Content Feed

The latest content from across the network

Ranked Latest Top this week
[2512.10411] SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing
Llms

[2512.10411] SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing

Abstract page for arXiv paper 2512.10411: SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing

arXiv - AI · 4 min ·
[2510.12117] Locket: Robust Feature-Locking Technique for Language Models
Llms

[2510.12117] Locket: Robust Feature-Locking Technique for Language Models

Abstract page for arXiv paper 2510.12117: Locket: Robust Feature-Locking Technique for Language Models

arXiv - Machine Learning · 3 min ·
[2512.00939] Constant-Time Motion Planning with Manipulation Behaviors
Nlp

[2512.00939] Constant-Time Motion Planning with Manipulation Behaviors

Abstract page for arXiv paper 2512.00939: Constant-Time Motion Planning with Manipulation Behaviors

arXiv - AI · 4 min ·
[2509.21385] Debugging Concept Bottleneck Models through Removal and Retraining
Machine Learning

[2509.21385] Debugging Concept Bottleneck Models through Removal and Retraining

Abstract page for arXiv paper 2509.21385: Debugging Concept Bottleneck Models through Removal and Retraining

arXiv - Machine Learning · 4 min ·
[2512.00804] Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval
Llms

[2512.00804] Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval

Abstract page for arXiv paper 2512.00804: Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval

arXiv - AI · 4 min ·
[2508.18768] Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits

[2508.18768] Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits

Abstract page for arXiv paper 2508.18768: Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits

arXiv - Machine Learning · 3 min ·
[2511.20721] Foundry: Distilling 3D Foundation Models for the Edge
Llms

[2511.20721] Foundry: Distilling 3D Foundation Models for the Edge

Abstract page for arXiv paper 2511.20721: Foundry: Distilling 3D Foundation Models for the Edge

arXiv - Machine Learning · 4 min ·
[2511.03255] Generative deep learning for foundational video translation in ultrasound
Machine Learning

[2511.03255] Generative deep learning for foundational video translation in ultrasound

Abstract page for arXiv paper 2511.03255: Generative deep learning for foundational video translation in ultrasound

arXiv - AI · 4 min ·
[2510.24821] Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
Machine Learning

[2510.24821] Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

Abstract page for arXiv paper 2510.24821: Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

arXiv - AI · 4 min ·
[2507.16058] Data-driven Mori-Zwanzig modeling of Lagrangian particle dynamics in turbulent flows
Machine Learning

[2507.16058] Data-driven Mori-Zwanzig modeling of Lagrangian particle dynamics in turbulent flows

Abstract page for arXiv paper 2507.16058: Data-driven Mori-Zwanzig modeling of Lagrangian particle dynamics in turbulent flows

arXiv - Machine Learning · 4 min ·
[2507.03689] A Resource Efficient Quantum Kernel
Machine Learning

[2507.03689] A Resource Efficient Quantum Kernel

Abstract page for arXiv paper 2507.03689: A Resource Efficient Quantum Kernel

arXiv - Machine Learning · 4 min ·
[2510.14989] Constrained Diffusion for Protein Design with Hard Structural Constraints
Machine Learning

[2510.14989] Constrained Diffusion for Protein Design with Hard Structural Constraints

Abstract page for arXiv paper 2510.14989: Constrained Diffusion for Protein Design with Hard Structural Constraints

arXiv - Machine Learning · 3 min ·
[2506.22504] Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection
Machine Learning

[2506.22504] Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection

Abstract page for arXiv paper 2506.22504: Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection

arXiv - Machine Learning · 4 min ·
[2510.10415] CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints
Nlp

[2510.10415] CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints

Abstract page for arXiv paper 2510.10415: CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints

arXiv - AI · 3 min ·
[2509.24296] DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
Llms

[2509.24296] DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

Abstract page for arXiv paper 2509.24296: DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

arXiv - AI · 4 min ·
[2509.19354] GeoResponder: Towards Building Geospatial LLMs for Time-Critical Disaster Response
Llms

[2509.19354] GeoResponder: Towards Building Geospatial LLMs for Time-Critical Disaster Response

Abstract page for arXiv paper 2509.19354: GeoResponder: Towards Building Geospatial LLMs for Time-Critical Disaster Response

arXiv - AI · 3 min ·
[2509.01388] End-to-End Low-Level Neural Control of an Industrial-Grade 6D Magnetic Levitation System
Machine Learning

[2509.01388] End-to-End Low-Level Neural Control of an Industrial-Grade 6D Magnetic Levitation System

Abstract page for arXiv paper 2509.01388: End-to-End Low-Level Neural Control of an Industrial-Grade 6D Magnetic Levitation System

arXiv - AI · 4 min ·
[2508.21435] MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation
Machine Learning

[2508.21435] MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation

Abstract page for arXiv paper 2508.21435: MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation

arXiv - AI · 4 min ·
[2505.21545] Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation
Machine Learning

[2505.21545] Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation

Abstract page for arXiv paper 2505.21545: Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation

arXiv - Machine Learning · 4 min ·
[2505.19046] When Models Don't Collapse: On the Consistency of Iterative MLE
Machine Learning

[2505.19046] When Models Don't Collapse: On the Consistency of Iterative MLE

Abstract page for arXiv paper 2505.19046: When Models Don't Collapse: On the Consistency of Iterative MLE

arXiv - Machine Learning · 4 min ·