![[2603.10652] Are Video Reasoning Models Ready to Go Outside?](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Llms
[2603.10652] Are Video Reasoning Models Ready to Go Outside?
Abstract page for arXiv paper 2603.10652: Are Video Reasoning Models Ready to Go Outside?
arXiv - AI
·
4 min
·
AI Infrastructure
GPUs, training clusters, MLOps, and deployment
Top This Week
Machine Learning
[2602.00181] CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
Abstract page for arXiv paper 2602.00181: CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
arXiv - AI
·
4 min
·
Llms
[2512.06443] Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
Abstract page for arXiv paper 2512.06443: Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
arXiv - AI
·
4 min
·
All Content
Nlp
[2510.02348] mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations
The paper introduces mini-vec2vec, an efficient method for aligning text embedding spaces using linear transformations, significantly imp...
arXiv - AI
·
3 min
·
Llms
[2510.01143] Generalized Parallel Scaling with Interdependent Generations
The paper presents a novel approach, Bridge, for parallel scaling in LLM inference that generates interdependent responses, enhancing acc...
arXiv - Machine Learning
·
3 min
·
Llms
[2510.00565] Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
This paper explores vulnerabilities in diffusion language models (DLMs) related to priming attacks and proposes a novel safety alignment ...
arXiv - Machine Learning
·
4 min
·
Ai Infrastructure
[2509.14461] Learning depth-3 circuits via quantum agnostic boosting
This article introduces quantum agnostic learning protocols for depth-3 circuits, showcasing a quantum agnostic boosting method that enha...
arXiv - Machine Learning
·
4 min
·
Ai Agents
[2602.15721] Lifelong Scalable Multi-Agent Realistic Testbed and A Comprehensive Study on Design Choices in Lifelong AGV Fleet Management Systems
The paper presents LSMART, an open-source simulator for evaluating Multi-Agent Path Finding (MAPF) algorithms in Automated Guided Vehicle...
arXiv - AI
·
4 min
·
Machine Learning
[2507.01110] A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memory
The paper presents a novel framework, A LoD of Gaussians, for ultra-large-scale scene reconstruction and rendering using Gaussian splatti...
arXiv - Machine Learning
·
4 min
·
Machine Learning
[2410.11855] Online GPU Energy Optimization with Switching-Aware Bandits
This paper presents EnergyUCB, a novel online GPU energy optimization method using a multi-armed bandit approach to balance performance a...
arXiv - Machine Learning
·
4 min
·
Machine Learning
[2602.15564] Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
The paper presents a novel approach to Text-to-SQL systems by introducing dynamic workflows that adapt during inference, enhancing perfor...
arXiv - AI
·
3 min
·
Machine Learning
[2405.20178] Non-intrusive data-driven model order reduction for circuits based on Hammerstein architectures
This paper presents a non-intrusive data-driven model order reduction method for circuits using Hammerstein architectures, demonstrating ...
arXiv - Machine Learning
·
4 min
·
Llms
[2602.15549] VLM-DEWM: Dynamic External World Model for Verifiable and Resilient Vision-Language Planning in Manufacturing
The paper introduces VLM-DEWM, a novel cognitive architecture designed to enhance vision-language planning in manufacturing by addressing...
arXiv - AI
·
4 min
·
Machine Learning
[2602.08032] Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
The paper presents Horizon Imagination (HI), an innovative on-policy imagination process for reinforcement learning using diffusion-based...
arXiv - Machine Learning
·
3 min
·
Nlp
[2602.15491] The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs
The paper presents Shape-Gain Decomposition for Neural Audio Codecs, enhancing bitrate-distortion performance and reducing complexity by ...
arXiv - AI
·
4 min
·
Machine Learning
[2602.00240] Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting
Green-NAS presents a multi-objective neural architecture search framework aimed at optimizing weather forecasting models for low-resource...
arXiv - Machine Learning
·
4 min
·
Ai Infrastructure
[2602.15377] Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework
This paper presents an orchestration-free framework for customer service automation, utilizing Task-Oriented Flowcharts (TOFs) to enhance...
arXiv - AI
·
3 min
·
Machine Learning
[2601.01016] Improving Variational Autoencoder using Random Fourier Transformation: An Aviation Safety Anomaly Detection Case-Study
This study explores enhancements to Variational Autoencoders (VAEs) using Random Fourier Transformation (RFT) for anomaly detection in av...
arXiv - Machine Learning
·
4 min
·
Machine Learning
[2512.04189] BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
The paper presents BEP, a novel Binary Error Propagation algorithm for training Binary Neural Networks (BNNs) that enables efficient back...
arXiv - AI
·
4 min
·
Machine Learning
[2512.01389] Syndrome-Flow Consistency Model Achieves One-step Denoising Error Correction Codes
The paper presents the Error Correction Syndrome-Flow Consistency Model (ECCFM), which enhances one-step denoising error correction codes...
arXiv - AI
·
4 min
·
Llms
[2602.15353] NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
The paper presents NeuroSymActive, a novel framework for Knowledge Graph Question Answering that integrates differentiable neural-symboli...
arXiv - AI
·
3 min
·
Llms
[2602.15318] Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs
The paper introduces Sparrow, a novel framework designed to enhance speculative decoding in Video Large Language Models (Vid-LLMs) by opt...
arXiv - AI
·
4 min
·
Machine Learning
[2508.11460] Calibrated and uncertain? Evaluating uncertainty estimates in binary classification models
This article evaluates uncertainty estimates in binary classification models, comparing six probabilistic machine learning algorithms to ...
arXiv - Machine Learning
·
4 min
·
Related Topics
Stay updated with AI News
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime