research note
Message Passing Enables Efficient Reasoning
This paper addresses the efficiency and scalability limitations of current large language model (LLM) reasoning paradigms at inference time, particularly.
Research
Page 58 of 166
Skip to content
research note
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
This paper addresses the problem of Temporal Forgery Localization (TFL), which requires precisely identifying manipulated segments within long untrimmed.
research note
MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages
MultiSynt/MT is an open synthetic parallel corpus created by translating approximately 100 billion high-quality English tokens from Nemotron-CC into 36.
research note
Optimal Resource Utilization for Autonomous Laboratory Orchestrators
This paper addresses the complex problem of resource scheduling and execution orchestration in autonomous laboratories, using as a case study a robotic.
research note
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
This paper addresses the challenge of fine-grained visual reasoning in vision-language models (VLMs), particularly when critical visual details are small.
research note
Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences
This paper investigates the occurrence and persistence of hallucinated citations—fabricated or author-mismatched references—in peer-reviewed conference.
research note
Quantum vs. Classical Machine Learning: A Unified Empirical Comparison
This paper presents a first-of-its-kind unified empirical comparison between quantum machine learning (QML) models and their classical machine learning.
research note
Relation-Centric Open-Vocabulary 3D Gaussian Segmentation
The paper addresses the challenge of open-vocabulary 3D Gaussian segmentation, which requires both rich language understanding for diverse text queries.
research note
SAGE: Structured Agentic Graph Editing for Software Diagrams
SAGE presents a hybrid approach to editing software engineering diagrams by combining structured graph representations with language model (LLM) guided.
research note
Sensorless Four-Channel Control Architecture Using Inverse Dynamics Modeling for Human-Scale Bilateral Teleoperation
This paper addresses the challenge of achieving high transparency in human-scale bilateral teleoperation systems, which traditionally rely on costly and.
research note
Sign in the Air to Unlock: An Interface for authentication in Virtual and Augmented Reality Powered by Point-Voxel Cross-Attention Network
This paper addresses the challenge of user authentication within immersive Virtual and Augmented Reality (VR/AR) environments, where traditional methods.
research note
Social-Annotate: Self-Healing Browser Extension to Annotate and Collect Social Media Data
Social-Annotate addresses the critical challenge of collecting high-quality human-annotated social media data while preserving ecological validity.