Search: “research”

Calibrated Test-Time Guidance for Bayesian Inference

arXiv:2602.22428v2 Announce Type: replace-cross Abstract: Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existin

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models

DGX agent

arXiv:2607.00862v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequ

researcharxiv-cs-ai

2 Jul 2026

CausalMix: Data Mixture as Causal Inference for Language Model Training

arXiv:2607.01104v1 Announce Type: cross Abstract: In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via

Characterizing and Identifying Separable Graphical Models

arXiv:2607.01057v1 Announce Type: cross Abstract: We study a broad class of graphical models whose independencies correspond to vertex separation in mixed graphs with directed, undirected, and bidirec

China added over 543 Gigawatts to their grid last year. 434 GW was renewables because they are faster to build. The U.S. added a paltry 53 G…

China added over 543 Gigawatts to their grid last year. 434 GW was renewables because they are faster to build. The U.S. added a paltry 53 GW. We are losing the “AI race” to China because these idiots

researchyann-lecun--x

Closed-loop coupling of personalised and foundation models for real-time treatment guidance with MRI

arXiv:2607.00500v1 Announce Type: cross Abstract: Image-guided therapies, including radiotherapy, biopsy and deep brain stimulation, rely on real-time targeting of anatomical structures. However, in t

Constructing Epistemic AI Literacy: Detecting Epistemic Aims and Processes in Student-AI Co-Programming

arXiv:2607.00211v1 Announce Type: new Abstract: Epistemic thinking plays a central role in students' learning processes when applying generative artificial intelligence (GenAI), particularly in progra

Controllable Diffusion-Based Lesion Inpainting for Scalable Histopathology Data Augmentation

arXiv:2601.08127v2 Announce Type: replace-cross Abstract: Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens o

Controllable Narrative Rendering for Enhanced Assisted Writing

arXiv:2607.00009v1 Announce Type: cross Abstract: Despite the remarkable proficiency of large language models (LLMs) in basic writing assistance, their utility in creative writing is fundamentally hin

Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks

arXiv:2607.00553v1 Announce Type: cross Abstract: Lightweight machine learning models are increasingly proposed for intrusion detection in Industrial Internet of Things (IIoT) networks due to their su

Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning

arXiv:2607.00514v1 Announce Type: cross Abstract: Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and e

Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

arXiv:2604.02270v2 Announce Type: replace-cross Abstract: Generative models for crystalline materials often rely on equivariant graph neural networks, which capture geometric structure well but are co

DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding

arXiv:2607.00672v1 Announce Type: new Abstract: Zero-shot video temporal grounding (VTG) localizes events in untrimmed videos from natural language queries without task-specific training. Existing met

DART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation

arXiv:2607.01043v1 Announce Type: cross Abstract: Memory-based discrete vision-language navigation (VLN) agents must act under partial observability, yet even strong frozen backbones remain vulnerable

Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners

arXiv:2607.00125v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot im

Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization

arXiv:2607.00766v1 Announce Type: new Abstract: Text-to-image personalization aims to generate a user-provided subject in novel scenes described by text. However, most existing methods encode subject

Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range

arXiv:2603.16565v2 Announce Type: replace-cross Abstract: This article presents a deep learning-driven inverse design methodology for Doherty power amplifiers (PA) with multi-port pixelated output com

Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity

arXiv:2607.00995v1 Announce Type: cross Abstract: Most existing multitask learning approaches are limited by their reliance on task-specific loss functions tailored to the scale and type of each outco

Destination-Labeled Self-Looping Systems with Dwell: Intrinsic Characterization, Realization Cost, and Recognition

arXiv:2607.00044v1 Announce Type: cross Abstract: We study a finite-state symbolic controller for systems in which the admissible visible transitions are fixed in advance and each visible state carrie

Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts

arXiv:2607.00249v1 Announce Type: new Abstract: New device layouts pose a challenging modeling problem due to the lack of large datasets for each specific layout. Biosignal foundation models offer a p

DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors

arXiv:2607.00889v1 Announce Type: cross Abstract: We present DeWorldSG, a novel framework that generates spatio-temporally robust 3D Semantic Scene Graphs from RGB-D sequences. Existing methods often

Did a long chat with @yayitsrob on Shift Key about the Gigascale thesis, hard tech, and why the 'US can't build anything' take is wrong. A f…

Yann LeCun discussed the Gigascale thesis, hard technology development, and challenged the narrative that the US lacks manufacturing and building capabilities in a conversation with @yayitsrob on Shif

researchyann-lecun--x

Diffusion-Based Multi-Class Normality for OOD Detection: An Application to CDP Authentication

arXiv:2607.00609v1 Announce Type: new Abstract: Reconstruction-based generative models offer a natural framework for unsupervised out-of-distribution (OOD) detection, but multi-class normality modelli

Disentangling Speaker and Language Effects in Cross-Lingual Speaker Verification for Iberian Languages

arXiv:2607.01161v1 Announce Type: cross Abstract: Cross-lingual speaker verification (SV) systems typically exhibit performance degradation when enrollment and test utterances are spoken in different

researcharxiv-cs-cl

Distributed Online Bandit Submodular Maximization with Bounded Sampling Violations

arXiv:2607.00680v1 Announce Type: new Abstract: We study distributed online submodular maximization under partition matroid constraints, in which multiple agents select a limited number of actions fro

Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting

arXiv:2606.18367v2 Announce Type: replace Abstract: Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating

'Don't Say It!': Constraints, Compliance, and Communication when Language Models Play Taboo

arXiv:2607.00601v1 Announce Type: new Abstract: The game of Taboo requires describing a target word without using a set of forbidden words, so that other players can guess it. This deceptively simple

researcharxiv-cs-cl

DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble

arXiv:2607.00416v1 Announce Type: new Abstract: We present DroneIQA-VLE, our solution to the ICME 2026 Drone-IQA Grand Challenge on Target-aware Image Quality Assessment for Low-altitude UAV Images. T

E-TIDE: Fast, Structure-Preserving Motion Forecasting from Event Sequences

arXiv:2603.27757v2 Announce Type: replace Abstract: Event-based cameras capture visual information as asynchronous streams of per-pixel brightness changes, generating sparse, temporally precise data.

Efficient Multilingual Reasoning Transfer via Progressive Code-Switching

arXiv:2607.00485v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong reasoning capabilities in English, yet their performance degrades significantly when required to reas

researcharxiv-cs-cl

Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing

arXiv:2602.02157v2 Announce Type: replace Abstract: Neural Controlled Differential Equations (Neural CDEs) provide a powerful continuous-time framework for sequence modeling, yet the roughness of the

Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution

arXiv:2508.11664v2 Announce Type: replace-cross Abstract: Sleep stage classification is critical for diagnosing and managing disorders like sleep apnea and insomnia. However, conventional methods like

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

arXiv:2607.00363v1 Announce Type: cross Abstract: Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To a

Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention

arXiv:2607.00057v1 Announce Type: cross Abstract: Oracle Bone Inscriptions (OBIs) recognition plays a crucial role in understanding ancient Chinese culture. However, accurately recognizing OBIs remain

Enhancing Robustness in Robot-Environment Interactions through Passive Compliant Degrees of Freedom: A Hybrid Position-Force Control Approach with Feedback Linearization

arXiv:2607.00571v1 Announce Type: new Abstract: Robot-environment interactions in dynamic or unstructured settings are often degraded by impact shocks, vibrations, and uncertainties in contact geometr

researcharxiv-cs-ro

EO-VGGT: Orbital Ray-Conditioned 3D Foundation Models for Satellite Multi-View Reconstruction

arXiv:2607.00417v1 Announce Type: cross Abstract: In the era of satellite constellations, multi-view optical satellite imagery is pivotal for Earth Observation (EO) and high-quality Digital Surface Mo

Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition

arXiv:2607.00777v1 Announce Type: cross Abstract: Recognizing jazz standards from audio is a challenging form of tune-level music retrieval: different performances of the same standard may vary in tem

Even right now, many workflows are morphing into LRM-guided harnessess that manipulate symbolic programs. Which is a crude, but currently-ac…

researchfrancois-chollet--x

Francois Chollet discusses how current workflows are increasingly incorporating Large Reasoning Models (LRMs) as control systems that direct symbolic programs and tools, representing a pragmatic but i

Eventually, much of AI will converge towards intuition-guided symbolic world modeling, i.e. deep learning-guided program synthesis. It is in…

researchfrancois-chollet--x

Eventually, much of AI will converge towards intuition-guided symbolic world modeling, i.e. deep learning-guided program synthesis. It is inevitable. Symbolic modeling lets a system construct a compac

Explainability in mulimodal deep transformation models for stroke outcome prediction

arXiv:2504.06299v2 Announce Type: replace-cross Abstract: Multimodal prediction models based on imaging and clinical data are increasingly used for clinical decision support, yet their interpretabilit

Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions

arXiv:2607.00931v1 Announce Type: new Abstract: Predicting cancer drug response from transcriptomic profiles is a cornerstone of precision oncology, yet the scientific value of machine learning models

Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications

arXiv:2607.00661v1 Announce Type: cross Abstract: Explanations for emotion classifiers are usually produced post hoc, with no guarantee that they reflect the computation behind the label. We present a

FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning

arXiv:2603.22969v2 Announce Type: replace Abstract: Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask a

Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds

arXiv:2606.18218v2 Announce Type: replace-cross Abstract: We study finite-horizon queue peaks in generalized switches, a standard stochastic-network model in which many queues share constrained servic

FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning

arXiv:2508.04064v2 Announce Type: replace-cross Abstract: Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR)

Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition

arXiv:2607.00535v1 Announce Type: cross Abstract: Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between nois

Flow-Through Tensors: A Unified Computational Graph Architecture for Multi-Layer Transportation Network Optimization

arXiv:2507.02961v2 Announce Type: replace-cross Abstract: Modern transportation network modeling increasingly involves the integration of diverse methodologies including sensor-based forecasting, rein

Forensic-Oriented Intrusion Detection Using Synthetic Network Traffic Data and Explainable Artificial Intelligence

arXiv:2607.00763v1 Announce Type: cross Abstract: Digital forensic investigations of network intrusions require analytical outputs that are traceable, reproducible, and court-defensible - requirements