AI.info

Latest Research — Page 122

Browse Latest Research on AI.info.

• DEPO: Dual-Efficiency Preference Optimization for LLM Agents
• WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
• Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines
• Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
• Geometric Robot Calibration Using a Calibration Plate
• What's the Catch? Evaluating Temporal Consistency in Vision-Language Models
• Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
• Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
• Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
• Towards Unified Vision Language Models for Forest Ecological Analysis in Earth Observation
• Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization
• UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
• Efficient Resource-Constrained Training of Transformers via Subspace Optimization
• Correlation Dimension of Auto-Regressive Large Language Models
• SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
• Differentially Private In-Context Learning with Nearest Neighbor Search
• Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions
• Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen
• ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
• LLM Rationalis? Measuring Bargaining Capabilities of AI Negotiators
• Building Patient Journeys in Hebrew: A Language Model for Clinical Timeline Extraction
• Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
• VIDEOP2R: Video Understanding from Perception to Reasoning
• MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
• Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs
• Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch
• Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
• MyGram: Modality-aware Graph Transformer with Global Distribution for Multi-modal Entity Alignment
• HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
• SCULPT: Subtractive Composition for 3D Part Generation
• Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System
• BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models
• Differential Perspectives: Epistemic Disconnects Surrounding the US Census Bureau's Use of Differential Privacy
• SiPhy: Single-Image Physical Property Reasoning
• Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
• ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
• From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures
• KAN-GCN: Combining Kolmogorov-Arnold Network with Graph Convolution Network for an Accurate Ice Sheet Emulator
• MOVA: Towards Scalable and Synchronized Video-Audio Generation
• Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks