AI.info

Latest Research — Page 61

Browse Latest Research on AI.info.

• FOCUS: DLLMs Know How to Tame Their Compute Bound
• PaveSync: A Unified and Comprehensive Dataset for Pavement Distress Analysis and Classification
• Minimizing Human Intervention in Online Classification
• Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection
• QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
• RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models
• LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
• Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference
• Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI
• SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG
• LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization
• TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models
• Low Cost, High Efficiency: LiDAR Place Recognition in Vineyards with Matryoshka Representation Learning
• Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition
• Reinforcement Learning from Compiler and Language Server Feedback
• Random Initialization of Gated Sparse Adapters
• The Structure of Relation Decoding Linear Operators in Large Language Models
• Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models
• Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths
• TINY_SCHILLER: A Drop-In German Drama Corpus for Small Language Models
• PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval
• De novo generation of functional terpene synthases using TpsGPT
• GraphMERT: Efficient and Scalable Distillation of Reliable Knowledge Graphs from Unstructured Data
• AnyUp: Universal Feature Upsampling
• WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
• Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery
• Self-Improving Large Language Models via Progressive Experience Evolution
• Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion
• Computational Hardness of Reinforcement Learning with Partial $q^π$-Realizability
• Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
• Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
• Spatio-Spectroscopic Representation Learning using Unsupervised Convolutional Long-Short Term Memory Networks
• On the Military Applications of Large Language Models
• Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans
• STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models
• Where Norms and References Collide: Evaluating LLMs on Normative Reasoning
• Olaf-World: Orienting Latent Actions for Video World Modeling
• Don't Just Fine-tune the Agent, Tune the Environment
• SoccerMaster: A Vision Foundation Model for Soccer Understanding
• TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction