composing reusable skills from a library. To address this, the key challenge is not

SLAMFormer-infty: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing

arXiv:2608.03429v1 Announce Type: new Abstract: We introduce the Infinite SLAM Transformer (SLAMFormer-infty), the first geometric transformer capable of supporting both long-range frontend and backen

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels

arXiv:2608.02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researche

Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages

arXiv:2508.05149v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art perf

SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding

arXiv:2608.03165v1 Announce Type: cross Abstract: Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortio

SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense

arXiv:2608.03395v1 Announce Type: new Abstract: Deepfake technologies pose increasing threats to facial privacy and identity security, motivating proactive defenses that protect facial images before m

Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing

arXiv:2608.03023v1 Announce Type: cross Abstract: Remote sensing semantic segmentation is hindered by costly pixel-level annotations, motivating training-free open-vocabulary methods. Recently, the re

State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking

arXiv:2608.03425v1 Announce Type: new Abstract: Transformer-based architectures have dominated sequence modeling, largely due to the expressive power of attention mechanisms. However, for a class of d

States Hidden in Hidden States: Implicit Discrete State Representations Emerge in LLMs' Hidden States

arXiv:2407.11421v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit emergent abilities that may reveal aspects of their internal mechanisms. We study one such capability: directly

Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework

arXiv:2608.03001v1 Announce Type: cross Abstract: Unit excitation (UE) is a common assumption in stochastic saddle avoidance: the stochastic error must have a uniformly positive component along every

Strong bounds for large-scale Minimum Sum-of-Squares Clustering

arXiv:2502.08397v3 Announce Type: replace-cross Abstract: Clustering is a fundamental technique in data analysis and machine learning, used to group similar data points together. Among various cluster

StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement

arXiv:2603.09234v2 Announce Type: cross Abstract: Achieving high perceptual quality without hallucination remains a challenge in generative speech enhancement (SE). A representative approach, PASE, is

Subjective Risk Decomposition: A New View for Uncertainty Quantification

arXiv:2607.15196v2 Announce Type: replace-cross Abstract: We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but

Suffix-Constrained Greedy Search Algorithms for Causal Language Models

arXiv:2603.01243v2 Announce Type: replace Abstract: Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. Beside free-form generati

Surface Keypoint Representation for Multi-Object and Articulated Human-Object Interaction Generation

arXiv:2608.03158v1 Announce Type: new Abstract: Daily activities require humans to coordinate whole-body motion with the motion of surrounding objects. Despite recent progress in human-object interact

Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study

arXiv:2608.03172v1 Announce Type: new Abstract: Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- 'Anna S.' becomes 'Maria S.',

TabletCraft: Bridging a 4,000-Year Cultural Gap with Bidirectional Akkadian NMT and Cuneiform Rendering

arXiv:2608.02609v1 Announce Type: new Abstract: Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world's oldest writing system, le

TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models

arXiv:2608.03057v1 Announce Type: new Abstract: Static quantization assigns one weight precision to every denoising step. To preserve quality, that precision must accommodate the most quantization-sen

Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores

arXiv:2608.02985v1 Announce Type: cross Abstract: The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformat

Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility

arXiv:2608.04001v1 Announce Type: cross Abstract: Large language models can solve substantially harder reasoning problems with more inference-time compute. The term 'test-time scaling,' however, now c

The bottleneck for AI progress was never compute, it was always the verifier. Recursive self-improvement is limited by verification, not com…

The bottleneck for AI progress was never compute, it was always the verifier. Recursive self-improvement is limited by verification, not computation. Compute buys proposals - verifiers buy knowledge.

researchyann-lecun--x

The Geometric Nature and a Free Proxy for Flow-Matching Uncertainty

arXiv:2607.27933v2 Announce Type: replace Abstract: Flow matching (FM) has become a popular action head paradigm for modern embodied models. However, as a conditional generative model, it does not exp

The Transformer Revolution, Part 1: Dynamic Processing through Output- Weight Interconnections

arXiv:2608.03921v1 Announce Type: new Abstract: This paper offers a new interpretation of the Transformer during inference. Against the 'stochastic parrot' view that large language models merely repro

Tight Worst-Case Bounds for the Smallest Eigenvalue of ReLU NTK Gram Matrices

arXiv:2608.03368v1 Announce Type: new Abstract: For n unit vectors x_1,ldots,x_n in R^d, we study the continuous ReLU derivative Gram matrix H, whose entries are obtained by averaging pairwise gated i

Topological Simplification in Predictive Coding Networks

arXiv:2608.02816v1 Announce Type: new Abstract: We study the topology of learned representations in predictive coding networks (PCNs), a neuro-inspired bidirectional architecture, using a quantitative

Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models

arXiv:2510.22014v2 Announce Type: replace-cross Abstract: Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto

Toward Visual Grounding: A Survey

arXiv:2412.20206v4 Announce Type: replace Abstract: Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) b

Towards a new paradigm of scientific discovery with socialized artificial intelligence

arXiv:2608.02775v1 Announce Type: new Abstract: Scientific discovery has advanced through successive transformations in the organization of knowledge. Observation and experimentation established the e

Towards Reliable and Reproducible Fetal Brain Biometry: A Deep Learning Approach Using MRI

arXiv:2608.03724v1 Announce Type: new Abstract: Fetal brain biometry is essential for quantitative assessment of brain development, supporting gestational age estimation, developmental monitoring, and

Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis

arXiv:2508.04551v2 Announce Type: replace Abstract: While recent advances in virtual try-on (VTON) have achieved realistic garment transfer to human subjects, its inverse task, virtual try-off (VTOFF)

UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space

arXiv:2608.03817v1 Announce Type: cross Abstract: Large vision--language models (LVLMs) demonstrate strong multimodal reasoning capabilities but remain prone to hallucination, where model predictions

UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search

arXiv:2503.00340v2 Announce Type: cross Abstract: Lightweight models are essential for real-time speech enhancement applications. In recent years, there has been a growing trend toward developing incr

Uncovering Spontaneous Physics Representations in In-Context Learning

arXiv:2508.12448v2 Announce Type: replace-cross Abstract: In-context learning (ICL) lets large language models (LLMs) solve new tasks from prompts alone, across an ever-widening range of domains, yet

UniEvo-RS: Omni-Prompt Unified Remote Sensing Segmentation with Representative Exemplar-Driven Prototype Evolution

arXiv:2608.03911v1 Announce Type: new Abstract: Prompt-driven vision-language models (VLMs) hold immense promise for accelerating dense remote sensing (RS) annotation, but static models suffer from se

UniGD: A Unified Generative-Discriminative Framework for Industrial Retrieval

arXiv:2608.03150v1 Announce Type: new Abstract: Generative retrieval (GR) is a promising paradigm for industrial search advertising, yet its deployment is constrained by strict relevance and latency r

UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations

arXiv:2604.14606v2 Announce Type: cross Abstract: Universal speech enhancement (USE) aims to restore speech signals from diverse distortions across multiple sampling rates. We propose UniPASE, an exte

Unsupervised Adversarial Domain Adaptation for Uterine layer Segmentation: From Labeled Cine to Unlabeled Dynamic EPI MRI

arXiv:2608.03762v1 Announce Type: cross Abstract: Uterine peristalsis is a key physiological phenomenon responsible for various functions across the menstrual cycle, intimately linked to uterine wall

V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors

arXiv:2608.03008v1 Announce Type: cross Abstract: As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and

Variational Approximated Restricted Maximum Likelihood Estimation for Spatial Data

arXiv:2604.07635v2 Announce Type: replace-cross Abstract: This research considers a scalable inference for spatial data modeled through Gaussian intrinsic conditional autoregressive (ICAR) structures.

Very interesting to see @JeffDean's pitch deck. Just look at those open science and engineering problems. Lots to advance there with automat…

Very interesting to see @JeffDean's pitch deck. Just look at those open science and engineering problems. Lots to advance there with automated ML engineering. AI for science and engineering is just ge

researchdair-ai--x

VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations

arXiv:2608.03675v1 Announce Type: new Abstract: Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in